National implementation of a digital Parkinson’s disease screening programme in Thailand: reach, usability, and real-world performance of the CheckPD app

National implementation of a digital Parkinson’s disease screening programme in Thailand: reach, usability, and real-world performance of the CheckPD app | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article National implementation of a digital Parkinson’s disease screening programme in Thailand: reach, usability, and real-world performance of the CheckPD app Roongroj Bhidayasiri, Saisamorn Phumphid, Jirada Sringean, Chanawat Anan, and 40 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8565015/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 15 You are reading this latest preprint version Abstract Background Parkinson’s disease (PD) remains underdiagnosed in Thailand, and its rising prevalence presents a growing challenge for the healthcare system. The previously validated CheckPD digital population screening platform has been implemented nationally in collaboration with the Thai Red Cross Society (TRCS) and the National Health Security Office (NHSO), enabling integration of digital PD risk screening into preventive health frameworks. Objective To evaluate the early phase of a national rollout of the CheckPD platform, focusing on population reach, usability, predictive performance, and implementation factors influencing adoption and scalability across diverse real-world settings. Methods This mixed-methods implementation study undertaken in 10 screening provinces in Thailand was guided by the RE-AIM framework. Usability was assessed using the System Usability Scale (SUS) and task-completion metrics. AI-predicted PD risk was compared with diagnoses made by neurologists. Qualitative feedback was collected from Village Health Volunteers and Public Health Officers. Data storage and governance complied with Thailand’s Personal Data Protection Act of 2019. Results Between January 2024 and October 2025, 13,381 out of 21,882 users completed screening across 10 provinces (completion rate: 72%). The mean SUS score was 83, with a 92% first-time task completion rate. Programme reach was achieved through multiple channels, including Village Health Volunteers (6,742 participants), community field campaigns (5,207), online training initiatives (3,172), and self-initiated app downloads (2,080). When compared with neurologists’ diagnoses, the screening demonstrated a positive predictive value of 89.15%. Key facilitators of implementation included TRCS endorsement and network support, community volunteer engagement, and user-centred app design. Logistic regression analysis identified that barriers to completing the CheckPD app screening tests included a lower educational level and a more rural geographical location suggesting some disparities in access. Conclusions The CheckPD programme demonstrates that national-scale digital screening for neurological disorders is feasible in a low-to-middle-income country when embedded within trusted institutions, supported by community networks, and aligned with data protection standards. Thailand’s experience provides a scalable and replicable model for implementing population-level improvements in brain health by allowing early detection and assessment of those at individuals at risk, aligning with the World Health Organization’s Brain Health framework. Parkinson’s disease Thailand Digital interventions Non-communicable diseases Healthcare policy Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Background Parkinson’s disease is a significant public health issue. Parkinson’s disease (PD) is one of the fastest-growing neurological disorders worldwide and represents an increasing public health challenge in ageing societies [ 1 ]. Its global prevalence has increased markedly over the past three decades, driven largely by population ageing and longer disease duration, with additional contributions from environmental risk factors such as exposure to pesticides and other pollutants [ 2 – 4 ]. Projection studies have estimated that by 2050, globally 25.2 million people will be living with PD, representing a 112% increase from 2021, and this rise is expected to be more pronounced among low-to-middle-income countries (LMICs) [ 5 , 6 ]. In Thailand, epidemiological studies using data from the national Parkinson's Disease Registry have established that PD is generally under-reported but have estimated an age-adjusted prevalence of 424.57 PD cases/100,000 of the population, with a significantly higher prevalence in rural versus urban areas [ 7 ]. PD is associated with progressive motor and non-motor disability, reduced quality of life, and substantial long-term healthcare and societal costs [ 8 , 9 ]. Despite the availability of effective symptomatic treatments, delays in receiving a definitive diagnosis of PD are common, limiting opportunities for early intervention, risk modification, and timely access to specialist care [ 10 ]. These challenges are particularly pronounced in LMICs where healthcare resources and specialist capacity may be lacking, and where disparities in access to these services exist between urban and rural areas [ 11 ]. In Thailand, for example, definitive diagnosis of PD is often delayed by 2–3 years, partly due to limited availability of movement disorders specialists [ 7 , 11 ]. Currently, Thailand has 926 neurologists, however most are located in larger provinces, such as Bangkok, Chiang Mai, and Chonburi, with far fewer in rural areas, resulting in inequitable access to specialist care [ 12 – 14 ]. Prompt diagnosis of PD and referral for specialist care at its early stages is essential to avoid people living with the consequences of debilitating motor and non-motor PD symptoms, to maximise their long-term outcomes, and to minimise the impact on the healthcare system. Gaps in current PD detection and prevention strategies When PD remains undiagnosed and untreated, progression to advanced stages is associated with profound deterioration in quality of life for patients and caregivers, alongside escalating requirements for long-term supportive and social care. Correspondingly, the economic burden on healthcare systems and society increases substantially, with costs of care for advanced PD far exceeding those associated with early detection and management [ 8 , 15 – 17 ]. The rising demand for timely PD diagnosis and effective treatment poses growing challenges to national health systems, economic sustainability, and workforce capacity. These pressures underscore the urgent need to shift from predominantly reactive care models towards preventive, population-based strategies that facilitate earlier risk identification and intervention at scale [ 18 , 19 ]. In line with recommendations from the Global Burden of Disease Study and related initiatives, prioritising prevention of non-communicable diseases (NCDs), including PD, alongside the development of clear treatment pathways and the strengthening of health system infrastructure, is essential to mitigate long-term neurological disease burden [ 20 , 21 ]. While the timely identification of PD across populations seems like a logical approach to the problem, there are often significant barriers to its practical implementation at a primary and secondary care level within national healthcare systems and infrastructures [ 22 ]. In Thailand, the majority of the population lives in remote or rural areas so traditional face-to-face assessment in a clinic is not always feasible and can be resource intensive, plus specialist PD expertise may not be easily available [ 11 ]. It is clear that in order to address these challenges, there is a need for simple, accessible, and preventive approaches that can be deployed nationally and equitably across both urban and rural populations. Population-level digital health interventions provide a scalable mechanism to address these implementation barriers by enabling systematic early risk detection while supporting more efficient allocation of specialist and healthcare resources [ 23 ]. . Digital screening as a public health strategy Digital tools and innovative technologies powered by artificial intelligence (AI) and machine learning are increasingly being adopted across multiple areas of medicine, including PD, to support clinicians in diagnosis, monitoring, and treatment decision-making [ 24 – 27 ]. The use of AI-supported digital tools for population health screening offers substantial advantages over traditional methods in terms of speed, scalability, remote accessibility, and systematic data collection to better quantify disease burden. As a result, these approaches have particular value for LMICs, especially in remote or underserved areas where healthcare resources are constrained [ 28 – 30 ]. Globally, a wide range of digital health screening tools has been evaluated across diverse disease contexts [ 31 ]. Examples include the UK’s National Health Service digital portal, which enables citizens to access health services, including screening, and self-management resources [ 32 ] and India’s MadhuNETrAI, an AI-driven mobile application developed for national diabetic retinopathy screening [ 33 ]. The benefits of digital health tools have also been demonstrated in mental health and cognitive or neurocognitive population screening [ 34 – 36 ], with the World Health Organization (WHO)’s Mental Health Gap Action Programme (e-mhGAP) aiming to leverage such tools to scale services for mental, neurological, and substance use disorders globally. Within Southeast Asia, initiatives in Indonesia, Vietnam, Malaysia, and Thailand illustrate how mobile- and tablet-based platforms are being adopted for screening of chronic diseases and geriatric health conditions, helping to overcome longstanding barriers related to access, workforce limitations, and geographic inequities [ 37 – 40 ]. Thailand already has a well-established example of large-scale, AI-enabled population screening through its national diabetic retinopathy programme. In this programme, a deep-learning system has been prospectively deployed across multiple primary care sites to deliver real-time diabetic retinopathy detection with specialist-level accuracy, demonstrating both feasibility and effectiveness within a middle-income country health system [ 41 ]. This initiative highlights how AI-supported digital screening can be successfully integrated into routine workflows, particularly in settings with limited specialist availability. Against this backdrop, the implementation of digital PD risk screening platforms, such as CheckPD, represents a logical extension of established national digital screening strategies, applying similar principles of early identification, task-shifting, and scalability to the growing neurological disease burden. Thailand’s digital readiness and constraints Table 1 shows an overview of internet use, devices, and access locations in Thailand. Most people use the internet, and mobile phone subscriptions are higher than the total population, showing that mobile connectivity is very common. On average, people spend more than seven hours per day online, with much of this time spent using mobile phones. This shows that mobile internet use is dominant in Thailand [ 42 ]. Smartphones are the main device used to access the internet, while desktops, laptops, and tablets are used by far fewer people. This indicates a strong reliance on smartphones and limited use of advanced computing devices. Most users access the internet at home, followed by workplaces and private service centres. Public access locations are used less often. Overall, internet access in Thailand is widespread but mainly mobile-based and home-centred [ 43 ]. Table 1 Statistics on internet use, device access and device use in Thailand. Indicator Value Internet access Internet users (% of population) 91.2% (65.4 million people) Mobile phone subscriptions (% of population) 139% (99.5 million numbers) Average daily internet use 7 hours 54 minutes Internet use via mobile phones 5 hours per day (63.3%) Main devices for internet access Smartphones 99.6% Desktops 16.7% Laptops 10.6% Tablets 2.8% Common internet access locations Home 95.9% Work 38.3% Private centers 27.5% Public centers 14.2% Note: Totals exceed 100% as users can use more than one device and more than one access location. However, as some older Thai adults may face challenges when using digital tools due to low levels of digital literacy, lack of confidence, or limited internet accessibility [ 44 – 46 ] it is important that health care apps are designed to be inclusive to all potential users as well as having support to facilitate engagement. Within this context, community health volunteers (also known as Village Health Volunteers, VHV) represent a critical enabling resource for bridging digital gaps between citizens and healthcare systems. VHVs have an established role in Thailand’s primary healthcare infrastructure and are well positioned to support the adoption of digital health tools at the community level [ 47 , 48 ]. Through targeted training, volunteers can assist individuals in navigating mobile and online health applications, provide hands-on support for initial use, and reinforce confidence in digital health participation. This community-embedded support model offers a practical strategy to enhance equitable uptake of digital health interventions, particularly among older adults and populations with limited digital literacy. The CheckPD platform and its benefits as a national screening tool The digital screening platform evaluated in this study, hereafter referred to as CheckPD, is a multimodal, AI-assisted mobile application that has been specifically developed for population-level PD screening in Thailand (ClinicalTrials.gov registration number: NCT06609681). The protocol for national digital screening using CheckPD has been described previously and established the suitability of CheckPD for national rollout under the Royal Patronage of Her Royal Highness the Princess, in collaboration with the Thai Red Cross Society (TRCS) and the National Health Security Office (NHSO) [ 49 ]. CheckPD employs AI-driven multimodal assessment methods that integrate a structured questionnaire on PD symptoms and risk factors with digital analyses of tapping, tremor, gait, and voice parameters, and is implemented within a governance framework aligned with Thailand’s Personal Data Protection Act (PDPA). Preliminary analyses focusing on participants reporting hyposmia and probable REM sleep behaviour disorder (RBD) have been presented as posters at the International Congress of Parkinson’s Disease and Movement Disorders Annual Meeting in October 2025 [ 50 , 51 ]. Recent studies have highlighted usability and human-centred design (HCD) as essential criteria for effective digital health screening platforms, particularly for older adults [ 52 , 53 ]. Successful designs prioritise accessibility, comfort, and user trust by focusing on user needs rather than technological complexity alone [ 54 ]. Evidence indicates that inclusive interfaces, clear instructions, and adaptable features enable older users and individuals with motor or cognitive challenges to engage confidently with digital tools, while design elements such as clear typography, strong colour contrast, and uncluttered layouts further enhance readability and usability in ageing populations [ 55 – 57 ]. Despite the rapid growth of digital tools developed for PD, most existing platforms have been conceived primarily as research instruments or as disease assessment and symptom-monitoring tools for individuals with established diagnoses (Table 2 ). The majority were developed within controlled research settings, often to validate specific digital biomarkers, such as gait variability, tremor amplitude, voice features, or freezing of gait, rather than to function as end-to-end screening solutions deployable at scale. Consequently, these platforms tend to be purpose-specific, targeting narrowly defined clinical or research questions, and are rarely designed for population-level implementation, integration into routine healthcare systems, or linkage to formal referral pathways. In addition, the level of evidence supporting their utility varies considerably, ranging from small proof-of-concept studies and short-term validation cohorts to larger longitudinal research datasets, with few demonstrating real-world effectiveness or sustainability beyond research contexts. As a result, their clinical and public health applicability remains limited when considered in the context of large-scale, population-based screening programmes [ 58 – 60 ]. In contrast, CheckPD was purposefully designed from inception as an accessible, HCD-driven, informed digital screening platform capable of operating at a national scale in real-world settings. Rather than focusing on a single symptom domain, the application integrates multimodal assessments and is embedded within Thailand’s healthcare infrastructure through a formal memorandum of understanding with the NHSO. This enables clearly defined referral pathways following risk identification. When screening results indicate an elevated risk of PD, the app automatically directs users to registered hospitals within the national health system for further clinical evaluation. A comparative overview of CheckPD and selected global PD digital platforms, highlighting differences in purpose, evidence base, scalability, and system integration, is presented in Table 2 . Table 2 Comparison of the features of CheckPD with those of other selected global PD digital platforms. Platform Country Setting Primary purpose Key features Strengths Limitations Screening or diagnosis CheckPD [ 49 ] Thailand Real world National PD screening and risk stratification Multimodal AI (tapping, tremor, balance, voice), questionnaire, offline-first, VHV integration, cloud dashboards Only national-scale PD screening system; strong usability; policy integration; PDPA compliance; real-world deployment Requires device capability; follow-up clinical pathways still developing mPower [ 95 , 96 ] USA Research Research data collection and digital biomarker discovery Tapping, gait, voice tasks; ResearchKit; large open dataset Massive user base; open science; high-frequency longitudinal data Not designed for clinical screening; variable data quality; no health-system integration PREDICT-PD [ 97 , 98 ] UK Research Early detection research in high-risk PD Online questionnaires, smell tests, risk modeling Strong epidemiological base; long-term longitudinal follow-up No motor-sensor tasks; not mobile-first; limited scalability KeySense [ 99 ] USA Real world Early detection and self-screening for Parkinson’s disease Typing-based motor assessment (KeySense®), AI analysis of keystroke dynamics, web-based access, no wearable devices required Simple and non-invasive screening; accessible via standard computer keyboard; free public access; focuses on early detection Not a clinical diagnostic tool; limited multimodal assessment (no voice, gait, or tremor sensors); requires desktop or laptop keyboard; limited integration with healthcare systems Smartphone motor testing app [ 100 ] UK Research Differentiate PD, iRBD, and controls using smartphone motor tasks Voice, gait, balance, tapping, tremor tasks; smartphone sensors; ML classification High accuracy; low-cost; captures real-world motor data Research-only; data quality depends on user compliance; not a deployed screening system Roche PD Mobile Application v2 [ 101 ] Click or tap here to enter text. Switzerland Research Remote monitoring of motor symptoms in early PD Smartphone & smartwatch tests (tapping, tremor, gait, balance, speech); passive monitoring High reliability and validity; frequent at-home assessment Research-only; focused on early-stage PD; not deployed for population screening APDM Mobility Lab [ 102 ] Click or tap here to enter text. USA Research Objective gait and balance assessment in PD Wearable IMU sensors; gait, balance, turning measures Validated, reliable; sensitive to PD severity and progression Research-focused; requires sensors; not population screening Motor symptom monitoring Hopkins PDKit [ 103 ] Click or tap here to enter text. USA Research Open-source digital biomarker toolkit Python-based pipeline for gait, tapping, voice; harmonization of mobile sensor data Enables reproducible analysis; strongly used in academic research Not a patient-facing screening app; requires programming expertise SmartMOVE [ 104 ] Singapore Research Objective gait assessment and gait variability analysis in PD Smartphone accelerometer and gyroscope; step time and step length variability; validation against footswitches and the gait mat system Clinically validated accuracy; low-cost and portable; suitable for clinic and home use Small sample size; focused on gait only; not designed for large-scale screening or health-system integration STOP App – Smartphone-based tremor monitoring [ 105 ] Click or tap here to enter text. Finland / UK Research Remote monitoring of hand tremor severity and medication effects in PD Smartphone accelerometer; gamified ball-balancing task; tremor intensity parameter (TIP); before/after medication analysis Objective tremor quantification; correlates with UPDRS; feasible real-world monitoring Small sample size; focuses mainly on hand tremor; device variability; not designed for population screening Smartphone-based FOG Monitoring System [ 106 ] Italy Research Home assessment and real-time detection of freezing of gait (FOG) in Parkinson’s disease Smartphone inertial sensors; fuzzy logic algorithm; spatio-temporal gait parameters (step cadence, step length); frequency-domain features; real-time FoG detection; home and laboratory validation High detection accuracy (AUC up to 0.94); interpretable knowledge-based model; real-time processing; strong agreement with clinician assessment; high usability for home monitoring Focused on FOG only (not full PD screening); requires calibration by clinicians; limited sample size; not designed as population-scale screening or integrated health system platform Smartphone-based Turning Assessment [ 107 ] Italy Research Remote assessment of motor impairment in PD Smartphone inertial sensors; turning task analysis; QoM index; ML classification Objective digital biomarker; correlates with clinical scales; low-cost home monitoring Limited to turning tasks; small sample size; not suitable for population-scale screening Smartphone-based Gait Assessment App [ 108 ] China / USA Research Objective assessment of gait impairment and disease severity in PD Smartphone IMU (accelerometer, gyroscope); single- and dual-task walking; stride time and variability; cloud data upload High validity vs. gold-standard sensors; correlates with UPDRS, cognition, and mood; low-cost and portable Clinic-based validation only; small sample size; focuses on gait only; not designed for large-scale screening Smartphone-based FOG Detection System [ 109 ] South Korea Research Objective detection of freezing of gait (FOG) in PD Smartphone accelerometer & gyroscope; unconstrained body placement (waist, pocket, ankle); machine learning (AdaBoost); real-world gait data High sensitivity (up to 86%); no external sensors required; practical daily-life deployment Focused only on FOG; small sample size; requires labeled data; not a comprehensive PD screening system Smartphone-based RPM [ 110 ] Italy Research Remote monitoring of PD patients during lockdown Smartphone app for gait, tapping, tremor, balance, cognition; questionnaires; telemonitoring Feasible home monitoring; good patient compliance; correlates with clinical scales (UPDRS, H&Y) Small sample size; short study duration; no control group; requires digital literacy Symptom fluctuation, behavior, and intervention support EMA eDiary for PD [ 111 ] Netherlands Research Daily-life monitoring of motor and non-motor symptom fluctuations in PD Smartphone-based ecological momentary assessment (EMA); repeated questionnaires on affect, motor function, context; free-living monitoring Captures intraday symptom fluctuations; good internal validity; patient-centered monitoring Small sample size; subjective self-report; not designed for screening or population-scale deployment 9zest Exercise App [ 112 ] Click or tap here to enter text. USA Research Home-based exercise support for people with PD Smartphone app; personalized video-guided exercise; in-app assessments (STS, TUG, PDQ-8); adaptive algorithm Safe and feasible; improves mobility, strength, and quality of life; accessible home use Small sample size; high dropout; not designed for screening or diagnosis mHealth-supported exercise program [ 113 ] USA Research Promote physical activity in people with PD Mobile app–supported home exercise, step tracking, remote monitoring, behavioral feedback Improves physical activity and mobility, especially in less active patients; safe and acceptable Small sample size; not a screening or diagnostic tool; limited generalizability ImageVis3D Mobile for DBS [ 114 ] Click or tap here to enter text. USA Real world Clinical decision support for DBS parameter selection in PD Mobile interactive visualization; patient-specific DBS models; visualization of electrode location and volume of tissue activated (VTA) Faster DBS parameter selection; comparable to standard care; intuitive mobile interface Requires precomputed models; limited patient sample; focused on DBS programming, not PD screening AI, artificial intelligence; ML, machine learning PD, Parkinson’s disease; PDPA, Personal Data Protection Act; VHV, Village Health Volunteers; STOP, Sentient Tracking of Parkinson’s; FOG, freezing of gait; EMA, ecological momentary assessment; QoM, Quality of Motion; STS, Sit-to-stand test; TUG, Timed Up and Go; PDQ-8, Parkinson's Disease Questionnaire-8; DBS, Deep Brain Stimulation; iRBD, Idiopathic Rapid Eye Movement Sleep Behavior Disorder; IMU, Inertial measurement unit; AUC, Area Under the Curve; UPDRS, Unified Parkinson's Disease Rating Scale; H&Y, Hoehn & Yahr Scale. Objectives of this study This study aimed to evaluate the early implementation of a phased national roll-out the CheckPD digital screening programme across 10 provinces in Thailand, focusing on reach, usability, real-world predictive performance, and implementation factors relevant to scale-up in a LMIC. Methods Study design and implementation framework This mixed-methods implementation study evaluated the early phase of national deployment of a digital PD screening programme in Thailand between January 2024 and October 2025. The study was designed as a pragmatic, real-world evaluation, embedded within routine public health activities, rather than in a controlled experimental setting, in order to reflect actual conditions of use at scale. Evaluation was guided by the RE-AIM framework (Reach, Effectiveness, Adoption, Implementation, and Maintenance), which is widely used to assess the public health impact, usability, and scalability of complex interventions [ 61 – 63 ]. The RE-AIM framework enabled systematic assessment of population reach, predictive performance under real-world conditions, adoption across provinces and delivery pathways, fidelity of implementation, and early indicators of sustainability. National rollout and programme governance were coordinated by the TRCS in collaboration with the NHSO. The NHSO is Thailand’s public agency responsible for ensuring equitable access to essential health services across the continuum of care, including health promotion, disease prevention, treatment, and rehabilitation, primarily through strategic financing and reimbursement of healthcare providers. Early risk identification through population-based screening initiatives such as CheckPD aligns with NHSO’s mandate by enabling more timely and effective treatment, optimising resource allocation, and improving long-term health outcomes. The programme was aligned with Thailand’s preventive health agenda and NCD strategies, facilitating integration with existing community health infrastructure and referral pathways. Study setting Implementation was conducted across selected to represent Thailand’s geographic, demographic, and socioeconomic diversity, including urban, peri-urban, and rural contexts (Fig. 1 ). Participating provinces included Bangkok, Nonthaburi, Pathum Thani, Samut Prakan, Chonburi, Nakhon Pathom, Phetchaburi, Nakhon Sawan, Chiang Rai, and Si Sa Ket. These provinces span central, northern, and northeastern regions and vary in population density, healthcare access, and digital connectivity. Screening activities were delivered through multiple community-based and institutional settings, including community centres, temples, district hospitals, public health outreach campaigns, and personal mobile devices. This multi-setting approach was intended to maximise inclusion of both digitally experienced users and individuals with limited digital literacy or constrained internet access, particularly older adults and residents of rural communities. This figure illustrates the spatial distribution of CheckPD screening participants across Thailand among the first 10 provinces included in the analysis. Provinces are shaded according to the number of screened participants, with darker shading indicating higher participation levels. The accompanying table summarises the absolute number and proportion of participants by province, while a second table indicates the number of neurologists available within each province. The number of neurologists per province was low across all included settings, highlighting a genuine limitation in local specialist availability. Participants and eligibility Adults aged 40 years or older residing in Thailand were eligible to participate in the screening programme, reflecting epidemiological evidence that the incidence of PD, while relatively low in early adulthood, begins to rise from the fourth decade of life and increases progressively with age. In addition, longitudinal studies indicate that prodromal features of PD, including non-motor symptoms such as hyposmia, RBD, and subtle motor changes, can emerge years to decades before clinical diagnosis, often during midlife [ 49 , 64 , 65 ]. Participation was voluntary and required provision of digital informed consent within the mobile application prior to initiation of screening. There were no exclusion criteria based on gender, educational attainment, occupation, or underlying health status, consistent with the population-level screening intent of the programme. Individuals who did not complete the consent process, who withdrew prior to submission of screening data, or who experienced technical failure that prevented capture of evaluable data were excluded from analytic datasets. No financial or material incentives were provided. Implementation and recruitment strategies The CheckPD screening programme was delivered using four coordinated implementation pathways designed to maximise reach while accommodating varying levels of digital literacy and access: (1) Field screening campaigns organised by provincial public health offices and conducted as one-day or multi-day outreach events; (2) Online training–activated screening sessions, in which trained community leaders or health workers facilitated local screening following remote instruction; (3) Community screening led by VHVs, with a focus on older adults and rural communities; and (4) Self-screening via app download, available nationwide throughout the study period (Fig. 2 ). Volunteers and public health officers involved in field and community screening received standardised training from the TRCS, delivered through online modules and written manuals. Training covered consent procedures, step-by-step screening workflows, device setup, and basic troubleshooting to ensure consistency, data quality, and participant safety across provinces and implementation settings. The CheckPD platform and screening workflow The CheckPD screening workflow comprises four sequential components designed for rapid, scalable population screening (Fig. 3 ). (1) User registration and digital informed consent, where participants securely register on the CheckPD mobile application and provide electronic consent prior to screening. (2) Structured symptom and risk factor assessment, consisting of a questionnaire capturing motor symptoms, non-motor symptoms, and established risk factors for PD. (3) Guided performance of digital motor and voice tasks, including finger tapping for bradykinesia, tremor assessment, gait and balance evaluation, and structured speech recording, with in-app instructions to ensure standardised task execution. (4) Automated data processing and risk classification, in which collected data are analysed using predefined algorithms to generate an individualised PD risk profile. The entire screening process is designed to be completed within approximately 8–10 minutes, supporting feasibility for large-scale, population-level deployment. (10) Completion of a 20-item Parkinson’s disease risk assessment questionnaire capturing motor symptoms, non-motor symptoms, and established risk factors. Component 4. Automated analysis and feedback: (11) Automated risk evaluation and classification; (12) Personalised health guidance and recommendations based on screening results. To enhance usability and accessibility, the application incorporates Thai-language localisation, audio-visual guidance, enlarged interface elements, and a linear, stepwise workflow. These design features were intentionally implemented to reduce cognitive load, support users with varying levels of digital literacy, and minimise task-related errors, particularly among older adults and individuals with motor or cognitive challenges. In addition, a step-by-step video tutorial demonstrating how to use the application and complete each screening task is provided to further support user onboarding and correct task execution (Supplementary data 1). Outcomes and evaluation measures Primary implementation outcomes were defined in accordance with the RE-AIM framework and included reach (number of app downloads, initiated screenings, and completed screenings), adoption (participation by province and by implementation pathway), implementation fidelity (task completion and dropout rates), and usability. Usability was assessed using the System Usability Scale (SUS) and the short User Experience Questionnaire (UEQ-S), capturing both pragmatic and hedonic dimensions of user experience [ 66 , 67 ]. Secondary outcomes included AI-based PD risk classification, system performance indicators (including application crash rate and offline success rate), and qualitative feedback from volunteers and public health officers regarding usability, user trust, and integration into existing workflows. Statistical analysis and data visualisation Quantitative analyses were conducted to characterise programme reach, user engagement, and task completion patterns during real-world implementation of the CheckPD platform. All analyses were performed using Python version 3.12.10, with the pandas library used for data handling and descriptive analyses and matplotlib for data visualisation Descriptive statistics were used throughout, consistent with the pragmatic and implementation-focused aims of the study. Continuous variables are reported as means with standard deviations, and categorical variables as counts and percentages. To examine age-related patterns of engagement, participants were stratified into five predefined age groups: <40, 40–49, 50–59, 60–69, and ≥ 70 years. For each age group, task outcomes were categorised as complete, incomplete, or unattempted. The number and proportion of participants in each category were calculated such that percentages within each age group totalled 100%. These analyses were used to assess age-related differences in task adherence and dropout across the screening workflow. Task-level engagement was further analysed by calculating completion rates for each individual screening task within the CheckPD application. Each task was coded as a binary outcome, with completion coded as ‘1’ and non-completion coded as ‘0’. For bilateral tasks (e.g. dual finger tapping and pinch-to-size), a task was considered complete only if both left- and right-sided components were successfully completed. Task completion rates were expressed as the percentage of participants who completed each task. Tasks were ranked from highest to lowest completion rate and visualised using funnel plots to illustrate cumulative attrition and identify stages of the screening workflow associated with the greatest participant dropout. These analyses were intended to highlight usability- and implementation-related barriers, particularly for tasks requiring greater sensor precision, balance stability, or environmental setup. In addition, multivariable logistic regression analysis was performed to explore factors associated with completion of the full screening protocol. The dependent variable was task completion status (completed versus not completed). Independent variables included selected sociodemographic and contextual factors, including educational attainment and province of residence. Results are presented as odds ratios with 95% confidence intervals. Model fit was assessed using the Omnibus test of model coefficients, Nagelkerke pseudo R², and the Hosmer–Lemeshow goodness-of-fit test. No hypothesis-driven inferential statistical testing beyond this exploratory regression analysis was undertaken, as the primary objective of the study was to evaluate real-world feasibility, engagement, and implementation performance, rather than to establish causal relationships. Analyses of AI predictive performance, including calculation of positive predictive value (PPV) based on neurologist verification, were conducted separately and are described in the following section. AI evaluation and clinical verification CheckPD classifies users as ‘normal’ or ‘at risk’ using an ensemble machine-learning model trained on multimodal input data derived from questionnaire responses and sensor-based motor and voice tasks, with the method described previously [ 49 ]. Participants classified as at risk were advised to seek further clinical evaluation through standard healthcare pathways. AI performance metrics were calculated only amongst participants who were flagged as at risk and subsequently underwent neurological assessment, considered as the gold standard for diagnosis of PD. Participants classified as screen-negative were not routinely clinically verified as part of this implementation programme; therefore, population-level diagnostic accuracy could not be estimated. Usability and user experience assessment Usability and user experience were assessed in a representative sample of participants following completion of the screening process. Validated Thai versions of the System Usability Scale (SUS) and the short User Experience Questionnaire (UEQ-S) were administered. UEQ-S results were analysed using standardised benchmark comparisons to assess pragmatic quality (e.g., clarity, efficiency, ease of use) and hedonic quality (e.g., interest, stimulation, perceived innovation). Data sources, management, and governance Data for this implementation study were derived from the CheckPD digital screening platform and its associated clinical screening and analytics infrastructure, as illustrated in the system architecture and data flow diagram (Fig. 4 ). The CheckPD ecosystem comprises three core components: (1) the CheckPD mobile application for population-level data capture, (2) a web-based screening module for clinical and questionnaire-based assessments, and (3) a Business Intelligence (BI) dashboard for monitoring programme performance and implementation outcomes. The CheckPD mobile application serves as the primary source of multimodal screening data. During routine use, participants generate real-time data including demographic information, questionnaire responses, motor assessments (finger tapping, tremor, gait, and balance), and speech recordings. Structured application data are stored as JavaScript Object Notation (JSON) files, while speech recordings are stored as waveform audio (WAV) files. All raw application data are housed within a NoSQL database operated by the TRCS, which functions as the secure primary data repository. To ensure data integrity and continuity, daily backups are performed through a dedicated web application, with archived copies stored on encrypted cloud storage and local hard disk drives. For secondary use, analysis, and reporting, selected structured data, primarily demographic and screening-related variables, are transferred from the TRCS NoSQL database to a structured SQL Data Warehouse managed internally by a team at Chulalongkorn Centre of Excellence for Parkinson’s Disease and Related Disorders (ChulaPD; www.chulapd.org ). Data migration occurs on a daily and weekly schedule, depending on data type and operational requirements. An automated migration pipeline transfers JSON and WAV files using three unique identifiers: a general system identifier, the Thai national identification number, and a record-specific identifier. This automated process includes built-in error detection, with notifications issued to the ChulaPD data team in the event of transfer failures or inconsistencies. Only records with neurologist-confirmed diagnostic labels (PD or control) are included in the analytic migration workflow. Clinical diagnostic data are generated through a dedicated physician-facing web application. Authorised neurologists review participant-level screening outputs and assign diagnostic classifications, categorised as ‘PD’ or ‘not PD’. Diagnostic access and labelling privileges are restricted to approved personnel, and all labelled records are stored exclusively within the SQL Data Warehouse. This separation of raw data storage and curated diagnostic datasets supports data minimisation, traceability, and role-based access control. Programme monitoring and implementation evaluation are supported by the BI dashboard, which integrates data from both the CheckPD and Screening components. Using visual analytics tools, including Looker Studio, the dashboard provides near real-time summaries of application downloads, screening completion rates, diagnostic distributions, task-level adherence, and system usage patterns. This infrastructure enables continuous monitoring of reach, adoption, implementation fidelity, and system performance throughout the national rollout. Data governance across the CheckPD platform is designed to comply with Thailand’s PDPA. Governance mechanisms include role-based access control, separation of identifiable and analytic datasets, controlled data migration, and secure storage managed by national and academic partners. Collectively, this architecture supports secure, scalable, and auditable use of digital health data for population-level PD screening and implementation research. Ethical considerations and data protection The TRCS acted as the designated data controller, with ChulaPD serving as the data processor. Prior to initiating any screening or assessment, all participants were required to provide explicit approval for data collection through a digital informed consent process embedded within the CheckPD platform, in accordance with approvals granted by the relevant ethics and regulatory bodies. All personal and health-related data were protected through end-to-end encryption, employing Advanced Encryption Standard 256-bit (AES-256) encryption for data at rest and Transport Layer Security (TLS) version 1.3 for data in transit. Data were stored on an ISO/IEC 27001-certified server infrastructure operated by the TCRS. Analytical activities were conducted exclusively on de-identified datasets under approval from the relevant ethics committees. Ethics approval was obtained from the Institutional Review Board of the Faculty of Medicine, Chulalongkorn University (IRB No. 0804/65), as well as from the Central Research Ethics Committee (CREC) under the approved protocol entitled ‘Flipping the Paradigm of Parkinson’s Disease: A Model of National ‘Eat, Move, Sleep’ Digital Interventions to Prevent or Slow the Rise of Non-Communicable Diseases in Thailand’ (CREC No. CREC023/68BR-MED06; Certificate Number COA-CREC105/2025). In accordance with Thailand’s PDPA (B.E. 2562, 2019), Data Protection Impact Assessments were performed on an annual basis to evaluate and mitigate potential risks related to data processing and security. Reporting standards and implementation framework alignment This study was designed and reported in alignment with principles from the RE-AIM framework for implementation research, with explicit reporting of reach, adoption, implementation fidelity, and early indicators of maintenance. Elements of the STROBE guidelines for observational studies were followed where applicable, including transparent reporting of study setting, participant eligibility, data sources, and outcome measures [ 68 ]. Given the pragmatic, implementation-focused nature of the programme, no randomisation or hypothesis-driven comparisons were undertaken, and reporting emphasised real-world feasibility, usability, and scalability rather than causal inference. Results Participant demographics and CheckPD app usage Between January 2024 and October 2025, the CheckPD platform recorded 30,327 application downloads nationwide, reflecting broad uptake during the national rollout. The present analysis focuses on users from the first 10 provinces included in the rollout, selected based on completed implementation governance and stable data pipelines, resulting in 18,520 users who initiated screening and provided evaluable data (Fig. 5 ). Participants had a mean age of 56.91 ± 11.89 years and spanned the predefined inclusion age range of 40 to ≥ 70 years (Table 3 ). The screened population was predominantly female, comprising 14,004 women (76.0%) and 4,460 men (24.0%). Amongst the analysed cohort, 13,381 participants (72%) completed all screening tasks, while 5,139 (28%) had incomplete assessments. Following screening, 730 individuals flagged as ‘at risk’ subsequently sought further neurological evaluation (Supplementary Data 2). Table 3 Demographic characteristics of CheckPD users from the first 10 provinces included in the national screening rollout (n = 18,520). Demographic data Total (n = 18,520) Age (Mean ± SD) 56.91 ± 11.89 Gender Male (%) 4460/18,520 (24%) Female (%) 14,004/18,520 (76%) Not specified (%) 56/18,520 (< 1%) Education Bachelor's degree or higher (%) 2,681/18,520 (15%) Below Bachelor's degree (%) 12,679/18,520 (68%) Not specified (%) 3,160/18,520 (17%) Occupation Civil servant (non-teaching) (%) 481/18,520 (3%) Farmer (%) 5,502/18,520 (30%) Merchant / Trader (%) 2,795/18,520 (15%) Petroleum/ oil exposure occupation (%) 9/18,520 (< 1%) Private sector employee (%) 503/18,520 (3%) Professional athlete (%) 1/18,520 (< 1%) Retired civil servant (%) 291/18,520 (2%) State enterprise employee (%) 121/18,520 (1%) Teacher / Lecturer (%) 56/18,520 (< 1%) Not employed (%) 1,912/18520 (10%) Other (%) 2,981/18,520 (16%) Not specified (%) 3,868/18,520 (21%) Marital status Single (%) 3,081/18,520 (17%) Married / Partnered (%) 9,687/18,520 (52%) Divorced (%) 848/18,520 (5%) Widowed (%) 1,720/18,520 (9%) Not specified (%) 3,184/18,520 (17%) Income No income (%) 759/18,520 (4%) Less than 5,000 THB (%) 3,999/18,520 (22%) 5,000–10,000 THB (%) 5,403/18,520 (29%) 10,001–20,000 THB (%) 1,820/18,520 (10%) 20,001–30,000 THB (%) 562/18,520 (3%) 30,001–40,000 THB (%) 300/18,520 (2%) More than 40,000 THB (%) 610/18,520 (3%) Not specified (%) 5,067/18,520 (27%) History of Smoking Yes (%) 121/18,520 (1%) No (%) 1,853/18,520 (10%) Not specified (%) 16,546/18,520 (89%) Alcohol drinking Yes (%) 428/18,520 (2%) No (%) 1,544/18,520 (8%) Not specified (%) 16,548/18,520 (89%) Coffee drinking Yes (%) 1,215/18,520 (7%) No (%) 762/18,520 (4%) Not specified (%) 16,543/18,520 (89%) Milk/dairy milk product consumption Yes (%) 747/18,520 (4%) No (%) 1,230/18,520 (7%) Not specified (%) 16,543/18,520 (89%) Regular exercise (more than 150 minutes/ week) Yes (%) 1,086/18,520 (6%) No (%) 891/18,520 (5%) Not specified (%) 16,543/18,520 (89%) Insecticide exposure Yes (%) 288/18,520 (2%) No (%) 1,689/18,520 (9%) Not specified (%) 16,543/18,520 (89%) History of narcotic use Yes (%) 41/18,520 (< 1%) No (%) 1,936/18,520 (11%) Not specified (%) 16,543/18,520 (89%) History of severe head injury Yes (%) 70/18,520 (< 1%) No (%) 1,906/18,520 (10%) Not specified (%) 16,544/18,520 (89%) THB, Thai Baht. CheckPD app performance Overall performance of the CheckPD app across all RE-AIM dimensions is summarised in Table 4 . Table 4 RE-AIM indicators for CheckPD. Domain Indicator Data Source Value Interpretation Reach 21,882 screened / 30,327 downloads App analytics 72.15% High participation Effectiveness Positive predictive value Positive predictive values 81.23% Strong agreement with clinical labels Adoption Active provinces TRCS records 10 Nationwide activation Implementation Mean SUS score/ completion rate Usability survey 83/92% Excellent usability Maintenance Integration into NCD programme TRCS policy In progress Early policy uptake Reach Overall programme reach, defined as the proportion of screened individuals relative to app downloads, was 72.15%, indicating high population engagement during this early phase of national implementation. Effectiveness The CheckPD app showed a positive predictive value of 81.23% based on those 730 users who were considered ‘at-risk’ according to the app’s AI prediction during screening versus the subsequent neurologist’s diagnosis (Supplementary Data 2) Adoption Most CheckPD implementation activities occurred in 2025, following a preparatory period in 2024 dedicated to programme planning, system development, stakeholder engagement, and team readiness. Adoption of the CheckPD platform increased primarily during organised implementation periods, with screening activity remaining low outside these intervals (Fig. 6 ). Distinct spikes in participation were observed following online training sessions and field-based screening activities across provinces, indicating that these facilitated activities directly contributed to increased app uptake and screening completion. The highest levels of screening activity were recorded between May and September 2025, during which weekly screening volumes exceeded 1,000 participants during peak periods (Fig. 6 ). intensive outreach between May and September 2025, demonstrating the direct impact of facilitated implementation strategies on user uptake and screening participation. Geographic distribution of screening participation varied across provinces (Fig. 1 ). The highest levels of participation were observed in Nakhon Pathom, while Chonburi recorded the lowest uptake. Provinces with more than 500 screened participants were predominantly located in the central, northeastern, and selected southern regions of Thailand, reflecting regional differences in adoption associated with local implementation intensity and engagement strategies (Fig. 1 ). Implementation Levels of participation and test completion within the CheckPD programme varied across provinces and by implementation method (Table 5 ). Across all settings, 13,381 of 18,520 participants (72%) completed the full screening protocol, while 5,139 (28%) had incomplete assessments. Volunteer-facilitated and organised implementation strategies accounted for the majority of engagement, with 6,742 participants screened through VHVs, 5,207 through community-based field screening campaigns, and 3,172 via online training-activated screening sessions whilst the remainder (2,080) were completed by self-initiated app downloads. Completion rates were consistently higher in structured, facilitated settings, particularly those involving VHVs and online training, compared with self-download pathways in several provinces (Table 5 ). Table 5 Participation and screening completion outcomes of the CheckPD programme by province and implementation method among users from the first 10 provinces Province Implementation method Participants Test result Completed Incomplete Nakhon Pathom Field Screening 850 (100%) 593 (70%) 257 (30%) Online Training 1,694 (100%) 1,319 (78%) 375 (22%) VHVs 2,189 (100%) 1,663 (76%) 526 (24%) Self-download 402 (100%) 296 (74%) 106 (26%) Phetchaburi Field Screening 434 (100%) 269 (62%) 165 (38%) Online Training 76 (100%) 49 (64%) 27 (36%) Self-download 66 (100%) 35 (53%) 31 (47%) Si Sa Ket Field Screening 617 (100%) 384 (62%) 233 (38%) Online Training 1 (100%) 1 (100%) 0 (0%) Self-download 433 (100%) 251 (58%) 182 (42%) Nakhon Sawan Field Screening 1,342 (100%) 919 (68%) 423 (32%) Online Training 887 (100%) 670 (76%) 217 (24%) VHVs 2,452 (100%) 1,896 (77%) 556 (23%) Self-download 373 (100%) 281 (75%) 92 (25%) Chiang Rai Field Screening 827 (100%) 471 (57%) 356 (43%) Online Training 146 (100%) 98 (67%) 48 (33%) VHVs 2,101 (100%) 1,571 (75%) 530 (25%) Self-download 44 (100%) 33 (75%) 11 (25%) Nonthaburi Field Screening 440 (100%) 299 (68%) 141 (32%) Online Training 89 (100%) 69 (78%) 20 (22%) Self-download 296 (100%) 206 (70%) 90 (30%) Pathum Thani Field Screening 331 (100%) 244 (74%) 87 (26%) Online Training 279 (100%) 206 (74%) 73 (26%) Self-download 283 (100%) 201 (71%) 82 (29%) Samut Prakan Field Screening 365 (100%) 303 (83%) 62 (17%) Self-download 93 (100%) 66 (71%) 27 (29%) Bangkok Self-download 1,043 (100%) 753 (72%) 290 (28%) ChulaPD Clinic 276 (100%) 170 (62%) 106 (38%) Chon Buri Field Screening 1 (100%) 0 (0%) 1 (100%) Self-download 90 (100%) 65 (72%) 25 (28%) Total 18,520 (100%) 13,381 (72%) 5,139 (28%) VHVs, Village Health Volunteers. Among participants who completed screening, 1,761 individuals (13%) were classified as ‘at risk’ by the CheckPD screening algorithm (Table 6 ). Of these, 730 individuals underwent in-person neurological evaluation, primarily through organised field screening activities where established referral pathways and specialist access were available (Fig. 5 ). Among the neurologist-evaluated participants, 593 were clinically diagnosed with PD, corresponding to a PPV of 81.23% for the CheckPD screening algorithm (Supplementary Data 2). The remaining individuals classified as ‘at risk’ had not yet received specialist diagnostic assessment at the time of analysis, reflecting real-world constraints related to access, timing, and referral uptake. Table 6 Distribution of CheckPD screening algorithm risk classifications amongst participants with completed assessments, by province and implementation method Province Implementation method Participants with completed test result AI prediction result At risk Normal Nakhon Pathom Field Screening 593 (100%) 104 (18%) 489 (82%) Online Training 1,319 (100%) 95 (7%) 1,224 (93%) VHVs 1,663 (100%) 141 (8%) 1,522 (92%) Self-download 296 (100%) 15 (5%) 281 (95%) Phetchaburi Field Screening 269 (100%) 30 (11%) 239 (89%) Online Training 49 (100%) 4 (8%) 45 (92%) Self-download 35 (100%) 8 (23%) 27 (77%) Si Sa Ket Field Screening 384 (100%) 51 (13%) 333 (87%) Online Training 1 (100%) 0 (0%) 1 (100%) Self-download 251 (100%) 25 (10%) 226 (90%) Nakhon Sawan Field Screening 919 (100%) 142 (15%) 777 (85%) Online Training 670 (100%) 51 (8%) 619 (92%) VHVs 1,896 (100%) 131 (7%) 1,765 (93%) Self-download 281 (100%) 17 (6%) 264 (94%) Chiang Rai Field Screening 471 (100%) 90 (19%) 381 (81%) Online Training 98 (100%) 7 (7%) 91 (93%) VHVs 1,571 (100%) 230 (15%) 1,341 (85%) Self-download 33 (100%) 11 (33%) 22 (67%) Nonthaburi Field Screening 299 (100%) 40 (13%) 259 (87%) Online Training 69 (100%) 7 (10%) 62 (90%) Self-download 206 (100%) 49 (24%) 157 (76%) Pathum Thani Field Screening 244 (100%) 32 (13%) 212 (87%) Online Training 206 (100%) 11 (5%) 195 (95%) Self-download 201 (100%) 31 (15%) 170 (85%) Samut Prakan Field Screening 303 (100%) 125 (41%) 178 (59%) Self-download 66 (100%) 23 (35%) 43 (65%) Bangkok Self-download 753 (100%) 161 (21%) 592 (79%) ChulaPD Clinic 170 (100%) 116 (68%) 54 (32%) Chon Buri Field Screening 0 (0%) 0 (0%) 0 (0%) Self-download 65 (100%) 14 (22%) 51 (78%) Total 13,381 (100%) 1,761 (13%) 11,620 (87%) VHVs, Village Health Volunteers. Task completion demonstrated clear age-related gradients, with completion rates declining progressively in older age groups (Fig. 7 ). Funnel plot analyses further highlighted task-specific differences in completion, with questionnaire-based and voice assessments achieving the highest completion rates, while motor tasks requiring greater physical stability, precise sensor positioning, or environmental setup, such as gait, balance, and certain tremor assessments, showed lower completion rates (Fig. 8 ). This figure illustrates screening task completion rates across predefined age groups among users from the first 10 provinces included in the analysis. Completion rates declined progressively with increasing age, indicating age-related differences in engagement and ability to complete all components of the digital screening workflow. This funnel plot shows the proportion of participants completing each screening task, with higher completion for questionnaire and voice-based assessments and lower completion for more complex motor tasks, reflecting increasing task burden in real-world, unsupervised use. Multivariable logistic regression analysis identified educational attainment and geographic context as significant predictors of screening completion (Table 7 ). Participants with a Bachelor’s degree or higher were more likely to complete all screening tasks compared with those with lower educational attainment (odds ratio [OR] = 1.528, 95% CI 1.380–1.691). In contrast, residence outside Bangkok was associated with a lower likelihood of completion (OR = 0.755, 95% CI 0.662–0.860), underscoring the influence of urban–rural context on implementation fidelity and user engagement (Table 7 ). Table 7 Logistic regression analysis of user parameters that influenced the likelihood of completing the CheckPD app screening tests. Predictors Exp (B) p -value Educational status – Bachelor's degree 1.528 (95%CI 1.380–1.691) < 0.001* Province – Bangkok 0.755 (95%CI 0.662–0.860) < 0.001* Model summary Omnibus tests of Model coefficients: Chi-square 17.393 < 0.001* Nagelkerke R Square 0.006 Hosmer and Lemeshow Test 0.365 *: Statistically significant. The pseudo R-square from the Nagelkerke R-square model determined the percentage of variance. Nagelkerke R-squared – an approximate measure of the proportion of explained variation. Hosmer and Lemeshow Test – the goodness of fit in the logistic regression model. Usability outcomes Results for the usability survey showed a mean (± SD) SUS score of 83 ± 9, along with a 92% completion rate among first-time users aged 40–70 years, indicating excellent usability. The median total test time was 8 minutes. Common user feedback was that the CheckPD app was “easy to understand” and “trustworthy because of the Red Cross logo”. Qualitative data confirmed emotional reassurance and confidence due to the clear prompts and branding. User experience (UX) The mean (± SD) UEQ-S scores for ‘efficiency’ and ‘interesting’ were 1.8 ± 1.0 and 1.7 ± 1.2, respectively. The overall mean pragmatic quality score was 1.6 ± 1.0, while the mean hedonic quality score was 1.5 ± 1.1, resulting in an overall mean user experience score of 1.6 ± 0.9. A multi-bar chart comparing these results with a reference benchmark dataset indicated that the app performed well, with mean overall values and values for pragmatic quality and hedonic quality rated as ‘good’ (Fig. 9 ). System performance Results for CheckPD app stability and response time confirmed that it is suitable for field operations. System logs confirmed a crash rate of < 1% and an offline success rate of 93%, enabling reliable operation in remote settings. Volunteer throughput was ~ 12 participants/hour. Discussion Overall findings for primary and secondary outcome measures This real-world implementation study has confirmed that the CheckPD app is a feasible and robust national PD screening platform for Thailand. Results for RE-AIM Framework parameters demonstrated that CheckPD had excellent reach and adoption with high levels of engagement and completion of tasks. The AI-driven CheckPD app also achieved high PPV (81.23%) when compared with neurologists’ PD diagnoses. The observed reduction in PPV in this study compared with the original hospital-based validation study’s reported diagnostic accuracy of 91% [ 49 ] confirms a broader and well-recognised phenomenon in AI deployment, a so-called ‘translation gap’ or ‘deployment gap’. Recent reviews have documented that AI systems which perform well under controlled development or clinical-trial conditions often fail to maintain performance when deployed in diverse real-world settings, due to data heterogeneity, variable workflows, and shifts in patient population [ 69 , 70 ]. In addition, machine-learning research has identified ‘under-specification’, the tendency for equally good models on training data to behave very differently once deployed outside the development domain, as a fundamental reason for unpredictability in real-world use [ 71 ]. These observations strongly support the need for of adaptive validation and continuous post-deployment monitoring when scaling diagnostic AI tools [ 72 ]. In this respect, CheckPD’s national rollout, spanning 10 Thai provinces with diverse demographics, device types, and real-world use conditions, provides a valuable empirical example of the deployment gap in a neurological screening context. Although direct comparison of the outcomes of the two studies is not possible due to metric differences (PPV versus diagnostic accuracy), the high PPV of 81.23% suggests that CheckPD continues to identify true PD cases with high precision in real-world implementation, consistent with the high accuracy previously reported in the controlled validation study [ 49 ]. This finding supports the robustness of CheckPD’s screening algorithm and suggests that its performance translates effectively into real-world use, even in a large, diverse population across multiple provinces. The performance of CheckPD during national implementation was influenced by several real-world factors that differed substantially from the controlled environment of the original validation study. Unlike structured testing performed under supervision, screening in community settings relies on participants’ ability to follow instructions independently, which introduces variability related to digital literacy and user skill, a known barrier to effective engagement with digital health technologies and outcomes across diverse populations [ 73 , 74 ]. Device heterogeneity, including differences in smartphone hardware, operating systems, sensor quality, and environmental conditions, has been shown to affect sensor data quality collected in real-world settings, potentially introducing inconsistencies in health-related assessments derived from consumer-owned devices [ 75 ]. In addition, incomplete task completion, network connectivity issues, and variable levels of user engagement can lead to missing data and reduced evaluable datasets, reflecting known challenges in remote and unsupervised digital data collection [ 76 ]. These implementation realities likely contribute to deviations from controlled-study performance metrics but also reflect the authentic operational environment in which CheckPD is intended to function. Despite these challenges, the app maintained a high PPV in real-world use, suggesting resilience of the screening algorithm even under less ideal conditions and underscoring the potential for well-designed digital health tools to yield clinically meaningful results outside the laboratory. Strengths of CheckPD and implementation success factors Key facilitators of the positive results obtained with CheckPD in this study included TRCS endorsement and network, community volunteer involvement, and its user-friendly design. While other PD mobile applications have been developed primarily for symptom tracking and patient support (Table 2 ), there is limited evidence regarding digital tools designed for national population-level screening. To our knowledge, CheckPD represents the first national, app-based population screening programme for PD, implemented within a universal healthcare coverage system. CheckPD differs from existing digital tools for PD in both its scope and means of deployment. A key strength of the app is that it employs multimodal analysis to evaluate a combination of different data inputs which previous studies have shown can provide valuable additional information leading to greater accuracy when compared to analysis of individual modalities alone [ 77 , 78 ]. Challenges and limitations Analysis of data from our national implementation study identified that gender, age, level of education and geographical location were all factors that influenced app engagement and test completion. Large population surveys of mobile health (mHealth) apps have also demonstrated systematic gender, age and education differences in app use and sustained engagement [ 79 ]. Our study attracted a higher proportion of female app users than men. This pattern probably reflects gender differences in health-seeking behavior and willingness to engage with preventive digital tools, rather than underlying disease epidemiology. The over-representation of women among CheckPD users contrasts with the slightly higher prevalence of PD in men [ 80 ]. Similar gender imbalances have been reported across internet- and app-based preventive and mental-health interventions, where evidence suggests that women may disproportionately engage with preventive health and health monitoring technologies, and that digital health innovations can positively affect women’s access to health care and self-care[ 81 – 83 ]. Our findings therefore probably reflect gendered patterns of digital health engagement rather than true PD risk, and raise the possibility that some higher-risk men are under-screened by the current digital strategy. The observed age-related patterns of test completion and dropout raise the possibility that some higher-risk individuals, particularly older men, may be under-screened by the current predominantly app-based strategy [ 84 – 86 ]. Future iterations of CheckPD should therefore consider targeted outreach and tailored messaging to improve engagement among older men and other under-represented groups. These patterns also suggest a dual mechanism of attrition: younger adults (often at lower PD risk) were more likely to skip individual tasks, whereas older adults, the primary target population for PD screening, were more likely to initiate screening but not complete the full assessment workflow. This pattern may reflect motivational dropout amongst younger users and capability- or usability-related dropout amongst older users, consistent with usability research demonstrating that age-related cognitive, sensory, and visuomotor changes can hinder effective interaction with complex digital interfaces and sensor-based tasks. Consequently, datasets used for training and validating digital biomarkers may over-represent younger, digitally proficient, and more adherent users, while under-representing frailer or more impaired older adults. This form of informative missingness represents an important limitation, as it may bias estimates of model performance when digital screening tools are deployed in routine, unsupervised real-world settings [ 87 ]. Our findings regarding educational level likely reflect the importance of digital health literacy for effective engagement with the CheckPD application. The lower completion rates observed among residents in more rural regions further highlight the value of VHVs in facilitating participation and supporting users with varying levels of digital access and literacy. Assessing the impact of missing data is critical for evaluating app-based screening tools in the field. However, in this real-world implementation, 72% of participants completed all assessment tasks, a substantial level of engagement for a multi-task, unsupervised workflow deployed at scale. This figure compares favourably with broader mHealth and digital phenotyping literature, where sustained adherence often falters outside controlled research environments. Indeed, contemporary studies suggest that real-world adherence exceeding 70% sits at the ‘high end’ of reported benchmarks [ 88 ]. For context, while intensive interventions with specialised design elements can reach ‘exceptionally high’ daily completion rates of 84%, typical real-world Ecological Momentary Assessment studies report averages closer to 67.2% [ 89 ]. Despite exceeding these benchmarks, our data revealed distinct patterns of incomplete engagement. Completion rates declined as participant age increased, with a notable divergence in behaviour: while younger participants more frequently left specific tasks unattempted, older adults were more likely to terminate assessments mid-sequence. Funnel analyses further clarified this attrition, highlighting cumulative dropout at transitions to complex or sensor-intensive motor tasks. This suggests that a subset of higher-burden activities accounted for a disproportionate share of data loss, underscoring the delicate balance between task complexity and sustained user adherence in remote screening. These patterns are consistent with findings from smartphone-based digital phenotyping studies, in which missing sensor and task data are common and vary widely between individuals, even within well-controlled research protocols [ 90 , 91 ]. Analyses of large digital phenotyping cohorts, such as the mindLAMP platform, similarly show that adherence decreases as task frequency and complexity increase, with high-friction tasks disproportionately driving disengagement [ 92 , 93 ]. Systematic reviews of mHealth interventions consistently identify participant attrition and engagement loss as key challenges for real-world implementation [ 94 ]. Conclusions The CheckPD programme has demonstrated a successful transition from a validated digital prototype to a scalable, real-world national public health intervention for PD. Its strong real-world performance, reflected in a high PPV of the screening algorithm, combined with a HCD approach and robust ethical governance, positions Thailand’s implementation as a credible reference model for digital neurology and population-level brain health initiatives globally. By enabling early identification of individuals at increased risk of PD and establishing clear pathways for clinical follow-up, CheckPD supports timely intervention and behaviour-focused risk modification. This approach aligns closely with emerging prevention-oriented strategies for PD and with the WHO’s Brain Health framework, highlighting the potential of integrated digital screening programmes to contribute meaningfully to neurological disease prevention at scale. Declarations Ethics approval: The protocol for this study was approved by the Institutional Review Board of the Faculty of Medicine, Chulalongkorn University (IRB No. 0804/65), as well as from the Central Research Ethics Committee (CREC) under the approved protocol entitled ‘Flipping the Paradigm of Parkinson’s Disease: A Model of National ‘Eat, Move, Sleep’ Digital Interventions to Prevent or Slow the Rise of Non-Communicable Diseases in Thailand’ (CREC No. CREC023/68BR-MED06; Certificate Number COA-CREC105/2025). Consent to participate: Digital informed consent was obtained from all participants. Availability of data and materials: Supplementary materials relevant to this study are available via the ChulaPD Screening Data Repository at: https://drive.google.com/drive/folders/1UqVXnM6HEsLGmdLu2gjng96AhRaQ2ios Competing interests: The authors declare that they have no competing interests. Funding: This research was funded by the following grants; the Thailand Science Research and Innovation Fund (Program Management Unit for Competitiveness, C01F670185), the National Economic and Social Development Council, Thailand Center for Excellence for Life Sciences (TC (ERP) 31/2568), National Research Council of Thailand (N42A680591, N35E680087), the Center of Excellence grants of Chulalongkorn University (CE68_028_3000_004), and the Thai Red Cross Education and Research Committee. Author contributions: All authors contributed to editorial changes in the manuscript. All authors read and approved the final manuscript. Acknowledgements: This national Parkinson’s disease screening initiative was conducted in honour of Her Royal Highness Princess Maha Chakri Sirindhorn, in recognition of her longstanding commitment to public health, medical education, and the wellbeing of the Thai population. The authors also gratefully acknowledge the collaboration with the National Health Security Office (NHSO), which was formally established under a Memorandum of Understanding (MOU) signed on 7 May 2024 enabling integration of the CheckPD screening programme within Thailand’s national health system and preventive health framework. The research team would like to express their sincere appreciation to all individuals and organisations involved in this national programme, including local collaborators, provincial coordinators, and administrative and public health personnel, whose dedication and support were essential to the successful implementation of the project. We also gratefully acknowledge the cooperation of government agencies, provincial public health offices, hospitals, and provincial Red Cross chapters across all participating provinces. This project was implemented through the collaboration of the following provinces and their affiliated institutions: Nakhon Sawan Province : Governor of Nakhon Sawan phase 1 (Mr. Thawee Sermphakdikul), President of the Nakhon Sawan Provincial Red Cross Chapter (Mrs. Waraporn Sermphakdikul )and Governor of Nakhon Sawan and President of the Nakhon Sawan Provincial Red Cross Chapter phase 2 (Ms. Chutiphon Sechang), Nakhon Sawan Provincial Public Health Office (Dr. Amnart Noikham , Mr.Teera Kangkhetkron , Miss Nattaya Pattaveenontawong and Miss Wilawan Nunart) Sawanpracharak Hospital (Rattikorn Thungsuk, Chattama Chairat and Mrs.Tassanee Tabthimthai). Nakhon Pathom Province : Governor of Nakhon Pathom and President of the Nakhon Pathom Provincial Red Cross Chapter (Ms. Arocha Nantamontry), Nakhon Pathom Hospital (Dr. Surachai Chokkrchitchai), Sam Phran Hospital (Dr. Tinnakorn Chuenchom), Nakhon Pathom Provincial Public Health Office (Mr.Suphat Katanyutita and Mr.Tawatchai Naksrisung). Nonthaburi Province : Governor of Nonthaburi (Mr. Kiattisak Trongsiri), President of the Nonthaburi Provincial Red Cross Chapter (Mrs. Phonsri Tongsiri), Nonthaburi Provincial Public Health Office (Dr. Paripon Juljerm and Mrs. Sineenart Rattanapunpanit) Pranangklao Hospital (Dr. Sakol Sookprome). Chiang Rai Province : Governor of Chiang Rai (Mr. Charin Tongsuk), President of the Chiang Rai Provincial Red Cross Chapter (Mrs. Sineenat Thongsuk) Chiang Rai Provincial Public Health Office (Dr. Ekkachai Kumlue) Chiang Rai Prachanukroh Hospital (Dr. Achara Laongnualpanich, Miss Netphit Khamhoi and Mrs. Jintana Yoongrum) Mayor of Chiang Rai City Municipality (Mr. Wanchai Jongsutanamanee). Samut Prakan Province : Governor of Samut Prakan (Mr. Suphamit Chinnasri), President of the Samut Prakan Provincial Red Cross Chapter (Miss Orawan Chinnasri), Samut Prakan Provincial Red Cross Chapter (Mrs. Kanchana Pansiri and Mr. Somsak Kaewsana) Samut Prakan Provincial Public Health Office (Mr. Prapart Phookduang and Mrs. Walaipun Sumritwatcharsai) Samut Prakan Hospital (Dr. Pimwalai Chulapimphan). Phetchaburi Province : Governor of Phetchaburi (Pol. Lt. Col. Phopchanok Chalanukhro), President of the Phetchaburi Provincial Red Cross Chapter (Mrs. Natthinee Kongbuchakiat), PhetchaburiProvincial Public Health Office (Mr. Chartchai Kitiyanun, Miss Sununtinee Rungsiriwattanakij and Miss Phiyawan Phobata) Phra Chom Klao Hospital (Dr. Attasit Nawaapisak). Sisaket Province : Governor of Sisaket (Mr. Anupong Suksamonit), President of the Sisaket Provincial Red Cross Chapter (Ms. Phakanan Sila-art), Sisaket Provincial Public Health Office (Dr.Thanong Veerasangpong Ms.Sineenuch Wirasaengpong and Ms. Mali Supatti), Sisaket Hospital (Dr.Sitthipan Janpong). Pathum Thani Province : Governor of Pathum Thani (Mr. Somkid Chanthamruek), President of the Pathum Thani Provincial Red Cross Chapter (Asst. Prof. Dr. Sasithorn Sujarittanakarn) Pathum Thani Provincial Public Health Office (Dr. Non Jindavech and Mr. Apichon Jeensavake) Pathum Thani Hospital (Dr. Saralee Chindamang and Ms. Kamolruetai Suphakawanich). References Global Burden of Disease Collaborators. Global age-sex-specific mortality, life expectancy, and population estimates in 204 countries and territories and 811 subnational locations, 1950–2021, and the impact of the COVID-19 pandemic: a comprehensive demographic analysis for the Global Burden of Disease Study 2021. Lancet. 2024;403(10440):1989–2056. Albin R, Grotewold N. What is the Parkinson Pandemic? Mov Disord. 2023;38(12):2141–4. Rossi A, Berger K, Chen H, Leslie D, Mailman RB, Huang X. Projection of the prevalence of Parkinson's disease in the coming decades: Revisited. Mov Disord. 2018;33(1):156–9. Payami H, Cohen G, Murchison CF, Sampson TR, Standaert DG, Wallen ZD. Population fraction of Parkinson's disease attributable to preventable risk factors. NPJ Parkinsons Dis. 2023;9(1):159. Su D, Cui Y, He C, Yin P, Bai R, Zhu J, Lam JST, Zhang J, Yan R, Zheng X, et al. Projections for prevalence of Parkinson's disease and its driving factors in 195 countries and territories to 2050: modelling study of Global Burden of Disease Study 2021. BMJ. 2025;388:e080952. Luo Y, Qiao L, Li M, Wen X, Zhang W, Li X. Global, regional, national epidemiology and trends of Parkinson's disease from 1990 to 2021: findings from the Global Burden of Disease Study 2021. Front Aging Neurosci. 2024;16:1498756. Bhidayasiri R, Wannachai N, Limpabandhu S, Choeytim S, Suchonwanich Y, Tananyakul S, Tharathep C, Panjapiyakul P, Srismith R, Chimabutra K, et al. A national registry to determine the distribution and prevalence of Parkinson's disease in Thailand: implications of urbanization and pesticides as risk factors for Parkinson's disease. Neuroepidemiology. 2011;37(3–4):222–30. Chaudhuri KR, Azulay JP, Odin P, Lindvall S, Domingos J, Alobaidi A, Kandukuri PL, Chaudhari VS, Parra JC, Yamazaki T, et al. Economic Burden of Parkinson's Disease: A Multinational, Real-World, Cost-of-Illness Study. Drugs Real World Outcomes; 2024. Cunha M, Almeida H, Guimarães I, Ferreira LN. Economic burden of Parkinson’s disease and research trends: a bibliometric analysis. J Public Health 2024. Khan AZ, Lavu D, Neal R. Parkinson's disease: A scoping review of the quantitative and qualitative evidence of its diagnostic accuracy in primary care. Br J Gen Pract 2023. Bhidayasiri R, Phokaewvarangkul O, Sakdisornchai K, Boonpang K, Chaudhuri KR, Parsons J, Lolekha P, Chairangsaris P, Srivanitchapoom P, Benedierks S, et al. Establishing apomorphine treatment in Thailand: understanding the challenges and opportunities of Parkinson's disease management in developing countries. Expert Rev Neurother. 2020;20(6):523–37. Bhidayasiri R, Virameteekul S, Sukoandari B, Tran TN, Lim TT. Challenges of Parkinson’s Disease Care in Southeast Asia. In: NeuroPsychopharmacotherapy. edn. Edited by Riederer P, Laux G, Nagatsu T, Le W, Riederer C. Cham: Springer International Publishing; 2020: 1–21. Lim SY, Tan AH, Ahmad-Annuar A, Klein C, Tan LCS, Rosales RL, Bhidayasiri R, Wu YR, Shang HF, Evans AH et al. Parkinson's disease in the Western Pacific Region. Lancet Neurol 2019. Thailand TNS. Number of Board-Certified and Certified Neurologists in Thailand and Neurology Residency Training Capacity (1964–2025). In.; 2025. Dahodwala N, Li P, Jahnke J, Ladage VP, Pettit AR, Kandukuri PL, Bao Y, Zamudio J, Jalundhwala YJ, Doshi JA. Burden of Parkinson's Disease by Severity: Health Care Costs in the U.S. Medicare Population. Mov Disord. 2021;36(1):133–42. Hjalte F, Norlin JM, Kellerborg K, Odin P. Parkinson's disease in Sweden-resource use and costs by severity. Acta Neurol Scand. 2021;144(5):592–9. Findley LJ, Wood E, Lowin J, Roeder C, Bergman A, Schifflers M. The economic burden of advanced Parkinson's disease: an analysis of a UK patient dataset. J Med Econ. 2011;14(1):130–9. Feigin VL, Vos T, Nichols E, Owolabi MO, Carroll WM, Dichgans M, Deuschl G, Parmar P, Brainin M, Murray C. The global burden of neurological disorders: translating evidence into policy. Lancet Neurol. 2020;19(3):255–65. Winkler AS. The growing burden of neurological disorders in low-income and middle-income countries: priorities for policy making. Lancet Neurol. 2020;19(3):200–2. Diseases GBD, Injuries C. Global incidence, prevalence, years lived with disability (YLDs), disability-adjusted life-years (DALYs), and healthy life expectancy (HALE) for 371 diseases and injuries in 204 countries and territories and 811 subnational locations, 1990–2021: a systematic analysis for the Global Burden of Disease Study 2021. Lancet. 2024;403(10440):2133–61. Dorsey ER, Sherer T, Okun MS, Bloem BR. The Emerging Evidence of the Parkinson Pandemic. J Parkinsons Dis. 2018;8(s1):S3–8. Bhidayasiri R. Old problems, new solutions: harnessing technology and innovation in Parkinson's disease-evidence and experiences from Thailand. J Neural Transm (Vienna) 2024. Bhidayasiri R, Kalia LV, Bloem BR. Tackling Parkinson's Disease as a Global Challenge. J Parkinsons Dis. 2023;13(8):1277–80. Bhidayasiri R, Goetz CG. Chap. 2 - Embracing the promise of artificial intelligence to improve patient care in movement disorders. In: Handbook of Digital Technologies in Movement Disorders. edn. Edited by Bhidayasiri R, Maetzler W: Academic Press; 2024: 11–23. Bhidayasiri R, Mathur S, Maetzler W. Chap. 1 - We are living in the Parkinson's pandemic: how can multi-stakeholders utilize digital technologies effectively? In: Handbook of Digital Technologies in Movement Disorders. edn. Edited by Bhidayasiri R, Maetzler W: Academic Press; 2024: 3–9. Bhidayasiri R. The grand challenge at the frontiers of neurotechnology and its emerging clinical applications. Front Neurol. 2024;15:1314477. Virameteekul S, Shin C, Hirczy SS, Sarva H, Paul SS, Maetzler W, Mirelman A, Schneider RB, Hausdorff JM, Vizcarra JA et al. Assessing Digital Health Technologies for Outcome Measurement in Parkinson's Disease Drug Trials: A Systematic Review. Mov Disord 2025. Osei E, Mashamba-Thompson TP. Mobile health applications for disease screening and treatment support in low-and middle-income countries: A narrative review. Heliyon. 2021;7(3):e06639. McCool J, Dobson R, Whittaker R, Paton C. Mobile Health (mHealth) in Low- and Middle-Income Countries. Annu Rev Public Health. 2022;43:525–39. Dino MJ, Thiamwong L, Xie R, Malacas MK, Hernandez R, Balbin PT, Vital JC, Rivero JA, Xi VW. Mobile health (mHealth) technologies for fall prevention among older adults in low-middle income countries: bibliometrics, network analysis and integrative review. Front Digit Health. 2025;7:1559570. Chong SOK, Pedron S, Abdelmalak N, Laxy M, Stephan AJ. An umbrella review of effectiveness and efficacy trials for app-based health interventions. NPJ Digit Med. 2023;6(1):233. Reidy C, Papoutsi C, Kc S, Gudgin B, Laverty AA, Greaves F, Powell J. Qualitative evaluation of the implementation and national roll-out of the NHS App in England. BMC Med. 2025;23(1):20. Chawla R, Karkhanis P, Shah M, Das A, Sharma R, Almaula D, Venkatesh P, Singh HV, Kumar M, Samanta R, et al. Artificial intelligence for advancing eye care in resource-poor settings: Assessing the predictive accuracy of an AI-model for diabetic retinopathy screening in India. Glob Epidemiol. 2025;9:100209. Yu Y, Zhang S, Li H, Xue F. A bayesian network model for neurocognitive disorders digital screening in Chinese population: development and validation study. BMC Psychiatry. 2025;25(1):760. Kohrt BA, Ojagbemi A, Luitel NP, Bakolis I, Bello T, McCrone P, Taylor Salisbury T, Jordans MJD, Votruba N, Carswell K, et al. An App-Based WHO Mental Health Guide for Depression Detection: A Cluster Randomized Clinical Trial. JAMA Netw Open. 2025;8(5):e2512064. Keynejad R, Spagnolo J, Thornicroft G. WHO mental health gap action programme (mhGAP) intervention guide: updated systematic review on evidence and impact. Evid Based Ment Health. 2021;24(3):124–30. Nong TTT, Nguyen GH, Lepe A, Tran TB, Nguyen LTP, Koot JAR. Challenges and Opportunities in Digital Screening for Hypertension and Diabetes Among Community Groups of Older Adults in Vietnam: Mixed Methods Study. J Med Internet Res. 2024;26:e54127. Fritz M, Grimm M, Weber I, Yom-Tov E, Praditya B. Can social media encourage diabetes self-screenings? A randomized controlled trial with Indonesian Facebook users. NPJ Digit Med. 2024;7(1):245. Singh DKA, Goh JW, Shaharudin MI, Shahar S. A Mobile App (FallSA) to Identify Fall Risk Among Malaysian Community-Dwelling Older Persons: Development and Validation Study. JMIR Mhealth Uhealth. 2021;9(10):e23663. Ooi CY, Ng CJ, Sales A, Teo CH. Pilot implementation study of a web-based men's health screening app in primary care during COVID-19: a mixed-methods approach. BMC Health Serv Res. 2024;24(1):1219. Ruamviboonsuk P, Tiwari R, Sayres R, Nganthavee V, Hemarat K, Kongprayoon A, Raman R, Levinstein B, Liu Y, Schaekermann M, et al. Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study. Lancet Digit Health. 2022;4(4):e235–44. Insightera. Digital 2025 Thailand: Key Highlights from We Are Social & Meltwater Report. In.; 2025. Sukphan J, Kitdamrongtam P, Satjasomboon S. Rethinking Digital Access in Thailand. Rajamangala Univ Technol Tawan-ok Social Sci J. 2024;13(1):1–10. Robru K, Setthasuravich P, Pukdeewut A, Wetchakama S. Internet use for health-related purposes among older people in Thailand: an analysis of nationwide cross-sectional data. Informatics. 2024;11(3):55. Thaneewat N, Sermsri N. Development of digital literacy skills in using government applications for the elderly in Samut Prakan Province. Procedia Multidisciplinary Res. 2024;2(11):53. Sureephong P, Laothiang A, Inthawong K, Satprasoet S, Auttajinda N. Digital transformation for non-communicable disease prevention and control in Thailand by using a mixed methods approach. In: Product lifecycle management Leveraging AI, digital twins, and smart technologies (PLM 2024). Volume 741 edn. Edited by Sureephong P, Danjou C, Bouras A. Switzerland: Springer Nature; 2025. Vichitkunakorn P, Sathirapanya C, Buathong N, Sornsenee P, Chaichulee S, Donraman T. Developing web-based interventions for alcohol use screening and alcohol education administered by village health volunteers in the community setting. Drug Alcohol Depend. 2024;264:112461. Songserm N, Woradet S, Bureelerd O, Thongchai C, Thongprung S, Ali A. Effectiveness of Leader Village Health Volunteers Training Program on Preventing Cholangiocarcinoma in Thailand: Advantages for High-Risk Area with Limited Public Health Personnel. J Cancer Educ. 2021;36(6):1306–15. Bhidayasiri R, Sringean J, Phumphid S, Anan C, Thanawattano C, Deoisres S, Panyakaew P, Phokaewvarangkul O, Maytharakcheep S, Buranasrikul V, et al. The rise of Parkinson's disease is a global challenge, but efforts to tackle this must begin at a national level: a protocol for national digital screening and eat, move, sleep lifestyle interventions to prevent or slow the rise of non-communicable diseases in Thailand. Front Neurol. 2024;15:1386608. Lean PL, Sringean J, Saengmanee T, Rattanajun P, Chaisongkram A, Bhidayasiri R. Clinical characteristics and motor dysfunction in probable REM sleep behavior disorder(pRBD): Insights from CHECK-PD community-based screening project. Mov Disord 2025, 40. Sringean J, Phumphid S, Anan C, Meesri J, Rattanajun P, Wehhinhiran S, Chantadunga A, Sanengmanee T, Bhidayasiri R. The discrepancy between self-reported hyposmia and objective assessment by Sniffin’ sticks in high risk of synucleinopathies and healthy controls. Mov Disord 2025, 40. Amouzadeh E, Dianat I, Faradmal J, Babamiri M. Optimizing mobile app design for older adults: systematic review of age-friendly design. Aging Clin Exp Res. 2025;37(1):248. Arslan STA, O'Connor S, Stanmore E. Human-Centred Design of Digital Health Dashboards for Management of Health in the Care of Older Adults: A Scoping Review. Stud Health Technol Inf. 2025;329:1986–7. Azadi H, Akbarzadeh-Totonchi MR, Jahani Y, Gohari SH, Khajouei R. Evaluation of mobile applications related to patients with Parkinson's disease based on their essential features and capabilities. BMC Med Inf Decis Mak. 2024;24(1):407. McCarthy B, Sabharwal JK, Chawla S. Old age or cognitive decline? Examining the usability of a mobile health app for older Australians. Inf Health Soc Care. 2024;49(1):83–97. Young SR, Dworak EM, Byrne GJ, Jones CM, Yao L, Yoshino Benavente JN, Diaz MV, Curtis L, Gershon R, Wolf M, et al. Remote Self-Administration of Cognitive Screeners for Older Adults Prior to a Primary Care Visit: Pilot Cross-Sectional Study of the Reliability and Usability of the MyCog Mobile Screening App. JMIR Form Res. 2024;8:e54299. Duracinsky M, Brown Hajdukova E, Peretz F, Sauzin J, Gouider-Khouja N, Atlani C, Dalili D. Collecting Feedback From Neurologists and Patients to Guide Development of a Parkinson Disease App (DigiPark): Qualitative, Noninterventional Study. JMIR Hum Factors. 2024;11:e55032. Triantafyllidis A, Segkouli S, Zygouris S, Michailidou C, Avgerinakis K, Fappa E, Vassiliades S, Bougea A, Papagiannakis N, Katakis I et al. Mobile App Interventions for Parkinson's Disease, Multiple Sclerosis and Stroke: A Systematic Literature Review. Sens (Basel) 2023, 23(7). Linares-Del Rey M, Vela-Desojo L, Cano-de la Cuerda R. Mobile phone applications in Parkinson's disease: A systematic review. Neurologia (Engl Ed). 2019;34(1):38–54. Lee J, Yeom I, Chung ML, Kim Y, Yoo S, Kim E. Use of Mobile Apps for Self-care in People With Parkinson Disease: Systematic Review. JMIR Mhealth Uhealth. 2022;10(1):e33944. Glasgow RE, Vogt TM, Boles SM. Evaluating the public health impact of health promotion interventions: the RE-AIM framework. Am J Public Health. 1999;89(9):1322–7. Glasgow RE, Klesges LM, Dzewaltowski DA, Estabrooks PA, Vogt TM. Evaluating the impact of health promotion programs: using the RE-AIM framework to form summary measures for decision making involving complex issues. Health Educ Res. 2006;21(5):688–94. Glasgow RE, Harden SM, Gaglio B, Rabin B, Smith ML, Porter GC, Ory MG, Estabrooks PA. RE-AIM Planning and Evaluation Framework: Adapting to New Science and Practice With a 20-Year Review. Front Public Health. 2019;7:64. Van Den Eeden SK, Tanner CM, Bernstein AL, Fross RD, Leimpeter A, Bloch DA, Nelson LM. Incidence of Parkinson's disease: variation by age, gender, and race/ethnicity. Am J Epidemiol. 2003;157(11):1015–22. Postuma RB, Berg D. Prodromal Parkinson's Disease: The Decade Past, the Decade to Come. Mov Disord. 2019;34(5):665–75. Brooke J. SUS - A quick and dirty usability scale. In: Usability Evaluation in Industry. edn. Edited by Jordan PW, Thomas B, Weerdmeester BA, McClelland IL: Taylor & Francis; 1996: 189–194. Schrepp M, Hinderks A, Thomaschewski J. Design and Evaluation of a Short Version of the User Experience Questionnaire (UEQ-S). Int J Interact Multimedia Artif Intell. 2017;4:103. von Elm E, Altman DG, Egger M, Pocock SJ, Gotzsche PC, Vandenbroucke JP, Initiative S. The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies. Lancet. 2007;370(9596):1453–7. El Arab RA, Abu-Mahfouz MS, Abuadas FH, Alzghoul H, Almari M, Ghannam A, Seweid MM. Bridging the Gap: From AI Success in Clinical Trials to Real-World Healthcare Implementation-A Narrative Review. Healthcare (Basel) 2025, 13(7). Overgaard SM, Graham MG, Brereton T, Pencina MJ, Halamka JD, Vidal DE, Economou-Zavlanos NJ. Implementing quality management systems to close the AI translation gap and facilitate safe, ethical, and effective health AI solutions. NPJ Digit Med. 2023;6(1):218. D’Amour A, Heller K, Moldovan D, Adlam B, Alipanahi B, Beutel A. Underspecification presents challenges for credibility in modern machine learning. J Mach Learn Res. 2022;23(266):1–61. Adnan HS, Shidani A, Clifton L, Bankhead CR, Perera-Salazar R. Implementation framework for AI deployment at scale in healthcare systems. iScience. 2025;28(5):112406. Wamala Andersson S, Gonzalez MP. Digital health literacy-a key factor in realizing the value of digital transformation in healthcare. Front Digit Health. 2025;7:1461342. Esper CD, Valdovinos BY, Schneider RB. The Importance of Digital Health Literacy in an Evolving Parkinson's Disease Care System. J Parkinsons Dis. 2024;14(s1):S181–9. Halabi R, Selvarajan R, Lin Z, Herd C, Li X, Kabrit J, Tummalacherla M, Chaibub Neto E, Pratap A. Comparative Assessment of Multimodal Sensor Data Quality Collected Using Android and iOS Smartphones in Real-World Settings. Sensors (Basel) 2024, 24(19). Gilbert S, Pimenta A, Stratton-Powell A, Welzel C, Melvin T. Continuous Improvement of Digital Health Applications Linked to Real-World Performance Monitoring: Safe Moving Targets? Mayo Clin Proc Digit Health. 2023;1(3):276–87. Ivanova A, Shcherbak A, Nesteruk S, Bril E, Baldycheva A, Somov A. Parkinson’s disease detection through multimodal data analysis. Smart Health. 2025;38:100618. Prashanth R, Dutta Roy S, Mandal PK, Ghosh S. High-Accuracy Detection of Early Parkinson's Disease through Multimodal Features and Machine Learning. Int J Med Inf. 2016;90:13–21. Carroll JK, Moorhead A, Bond R, LeBlanc WG, Petrella RJ, Fiscella K. Who Uses Mobile Phone Health Apps and Does Use Matter? A Secondary Data Analytics Approach. J Med Internet Res. 2017;19(4):e125. Ben-Shlomo Y, Darweesh S, Llibre-Guerra J, Marras C, San Luciano M, Tanner C. The epidemiology of Parkinson's disease. Lancet. 2024;403(10423):283–92. Tian L, Wong EL, Dong D, Cheung AW, Chan SK, Cao Y, Mok PKH, Zhou L, Xu RH. Improving mental health literacy using web- or app-based interventions: A scoping review. Digit Health. 2024;10:20552076241243133. Grace B, Wise LA, Nieroda M, Egbunike J, Usman NO. Digital health technologies to transform women's health innovation and inclusive research. BMJ. 2025;391:e085682. Borges do Nascimento IJ, Abdulazeem HM, Weerasekara I, Marquez J, Vasanthan LT, Deeken G, Morgan R, Tan HL, Yordi Aguirre I, Osteengaard L, et al. Transforming women's health, empowerment, and gender equality with digital health: evidence-based policy and practice. Lancet Digit Health. 2025;7(6):100858. Cen C, Peng H, Li X, Zhang Z, Hu J, Wang Z, Jiang T. Interactive interfaces and wearable technologies for enhancing health management among older adults: a systematic review. Front Med (Lausanne). 2025;12:1724828. Kannan L, Lelo de Larrea-Mancera ES, Maniglia M, Vodyanyk MM, Gallun FJ, Jaeggi SM, Seitz AR. Multidimensional relationships between sensory perception and cognitive aging. Front Aging Neurosci. 2024;16:1484494. Moon J, Huh YL, Cho HY, Kim C, Lee H, Jang DP, Cho BH. Exploring Age-Related Patterns in Smartphone Keystroke Dynamics Considering Temporal Variability: Cross-Sectional Study With AI-Based Analysis. JMIR Mhealth Uhealth. 2025;13:e80094. Hicks JL, Althoff T, Sosic R, Kuhar P, Bostjancic B, King AC, Leskovec J, Delp SL. Best practices for analyzing large-scale health data from wearables and smartphone apps. NPJ Digit Med. 2019;2:45. Carlozzi NE, Troost J, Lombard WL, Miner JA, Graves CM, Choi SW, Wu Z, Sen S, Sander AM. Completion and Compliance Rates for an Intensive mHealth Study Design to Promote Self-Awareness and Self-Care Among Care Partners of Individuals With Traumatic Brain Injury: Secondary Analysis of a Randomized Controlled Trial. JMIR Mhealth Uhealth. 2025;13:e73772. Daniels K, Quadflieg K, Robijns J, De Vry J, Van Alphen H, Van Beers R, Sourbron B, Vanbuel A, Meekers S, Mattheeussen M et al. From Steps to Context: Optimizing Digital Phenotyping for Physical Activity Monitoring in Older Adults by Integrating Wearable Data and Ecological Momentary Assessment. Sens (Basel) 2025, 25(3). Kiang MV, Chen JT, Krieger N, Buckee CO, Alexander MJ, Baker JT, Buckner RL, Coombs G 3rd, Rich-Edwards JW, Carlson KW, et al. Sociodemographic characteristics of missing data in digital phenotyping. Sci Rep. 2021;11(1):15408. Currey D, Torous J. Increasing the value of digital phenotyping through reducing missingness: a retrospective review and analysis of prior studies. BMJ Ment Health 2023, 26(1). Calvert E, Hackett K, Torous J, Giovannetti T. Barriers and facilitators to usability of a smartphone-based digital mental health tool in older adults: Insights from a secondary analysis of mindLAMP. Int Psychogeriatr 2025:100123. Dwyer B, Flathers M, Burns J, Mikkelson J, Perlmutter E, Chen K, Ram N, Torous J. Assessing Digital Phenotyping for App Recommendations and Sustained Engagement: Cohort Study. JMIR Form Res. 2024;8:e62725. Amagai S, Pila S, Kaat AJ, Nowinski CJ, Gershon RC. Challenges in Participant Engagement and Retention Using Mobile Health Apps: Literature Review. J Med Internet Res. 2022;24(4):e35120. Bot BM, Suver C, Neto EC, Kellen M, Klein A, Bare C, Doerr M, Pratap A, Wilbanks J, Dorsey ER, et al. The mPower study, Parkinson disease mobile data collected using ResearchKit. Sci Data. 2016;3:160011. Lipsmeier F, Taylor KI, Kilchenmann T, Wolf D, Scotland A, Schjodt-Eriksen J, Cheng WY, Fernandez-Garcia I, Siebourg-Polster J, Jin L, et al. Evaluation of smartphone-based testing to generate exploratory outcome measures in a phase 1 Parkinson's disease clinical trial. Mov Disord. 2018;33(8):1287–97. Noyce AJ, Bestwick JP, Silveira-Moriyama L, Hawkes CH, Knowles CH, Hardy J, Giovannoni G, Nageshwaran S, Osborne C, Lees AJ, et al. PREDICT-PD: identifying risk of Parkinson's disease in the community: methods and baseline results. J Neurol Neurosurg Psychiatry. 2014;85(1):31–7. Noyce AJ, R'Bibo L, Peress L, Bestwick JP, Adams-Carr KL, Mencacci NE, Hawkes CH, Masters JM, Wood N, Hardy J et al. PREDICT-PD: An online approach to prospectively identify risk indicators of Parkinson's disease. Mov Disord 2017, 32(2):219–226. Parkinson’s Disease. Early Detection and Monitoring with KeySense [ https://www.parkinsons-research.org/index.htm] Arora S, Baig F, Lo C, Barber TR, Lawton MA, Zhan A, Rolinski M, Ruffmann C, Klein JC, Rumbold J, et al. Smartphone motor testing to distinguish idiopathic REM sleep behavior disorder, controls, and PD. Neurology. 2018;91(16):e1528–38. Lipsmeier F, Taylor KI, Postuma RB, Volkova-Volkmar E, Kilchenmann T, Mollenhauer B, Bamdadian A, Popp WL, Cheng WY, Zhang YP, et al. Reliability and validity of the Roche PD Mobile Application for remote monitoring of early Parkinson's disease. Sci Rep. 2022;12(1):12081. Mancini M, Horak FB. Potential of APDM mobility lab for the monitoring of the progression of Parkinson's disease. Expert Rev Med Devices. 2016;13(5):455–62. Stamate C, Saez Pons J, Weston D, Roussos G. PDKit: A data science toolkit for the digital assessment of Parkinson's Disease. PLoS Comput Biol. 2021;17(3):e1008833. Ellis RJ, Ng YS, Zhu S, Tan DM, Anderson B, Schlaug G, Wang Y. A Validated Smartphone-Based Assessment of Gait and Gait Variability in Parkinson's Disease. PLoS ONE. 2015;10(10):e0141694. Kuosmanen E, Wolling F, Vega J, Kan V, Nishiyama Y, Harper S, Van Laerhoven K, Hosio S, Ferreira D. Smartphone-Based Monitoring of Parkinson Disease: Quasi-Experimental Study to Quantify Hand Tremor Severity and Medication Effectiveness. JMIR Mhealth Uhealth. 2020;8(11):e21543. Pepa L, Capecci M, Andrenelli E, Ciabattoni L, Spalazzi L, Ceravolo MG. A fuzzy logic system for the home assessment of freezing of gait in subjects with Parkinsons disease. Expert Syst Appl. 2020;147:113197. Borzì L, Olmo G, Artusi CA, Fabbri M, Rizzone MG, Romagnolo A, Zibetti M, Lopiano L. A new index to assess turning quality and postural stability in patients with Parkinson's disease. Biomed Signal Process Control. 2020;62:102059. Su D, Liu Z, Jiang X, Zhang F, Yu W, Ma H, Wang C, Wang Z, Wang X, Hu W, et al. Simple Smartphone-Based Assessment of Gait Characteristics in Parkinson Disease: Validation Study. JMIR Mhealth Uhealth. 2021;9(2):e25451. Kim H, Lee HJ, Lee W, Kwon S, Kim SK, Jeon HS, Park H, Shin CW, Yi WJ, Jeon BS, et al. Unconstrained detection of freezing of Gait in Parkinson's disease patients using smartphone. Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:3751–4. Motolese F, Magliozzi A, Puttini F, Rossi M, Capone F, Karlinski K, Stark-Inbar A, Yekutieli Z, Di Lazzaro V, Marano M. Parkinson's Disease Remote Patient Monitoring During the COVID-19 Lockdown. Front Neurol. 2020;11:567413. Habets J, Heijmans M, Herff C, Simons C, Leentjens AF, Temel Y, Kuijf M, Kubben P. Mobile Health Daily Life Monitoring for Parkinson Disease: Development and Validation of Ecological Momentary Assessments. JMIR Mhealth Uhealth. 2020;8(5):e15628. Landers MR, Ellis TD. A Mobile App Specifically Designed to Facilitate Exercise in Parkinson Disease: Single-Cohort Pilot Study on Feasibility, Safety, and Signal of Efficacy. JMIR Mhealth Uhealth. 2020;8(10):e18985. Ellis TD, Cavanaugh JT, DeAngelis T, Hendron K, Thomas CA, Saint-Hilaire M, Pencina K, Latham NK. Comparative Effectiveness of mHealth-Supported Exercise Compared With Exercise Alone for People With Parkinson Disease: Randomized Controlled Pilot Study. Phys Ther. 2019;99(2):203–16. Butson CR, Tamm G, Jain S, Fogal T, Kruger J. Evaluation of Interactive Visualization on Mobile Computing Platforms for Selection of Deep Brain Stimulation Parameters. IEEE Trans Vis Comput Graph. 2013;19(1):108–17. Additional Declarations No competing interests reported. Supplementary Files Suppl1CheckPDImplementationrbh08Jan2026.mp4 Suppl2CheckPDImplementationrbh08Jan2026.docx Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 30 Mar, 2026 Reviews received at journal 25 Mar, 2026 Reviews received at journal 11 Mar, 2026 Reviewers agreed at journal 27 Feb, 2026 Reviewers agreed at journal 09 Feb, 2026 Reviews received at journal 09 Feb, 2026 Reviewers agreed at journal 04 Feb, 2026 Reviewers agreed at journal 26 Jan, 2026 Reviewers agreed at journal 22 Jan, 2026 Reviewers agreed at journal 21 Jan, 2026 Reviewers invited by journal 21 Jan, 2026 Editor invited by journal 13 Jan, 2026 Editor assigned by journal 12 Jan, 2026 Submission checks completed at journal 12 Jan, 2026 First submitted to journal 09 Jan, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8565015","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":578924795,"identity":"7ebb6b8b-43db-4f78-9c48-c25418f3b287","order_by":0,"name":"Roongroj Bhidayasiri","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsElEQVRIiWNgGAWjYDACCR7GB4wNDDJApgHRWpgNgFp4SNLCJkGaFvPZvccqfu44zMM/u3kDw8c9tYS1yNw5l3az98xhHok7xwoYZzw7ToS7JHLMbjO2HeZhuJFjwMxz4BhxWopBWuRJ0sIM0mIA0VJDhBaZM8aSvW3pPIZAvxycceAAEVqkeww//GyzlpO73bzxwYcDdYS1IGlmYABacZhELUBAki2jYBSMglEwQgAA3bs6oj18NLwAAAAASUVORK5CYII=","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":true,"prefix":"","firstName":"Roongroj","middleName":"","lastName":"Bhidayasiri","suffix":""},{"id":578924796,"identity":"84ecdebf-e45f-4b19-a86d-2e0f3e61a2d9","order_by":1,"name":"Saisamorn Phumphid","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Saisamorn","middleName":"","lastName":"Phumphid","suffix":""},{"id":578924797,"identity":"382accdf-4c62-48b4-a1ea-10d4848171be","order_by":2,"name":"Jirada Sringean","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Jirada","middleName":"","lastName":"Sringean","suffix":""},{"id":578924798,"identity":"7d8ca62c-ab58-408c-b14f-b082556bc0a1","order_by":3,"name":"Chanawat Anan","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Chanawat","middleName":"","lastName":"Anan","suffix":""},{"id":578924799,"identity":"759f0ed4-7f75-4869-9444-2ab3a54b9d87","order_by":4,"name":"Teerawat Laosombat","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Teerawat","middleName":"","lastName":"Laosombat","suffix":""},{"id":578924800,"identity":"d27de7ae-3961-47e4-9741-64948d319574","order_by":5,"name":"Jeeranun Meesri","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Jeeranun","middleName":"","lastName":"Meesri","suffix":""},{"id":578924801,"identity":"842eff11-f682-4272-90fa-51a50167dee7","order_by":6,"name":"Sunaree Wekhinhiran","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Sunaree","middleName":"","lastName":"Wekhinhiran","suffix":""},{"id":578924802,"identity":"4c92c4cc-7e6e-4684-9722-54b64af295b1","order_by":7,"name":"Natthaphat Leabthong","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Natthaphat","middleName":"","lastName":"Leabthong","suffix":""},{"id":578924803,"identity":"6a878a4b-aa34-483d-9075-47e53357faaa","order_by":8,"name":"Onanong Phokaewvarangkul","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Onanong","middleName":"","lastName":"Phokaewvarangkul","suffix":""},{"id":578924804,"identity":"044bb0f0-0fbf-47b1-b188-93509412efdb","order_by":9,"name":"Decho Surangsrirat","email":"","orcid":"","institution":"National Science and Technology Development Agency","correspondingAuthor":false,"prefix":"","firstName":"Decho","middleName":"","lastName":"Surangsrirat","suffix":""},{"id":578924805,"identity":"a57ed281-0b0e-4159-b541-eae62d568919","order_by":10,"name":"Peerapon Vateekul","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Peerapon","middleName":"","lastName":"Vateekul","suffix":""},{"id":578924806,"identity":"e10b5270-7d51-4779-843e-15e5abd2485e","order_by":11,"name":"Zar Kyi Win","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Zar","middleName":"Kyi","lastName":"Win","suffix":""},{"id":578924807,"identity":"6f8cdb59-5bcd-40ff-ad48-4487eb943b05","order_by":12,"name":"Nurhussneeda Jeh-voh","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Nurhussneeda","middleName":"","lastName":"Jeh-voh","suffix":""},{"id":578924808,"identity":"0a456869-76e7-43c1-be85-462f31ab191a","order_by":13,"name":"Pattamon Panyakaew","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Pattamon","middleName":"","lastName":"Panyakaew","suffix":""},{"id":578924809,"identity":"e5ce37b4-2895-4050-8d50-f19c584c0449","order_by":14,"name":"Warongporn Phuenpathom","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Warongporn","middleName":"","lastName":"Phuenpathom","suffix":""},{"id":578924810,"identity":"cf52942e-c136-41b0-96c6-f3407ffad418","order_by":15,"name":"Suppata Maytharakcheep","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Suppata","middleName":"","lastName":"Maytharakcheep","suffix":""},{"id":578924811,"identity":"635f117b-4dbb-4874-8c90-9ac5492c0cbe","order_by":16,"name":"Priya Jagota","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Priya","middleName":"","lastName":"Jagota","suffix":""},{"id":578924813,"identity":"251a80ff-8ec6-473a-af33-0c825275c1f9","order_by":17,"name":"Varis Ratanasirisawad","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Varis","middleName":"","lastName":"Ratanasirisawad","suffix":""},{"id":578924815,"identity":"0b1bfc2d-21b7-4857-8505-0d4c6f99763b","order_by":18,"name":"Surasa Khongprasert","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Surasa","middleName":"","lastName":"Khongprasert","suffix":""},{"id":578924816,"identity":"f718c902-13bd-47eb-90b8-ea52d4ee10a6","order_by":19,"name":"Watchara Rattanachaisit","email":"","orcid":"","institution":"ChiangRai Prachanukroh Hospital","correspondingAuthor":false,"prefix":"","firstName":"Watchara","middleName":"","lastName":"Rattanachaisit","suffix":""},{"id":578924817,"identity":"1107471c-ba15-412d-9c75-14b1c26f7f14","order_by":20,"name":"Tittaya Prasertpan","email":"","orcid":"","institution":"Sawanpracharak Hospital","correspondingAuthor":false,"prefix":"","firstName":"Tittaya","middleName":"","lastName":"Prasertpan","suffix":""},{"id":578924818,"identity":"bb97339e-b047-403c-b361-c6a3eab9e767","order_by":21,"name":"Ornanong Udomsirithamrong","email":"","orcid":"","institution":"Bangkok Hospital","correspondingAuthor":false,"prefix":"","firstName":"Ornanong","middleName":"","lastName":"Udomsirithamrong","suffix":""},{"id":578924819,"identity":"c850d485-f673-4b17-b8a5-1b3849a0c8ed","order_by":22,"name":"Appasone Phoumindr","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Appasone","middleName":"","lastName":"Phoumindr","suffix":""},{"id":578924820,"identity":"c4bb1751-7823-49e9-b947-3f12eff70fd3","order_by":23,"name":"Nontakorn Likhitwitayawuid","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Nontakorn","middleName":"","lastName":"Likhitwitayawuid","suffix":""},{"id":578924821,"identity":"398ca0cf-ae6a-45e9-9533-af9750b31537","order_by":24,"name":"Thanachporn Saengmanee","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Thanachporn","middleName":"","lastName":"Saengmanee","suffix":""},{"id":578924822,"identity":"bcf43cd9-c39c-4bb6-85f9-9d18840016e1","order_by":25,"name":"Piyaporn Rattanajun","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Piyaporn","middleName":"","lastName":"Rattanajun","suffix":""},{"id":578924823,"identity":"688253dd-1017-4da0-89fd-a3a81cadb8a4","order_by":26,"name":"Kornake Horaruengdecha","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Kornake","middleName":"","lastName":"Horaruengdecha","suffix":""},{"id":578924824,"identity":"34c2c05e-6faa-4548-9b60-0d3243500764","order_by":27,"name":"Narumol Sukmueng","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Narumol","middleName":"","lastName":"Sukmueng","suffix":""},{"id":578924825,"identity":"cb6382bd-baa7-43b6-833b-a203f284590d","order_by":28,"name":"Punkorn Dornbunlon","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Punkorn","middleName":"","lastName":"Dornbunlon","suffix":""},{"id":578924826,"identity":"371d8dae-30aa-47a7-9a85-2c1072137448","order_by":29,"name":"Werasit Sittitrai","email":"","orcid":"","institution":"Thai Red Cross Society","correspondingAuthor":false,"prefix":"","firstName":"Werasit","middleName":"","lastName":"Sittitrai","suffix":""},{"id":578924827,"identity":"95319767-74eb-4cbe-844b-d89ee83a284a","order_by":30,"name":"Sukanda Vorachetbancha","email":"","orcid":"","institution":"Thai Red Cross Society","correspondingAuthor":false,"prefix":"","firstName":"Sukanda","middleName":"","lastName":"Vorachetbancha","suffix":""},{"id":578924828,"identity":"833de8ba-8e29-405c-acc7-47f7dbf942e1","order_by":31,"name":"Wittaya Chanchalong","email":"","orcid":"","institution":"Thai Red Cross Society","correspondingAuthor":false,"prefix":"","firstName":"Wittaya","middleName":"","lastName":"Chanchalong","suffix":""},{"id":578924829,"identity":"7c1990c8-965b-4b95-b674-ab85869c46ad","order_by":32,"name":"Aekamorn Phonsrithong","email":"","orcid":"","institution":"Thai Red Cross Society","correspondingAuthor":false,"prefix":"","firstName":"Aekamorn","middleName":"","lastName":"Phonsrithong","suffix":""},{"id":578924830,"identity":"3a9b067b-7bd1-4b6f-bd16-fa62ad69b72a","order_by":33,"name":"Pinit Kullavanijaya","email":"","orcid":"","institution":"Thai Red Cross Society","correspondingAuthor":false,"prefix":"","firstName":"Pinit","middleName":"","lastName":"Kullavanijaya","suffix":""},{"id":578924831,"identity":"db0a4994-dd0f-47d1-8ef6-0a27c9951aa3","order_by":34,"name":"Jintakan Sricholwattana","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Jintakan","middleName":"","lastName":"Sricholwattana","suffix":""},{"id":578924833,"identity":"7c1a8357-a90c-468d-ad5e-6b613aa16cfc","order_by":35,"name":"Vittratorn Chirapravati","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Vittratorn","middleName":"","lastName":"Chirapravati","suffix":""},{"id":578924836,"identity":"8639b6b3-3a17-4fed-be77-4961c3e882e4","order_by":36,"name":"Pradhana Chariyavilaskul","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Pradhana","middleName":"","lastName":"Chariyavilaskul","suffix":""},{"id":578924837,"identity":"50b0be6f-da51-4fc9-9fe9-77ece34ffc6d","order_by":37,"name":"Katevisuth Sukpisan","email":"","orcid":"","institution":"Chulalongkorn University","correspondingAuthor":false,"prefix":"","firstName":"Katevisuth","middleName":"","lastName":"Sukpisan","suffix":""},{"id":578924838,"identity":"116bcf23-583c-449d-9725-b7802df61185","order_by":38,"name":"Jadej Thammatacharee","email":"","orcid":"","institution":"National Health Security Office","correspondingAuthor":false,"prefix":"","firstName":"Jadej","middleName":"","lastName":"Thammatacharee","suffix":""},{"id":578924839,"identity":"49f11237-ad74-4437-adca-125af1662a60","order_by":39,"name":"Athaporn Limpanyalers","email":"","orcid":"","institution":"National Health Security Office","correspondingAuthor":false,"prefix":"","firstName":"Athaporn","middleName":"","lastName":"Limpanyalers","suffix":""},{"id":578924840,"identity":"4017d0d5-abec-4a29-be33-ebfb4f597652","order_by":40,"name":"Jakrawut Juthasong","email":"","orcid":"","institution":"Nakhon Sawan Public Health Office","correspondingAuthor":false,"prefix":"","firstName":"Jakrawut","middleName":"","lastName":"Juthasong","suffix":""},{"id":578924841,"identity":"ad51f04d-e5b6-457d-8914-272a7d781e67","order_by":41,"name":"Wiroj Rattanamornsakul","email":"","orcid":"","institution":"Nakhon Pathom Public Health Office","correspondingAuthor":false,"prefix":"","firstName":"Wiroj","middleName":"","lastName":"Rattanamornsakul","suffix":""},{"id":578924842,"identity":"4f260bf8-ea35-4d68-ae9a-d6328638a19d","order_by":42,"name":"Tej Bunnag","email":"","orcid":"","institution":"Thai Red Cross Society","correspondingAuthor":false,"prefix":"","firstName":"Tej","middleName":"","lastName":"Bunnag","suffix":""},{"id":578924843,"identity":"c7db2846-bf76-4c34-a60c-19aca2431a38","order_by":43,"name":"Grisada Boonrach","email":"","orcid":"","institution":"Thai Red Cross Society","correspondingAuthor":false,"prefix":"","firstName":"Grisada","middleName":"","lastName":"Boonrach","suffix":""}],"badges":[],"createdAt":"2026-01-10 02:23:51","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8565015/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8565015/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102425253,"identity":"607444d9-3c25-4176-af21-d41474397941","added_by":"auto","created_at":"2026-02-11 14:30:53","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":2205905,"visible":true,"origin":"","legend":"\u003cp\u003eGeographic distribution of CheckPD screening participants and neurologist availability across the first 10 provinces included in the national rollout.\u003cbr\u003e\nThis figure illustrates the spatial distribution of CheckPD screening participants across Thailand among the first 10 provinces included in the analysis. Provinces are shaded according to the number of screened participants, with darker shading indicating higher participation levels. The accompanying table summarises the absolute number and proportion of participants by province, while a second table indicates the number of neurologists available within each province. The number of neurologists per province was low across all included settings, highlighting a genuine limitation in local specialist availability.\u003c/p\u003e","description":"","filename":"Fig1CheckPDImplementationrbh08Jan2026.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/be383529836d8d2949fa4495.jpg"},{"id":102425264,"identity":"80863d89-fbf1-45d3-9aa3-2c280ed4c2d7","added_by":"auto","created_at":"2026-02-11 14:30:54","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":14617930,"visible":true,"origin":"","legend":"\u003cp\u003eThis figure illustrates the four coordinated implementation pathways used to deliver the CheckPD Parkinson’s disease (PD) screening programme in real-world settings across Thailand, designed to maximise population reach while accommodating different levels of digital literacy and access. (a) Field screening: This row depicts public-facing activities, including PD awareness and education sessions delivered to local communities, participant registration for screening activities, referral for further diagnostic evaluation by specialist physicians, and guidance on preventive and disease-slowing strategies for PD (Eat–Move–Sleep interventions). (b) Online education and facilitated digital screening sessions. This row represents online screening activities delivered through remotely conducted sessions. These sessions combined public education on PD with step-by-step instructions on how to use the CheckPD application and perform the digital screening tasks. Participants were encouraged to download the app and complete the screening either during the live session or independently thereafter, with guidance provided by trained facilitators or community leaders. (c) Community-based screening led by trained Village Health Volunteers (VHVs). This row illustrates the training and deployment of VHVs to support PD screening in community and rural settings. VHVs received structured training on PD awareness and the use of the CheckPD application, enabling them to assist community members, particularly older adults and individuals with limited digital literacy, in completing the digital screening tasks during community outreach activities. (d) Nationwide self-administered screening via direct app download. This row represents the fully self-directed screening pathway available nationwide throughout the study period. Members of the public independently downloaded the CheckPD mobile application, completed user registration, and performed the digital screening tasks without on-site assistance.\u003c/p\u003e","description":"","filename":"Fig2CheckPDImplementationrbh08Jan2026.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/31e4238f674ce8356a133183.jpg"},{"id":102425256,"identity":"bff16b45-9844-47d0-9f04-698e7f5c9132","added_by":"auto","created_at":"2026-02-11 14:30:53","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":12277658,"visible":true,"origin":"","legend":"\u003cp\u003eDetailed digital screening workflow of the CheckPD platform illustrating individual assessment components. This figure presents the complete CheckPD screening workflow, comprising four sequential components and twelve individual assessment steps. Component 1. App access and test initiation: (1) Access to testing information and screening modules; (2) Download of the CheckPD mobile application via iOS or Android platforms. Component 2. Motor and voice performance assessments: (3) Voice assessment through structured speech recording; (4) Rest tremor assessment; (5) Action tremor assessment during voluntary movement; (6) Finger tapping test with alternating key presses; (7) Finger dexterity test involving finger extension and flexion; (8) Gait assessment; (9) Balance assessment. Component 3. Symptom and risk factor evaluation:\u003cbr\u003e\n(10) Completion of a 20-item Parkinson’s disease risk assessment questionnaire capturing motor symptoms, non-motor symptoms, and established risk factors. Component 4. Automated analysis and feedback: (11) Automated risk evaluation and classification;\u003cbr\u003e\n(12) Personalised health guidance and recommendations based on screening results.\u003c/p\u003e","description":"","filename":"Fig3CheckPDImplementationrbh08Jan2026.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/0fe230b2071571153a9e85f4.jpg"},{"id":102425262,"identity":"97af656f-ac7d-476f-811a-b60b9ca3a060","added_by":"auto","created_at":"2026-02-11 14:30:54","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":3945861,"visible":true,"origin":"","legend":"\u003cp\u003eSystem architecture and data flow of the CheckPD platform. This diagram illustrates the integrated data architecture of the CheckPD ecosystem, comprising the CheckPD mobile application, a web-based clinical screening module, and a Business Intelligence (BI) dashboard. Multimodal screening data collected via the mobile application are stored in a secure NoSQL database operated by the Thai Red Cross Society, with selected structured data migrated to a SQL Data Warehouse managed by ChulaPD for analysis and reporting. Clinical diagnostic labels assigned by authorised neurologists are stored exclusively within the SQL environment. Aggregated data from both components are visualised through the BI dashboard to support programme monitoring, implementation evaluation, and governance.\u003c/p\u003e","description":"","filename":"Fig4CheckPDImplementationrbh08Jan2026.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/72a2ac3aa3d872bae2480fc4.jpg"},{"id":102425258,"identity":"7550010d-2b63-4ec3-96ac-2840bdc7036b","added_by":"auto","created_at":"2026-02-11 14:30:53","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":1167029,"visible":true,"origin":"","legend":"\u003cp\u003eFlow of user engagement, screening completion, and diagnostic outcomes in the CheckPD programme. This flowchart illustrates user progression through the CheckPD screening pathway, from national application downloads to screening completion and subsequent clinical evaluation. The figure depicts the total number of app downloads, users who initiated screening, and the subset of participants from the first 10 provinces included in the analysis. It further shows completion and non-completion of screening tasks, identification of individuals classified as ‘at risk’ by the CheckPD screening algorithm, and the number of users who subsequently underwent neurological assessment with confirmed diagnostic outcomes.\u003c/p\u003e","description":"","filename":"Fig5CheckPDImplementationrbh08Jan2026.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/2c8d0a24484bd21bca541af7.jpg"},{"id":102425254,"identity":"07298901-352a-4c69-8565-1566514b5851","added_by":"auto","created_at":"2026-02-11 14:30:53","extension":"jpg","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":1162722,"visible":true,"origin":"","legend":"\u003cp\u003eTemporal trends in daily CheckPD screening activity in relation to implementation strategies. This figure displays daily numbers of completed CheckPD screenings over time, overlaid with the timing of key implementation activities across provinces. Coloured markers indicate the initiation of different implementation strategies, including online training sessions (red), field screening events (blue), and Village Health Volunteer (VHV) led screening activities (grey), while the black line represents total daily screening volume. Distinct peaks in screening activity correspond closely with organised implementation events, particularly during periods of\u003c/p\u003e\n\u003cp\u003eintensive outreach between May and September 2025, demonstrating the direct impact of facilitated implementation strategies on user uptake and screening participation.\u003c/p\u003e","description":"","filename":"Fig6CheckPDImplementationrbh08Jan2026.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/c0a6fff3ca3a7e6b41b55654.jpg"},{"id":102425260,"identity":"f96300e7-7a33-4650-bffb-a172803a2be6","added_by":"auto","created_at":"2026-02-11 14:30:53","extension":"jpg","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":1076745,"visible":true,"origin":"","legend":"\u003cp\u003eAge-stratified completion rates of the CheckPD app screening tasks.\u003cbr\u003e\nThis figure illustrates screening task completion rates across predefined age groups among users from the first 10 provinces included in the analysis. Completion rates declined progressively with increasing age, indicating age-related differences in engagement and ability to complete all components of the digital screening workflow.\u003c/p\u003e","description":"","filename":"Fig7CheckPDImplementationrbh08Jan2026.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/4742093736ae0ef202771f35.jpg"},{"id":102425257,"identity":"3e99afff-620a-4e0f-b10c-1fc6cb2cb659","added_by":"auto","created_at":"2026-02-11 14:30:53","extension":"jpg","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":1723372,"visible":true,"origin":"","legend":"\u003cp\u003eTask-specific completion rates in the CheckPD screening workflow.\u003cbr\u003e\nThis funnel plot shows the proportion of participants completing each screening task, with higher completion for questionnaire and voice-based assessments and lower completion for more complex motor tasks, reflecting increasing task burden in real-world, unsupervised use.\u003c/p\u003e","description":"","filename":"Fig8CheckPDImplementationrbh08Jan2026.jpg","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/610738448b4bb38f6bfb1a71.jpg"},{"id":102425255,"identity":"d34dfdfb-66b1-4d84-b355-8cfa86b693fc","added_by":"auto","created_at":"2026-02-11 14:30:53","extension":"jpeg","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":1010977,"visible":true,"origin":"","legend":"\u003cp\u003ePragmatic and hedonic qualities of the CheckPD app compared to existing values from a benchmark dataset.\u003c/p\u003e","description":"","filename":"Fig9CheckPDImplementationrbh08Jan2026.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/57078c045fab87305c600c80.jpeg"},{"id":102745562,"identity":"12ae8e1d-444e-44b9-baf6-d04c0a106632","added_by":"auto","created_at":"2026-02-16 08:51:47","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":41844753,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/ce54fa94-f408-42bb-8a0c-5151c062db02.pdf"},{"id":102425259,"identity":"26ae6630-0df6-4297-b822-546f7238b495","added_by":"auto","created_at":"2026-02-11 14:30:53","extension":"mp4","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":19879012,"visible":true,"origin":"","legend":"","description":"","filename":"Suppl1CheckPDImplementationrbh08Jan2026.mp4","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/fde59e5ff93f3931273771af.mp4"},{"id":102425261,"identity":"5944f441-e213-4b16-8605-3accff09b5a0","added_by":"auto","created_at":"2026-02-11 14:30:53","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":24100,"visible":true,"origin":"","legend":"","description":"","filename":"Suppl2CheckPDImplementationrbh08Jan2026.docx","url":"https://assets-eu.researchsquare.com/files/rs-8565015/v1/b43543da9a5d790f361be8fe.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"National implementation of a digital Parkinson’s disease screening programme in Thailand: reach, usability, and real-world performance of the CheckPD app","fulltext":[{"header":"Background","content":"\u003cp\u003e \u003cb\u003eParkinson\u0026rsquo;s disease is a significant public health issue.\u003c/b\u003e \u003c/p\u003e \u003cp\u003eParkinson\u0026rsquo;s disease (PD) is one of the fastest-growing neurological disorders worldwide and represents an increasing public health challenge in ageing societies [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Its global prevalence has increased markedly over the past three decades, driven largely by population ageing and longer disease duration, with additional contributions from environmental risk factors such as exposure to pesticides and other pollutants [\u003cspan additionalcitationids=\"CR3\" citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Projection studies have estimated that by 2050, globally 25.2\u0026nbsp;million people will be living with PD, representing a 112% increase from 2021, and this rise is expected to be more pronounced among low-to-middle-income countries (LMICs) [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. In Thailand, epidemiological studies using data from the national Parkinson's Disease Registry have established that PD is generally under-reported but have estimated an age-adjusted prevalence of 424.57 PD cases/100,000 of the population, with a significantly higher prevalence in rural versus urban areas [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e].\u003c/p\u003e \u003cp\u003ePD is associated with progressive motor and non-motor disability, reduced quality of life, and substantial long-term healthcare and societal costs [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Despite the availability of effective symptomatic treatments, delays in receiving a definitive diagnosis of PD are common, limiting opportunities for early intervention, risk modification, and timely access to specialist care [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. These challenges are particularly pronounced in LMICs where healthcare resources and specialist capacity may be lacking, and where disparities in access to these services exist between urban and rural areas [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. In Thailand, for example, definitive diagnosis of PD is often delayed by 2\u0026ndash;3 years, partly due to limited availability of movement disorders specialists [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. Currently, Thailand has 926 neurologists, however most are located in larger provinces, such as Bangkok, Chiang Mai, and Chonburi, with far fewer in rural areas, resulting in inequitable access to specialist care [\u003cspan additionalcitationids=\"CR13\" citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. Prompt diagnosis of PD and referral for specialist care at its early stages is essential to avoid people living with the consequences of debilitating motor and non-motor PD symptoms, to maximise their long-term outcomes, and to minimise the impact on the healthcare system.\u003c/p\u003e\n\u003ch3\u003eGaps in current PD detection and prevention strategies\u003c/h3\u003e\n\u003cp\u003eWhen PD remains undiagnosed and untreated, progression to advanced stages is associated with profound deterioration in quality of life for patients and caregivers, alongside escalating requirements for long-term supportive and social care. Correspondingly, the economic burden on healthcare systems and society increases substantially, with costs of care for advanced PD far exceeding those associated with early detection and management [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan additionalcitationids=\"CR16\" citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe rising demand for timely PD diagnosis and effective treatment poses growing challenges to national health systems, economic sustainability, and workforce capacity. These pressures underscore the urgent need to shift from predominantly reactive care models towards preventive, population-based strategies that facilitate earlier risk identification and intervention at scale [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. In line with recommendations from the Global Burden of Disease Study and related initiatives, prioritising prevention of non-communicable diseases (NCDs), including PD, alongside the development of clear treatment pathways and the strengthening of health system infrastructure, is essential to mitigate long-term neurological disease burden [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWhile the timely identification of PD across populations seems like a logical approach to the problem, there are often significant barriers to its practical implementation at a primary and secondary care level within national healthcare systems and infrastructures [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. In Thailand, the majority of the population lives in remote or rural areas so traditional face-to-face assessment in a clinic is not always feasible and can be resource intensive, plus specialist PD expertise may not be easily available [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. It is clear that in order to address these challenges, there is a need for simple, accessible, and preventive approaches that can be deployed nationally and equitably across both urban and rural populations. Population-level digital health interventions provide a scalable mechanism to address these implementation barriers by enabling systematic early risk detection while supporting more efficient allocation of specialist and healthcare resources [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e].\u003c/p\u003e \u003cp\u003e.\u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eDigital screening as a public health strategy\u003c/h2\u003e \u003cp\u003eDigital tools and innovative technologies powered by artificial intelligence (AI) and machine learning are increasingly being adopted across multiple areas of medicine, including PD, to support clinicians in diagnosis, monitoring, and treatment decision-making [\u003cspan additionalcitationids=\"CR25 CR26\" citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. The use of AI-supported digital tools for population health screening offers substantial advantages over traditional methods in terms of speed, scalability, remote accessibility, and systematic data collection to better quantify disease burden. As a result, these approaches have particular value for LMICs, especially in remote or underserved areas where healthcare resources are constrained [\u003cspan additionalcitationids=\"CR29\" citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eGlobally, a wide range of digital health screening tools has been evaluated across diverse disease contexts [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. Examples include the UK\u0026rsquo;s National Health Service digital portal, which enables citizens to access health services, including screening, and self-management resources [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e] and India\u0026rsquo;s MadhuNETrAI, an AI-driven mobile application developed for national diabetic retinopathy screening [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. The benefits of digital health tools have also been demonstrated in mental health and cognitive or neurocognitive population screening [\u003cspan additionalcitationids=\"CR35\" citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e], with the World Health Organization (WHO)\u0026rsquo;s Mental Health Gap Action Programme (e-mhGAP) aiming to leverage such tools to scale services for mental, neurological, and substance use disorders globally. Within Southeast Asia, initiatives in Indonesia, Vietnam, Malaysia, and Thailand illustrate how mobile- and tablet-based platforms are being adopted for screening of chronic diseases and geriatric health conditions, helping to overcome longstanding barriers related to access, workforce limitations, and geographic inequities [\u003cspan additionalcitationids=\"CR38 CR39\" citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThailand already has a well-established example of large-scale, AI-enabled population screening through its national diabetic retinopathy programme. In this programme, a deep-learning system has been prospectively deployed across multiple primary care sites to deliver real-time diabetic retinopathy detection with specialist-level accuracy, demonstrating both feasibility and effectiveness within a middle-income country health system [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]. This initiative highlights how AI-supported digital screening can be successfully integrated into routine workflows, particularly in settings with limited specialist availability.\u003c/p\u003e \u003cp\u003eAgainst this backdrop, the implementation of digital PD risk screening platforms, such as CheckPD, represents a logical extension of established national digital screening strategies, applying similar principles of early identification, task-shifting, and scalability to the growing neurological disease burden.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eThailand’s digital readiness and constraints\u003c/h3\u003e\n\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e shows an overview of internet use, devices, and access locations in Thailand. Most people use the internet, and mobile phone subscriptions are higher than the total population, showing that mobile connectivity is very common. On average, people spend more than seven hours per day online, with much of this time spent using mobile phones. This shows that mobile internet use is dominant in Thailand [\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. Smartphones are the main device used to access the internet, while desktops, laptops, and tablets are used by far fewer people. This indicates a strong reliance on smartphones and limited use of advanced computing devices. Most users access the internet at home, followed by workplaces and private service centres. Public access locations are used less often. Overall, internet access in Thailand is widespread but mainly mobile-based and home-centred [\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e].\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eStatistics on internet use, device access and device use in Thailand.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIndicator\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003eValue\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003eInternet access\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInternet users (% of population)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003e91.2% (65.4\u0026nbsp;million people)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMobile phone subscriptions (% of population)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003e139% (99.5\u0026nbsp;million numbers)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAverage daily internet use\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003e7 hours 54 minutes\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInternet use via mobile phones\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e \u003cp\u003e5 hours per day (63.3%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMain devices for internet access\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eSmartphones\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99.6%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eDesktops\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16.7%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eLaptops\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10.6%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eTablets\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.8%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eCommon internet access locations\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eHome\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95.9%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eWork\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e38.3%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003ePrivate centers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e27.5%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003ePublic centers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14.2%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"3\"\u003eNote: Totals exceed 100% as users can use more than one device and more than one access location.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eHowever, as some older Thai adults may face challenges when using digital tools due to low levels of digital literacy, lack of confidence, or limited internet accessibility [\u003cspan additionalcitationids=\"CR45\" citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e] it is important that health care apps are designed to be inclusive to all potential users as well as having support to facilitate engagement. Within this context, community health volunteers (also known as Village Health Volunteers, VHV) represent a critical enabling resource for bridging digital gaps between citizens and healthcare systems. VHVs have an established role in Thailand\u0026rsquo;s primary healthcare infrastructure and are well positioned to support the adoption of digital health tools at the community level [\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e, \u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e]. Through targeted training, volunteers can assist individuals in navigating mobile and online health applications, provide hands-on support for initial use, and reinforce confidence in digital health participation. This community-embedded support model offers a practical strategy to enhance equitable uptake of digital health interventions, particularly among older adults and populations with limited digital literacy.\u003c/p\u003e\n\u003ch3\u003eThe CheckPD platform and its benefits as a national screening tool\u003c/h3\u003e\n\u003cp\u003eThe digital screening platform evaluated in this study, hereafter referred to as CheckPD, is a multimodal, AI-assisted mobile application that has been specifically developed for population-level PD screening in Thailand (ClinicalTrials.gov registration number: NCT06609681). The protocol for national digital screening using CheckPD has been described previously and established the suitability of CheckPD for national rollout under the Royal Patronage of Her Royal Highness the Princess, in collaboration with the Thai Red Cross Society (TRCS) and the National Health Security Office (NHSO) [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e]. CheckPD employs AI-driven multimodal assessment methods that integrate a structured questionnaire on PD symptoms and risk factors with digital analyses of tapping, tremor, gait, and voice parameters, and is implemented within a governance framework aligned with Thailand\u0026rsquo;s Personal Data Protection Act (PDPA). Preliminary analyses focusing on participants reporting hyposmia and probable REM sleep behaviour disorder (RBD) have been presented as posters at the International Congress of Parkinson\u0026rsquo;s Disease and Movement Disorders Annual Meeting in October 2025 [\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e, \u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eRecent studies have highlighted usability and human-centred design (HCD) as essential criteria for effective digital health screening platforms, particularly for older adults [\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e, \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e]. Successful designs prioritise accessibility, comfort, and user trust by focusing on user needs rather than technological complexity alone [\u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e]. Evidence indicates that inclusive interfaces, clear instructions, and adaptable features enable older users and individuals with motor or cognitive challenges to engage confidently with digital tools, while design elements such as clear typography, strong colour contrast, and uncluttered layouts further enhance readability and usability in ageing populations [\u003cspan additionalcitationids=\"CR56\" citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eDespite the rapid growth of digital tools developed for PD, most existing platforms have been conceived primarily as research instruments or as disease assessment and symptom-monitoring tools for individuals with established diagnoses (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). The majority were developed within controlled research settings, often to validate specific digital biomarkers, such as gait variability, tremor amplitude, voice features, or freezing of gait, rather than to function as end-to-end screening solutions deployable at scale. Consequently, these platforms tend to be purpose-specific, targeting narrowly defined clinical or research questions, and are rarely designed for population-level implementation, integration into routine healthcare systems, or linkage to formal referral pathways. In addition, the level of evidence supporting their utility varies considerably, ranging from small proof-of-concept studies and short-term validation cohorts to larger longitudinal research datasets, with few demonstrating real-world effectiveness or sustainability beyond research contexts. As a result, their clinical and public health applicability remains limited when considered in the context of large-scale, population-based screening programmes [\u003cspan additionalcitationids=\"CR59\" citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eIn contrast, CheckPD was purposefully designed from inception as an accessible, HCD-driven, informed digital screening platform capable of operating at a national scale in real-world settings. Rather than focusing on a single symptom domain, the application integrates multimodal assessments and is embedded within Thailand\u0026rsquo;s healthcare infrastructure through a formal memorandum of understanding with the NHSO. This enables clearly defined referral pathways following risk identification. When screening results indicate an elevated risk of PD, the app automatically directs users to registered hospitals within the national health system for further clinical evaluation. A comparative overview of CheckPD and selected global PD digital platforms, highlighting differences in purpose, evidence base, scalability, and system integration, is presented in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eComparison of the features of CheckPD with those of other selected global PD digital platforms.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePlatform\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCountry\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSetting\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePrimary purpose\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eKey features\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eStrengths\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eLimitations\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e \u003cp\u003eScreening or diagnosis\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCheckPD [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eThailand\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReal world\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNational PD screening and risk stratification\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eMultimodal AI (tapping, tremor, balance, voice), questionnaire, offline-first, VHV integration, cloud dashboards\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eOnly national-scale PD screening system; strong usability; policy integration; PDPA compliance; real-world deployment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRequires device capability; follow-up clinical pathways still developing\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003emPower [\u003cspan citationid=\"CR95\" class=\"CitationRef\"\u003e95\u003c/span\u003e, \u003cspan citationid=\"CR96\" class=\"CitationRef\"\u003e96\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eResearch data collection and digital biomarker discovery\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTapping, gait, voice tasks; ResearchKit; large open dataset\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eMassive user base; open science; high-frequency longitudinal data\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNot designed for clinical screening; variable data quality; no health-system integration\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePREDICT-PD [\u003cspan citationid=\"CR97\" class=\"CitationRef\"\u003e97\u003c/span\u003e, \u003cspan citationid=\"CR98\" class=\"CitationRef\"\u003e98\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUK\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eEarly detection research in high-risk PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eOnline questionnaires, smell tests, risk modeling\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eStrong epidemiological base; long-term longitudinal follow-up\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNo motor-sensor tasks; not mobile-first; limited scalability\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKeySense [\u003cspan citationid=\"CR99\" class=\"CitationRef\"\u003e99\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReal world\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eEarly detection and self-screening for Parkinson\u0026rsquo;s disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTyping-based motor assessment (KeySense\u0026reg;), AI analysis of keystroke dynamics, web-based access, no wearable devices required\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSimple and non-invasive screening; accessible via standard computer keyboard; free public access; focuses on early detection\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNot a clinical diagnostic tool; limited multimodal assessment (no voice, gait, or tremor sensors); requires desktop or laptop keyboard; limited integration with healthcare systems\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmartphone motor testing app [\u003cspan citationid=\"CR100\" class=\"CitationRef\"\u003e100\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUK\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDifferentiate PD, iRBD, and controls using smartphone motor tasks\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eVoice, gait, balance, tapping, tremor tasks; smartphone sensors; ML classification\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eHigh accuracy; low-cost; captures real-world motor data\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eResearch-only; data quality depends on user compliance; not a deployed screening system\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRoche PD Mobile Application v2 [\u003cspan citationid=\"CR101\" class=\"CitationRef\"\u003e101\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eClick or tap here to enter text.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSwitzerland\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRemote monitoring of motor symptoms in early PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone \u0026amp; smartwatch tests (tapping, tremor, gait, balance, speech); passive monitoring\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eHigh reliability and validity; frequent at-home assessment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eResearch-only; focused on early-stage PD; not deployed for population screening\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAPDM Mobility Lab [\u003cspan citationid=\"CR102\" class=\"CitationRef\"\u003e102\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eClick or tap here to enter text.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eObjective gait and balance assessment in PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eWearable IMU sensors; gait, balance, turning measures\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eValidated, reliable; sensitive to PD severity and progression\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eResearch-focused; requires sensors; not population screening\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e \u003cp\u003eMotor symptom monitoring\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHopkins PDKit [\u003cspan citationid=\"CR103\" class=\"CitationRef\"\u003e103\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eClick or tap here to enter text.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eOpen-source digital biomarker toolkit\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003ePython-based pipeline for gait, tapping, voice; harmonization of mobile sensor data\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eEnables reproducible analysis; strongly used in academic research\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eNot a patient-facing screening app; requires programming expertise\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmartMOVE [\u003cspan citationid=\"CR104\" class=\"CitationRef\"\u003e104\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSingapore\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eObjective gait assessment and gait variability analysis in PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone accelerometer and gyroscope; step time and step length variability; validation against footswitches and the gait mat system\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eClinically validated accuracy; low-cost and portable; suitable for clinic and home use\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eSmall sample size; focused on gait only; not designed for large-scale screening or health-system integration\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSTOP App \u0026ndash; Smartphone-based tremor monitoring [\u003cspan citationid=\"CR105\" class=\"CitationRef\"\u003e105\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eClick or tap here to enter text.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFinland / UK\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRemote monitoring of hand tremor severity and medication effects in PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone accelerometer; gamified ball-balancing task; tremor intensity parameter (TIP); before/after medication analysis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eObjective tremor quantification; correlates with UPDRS; feasible real-world monitoring\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eSmall sample size; focuses mainly on hand tremor; device variability; not designed for population screening\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmartphone-based FOG Monitoring System [\u003cspan citationid=\"CR106\" class=\"CitationRef\"\u003e106\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eItaly\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eHome assessment and real-time detection of freezing of gait (FOG) in Parkinson\u0026rsquo;s disease\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone inertial sensors; fuzzy logic algorithm; spatio-temporal gait parameters (step cadence, step length); frequency-domain features; real-time FoG detection; home and laboratory validation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eHigh detection accuracy (AUC up to 0.94); interpretable knowledge-based model; real-time processing; strong agreement with clinician assessment; high usability for home monitoring\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eFocused on FOG only (not full PD screening); requires calibration by clinicians; limited sample size; not designed as population-scale screening or integrated health system platform\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmartphone-based Turning Assessment [\u003cspan citationid=\"CR107\" class=\"CitationRef\"\u003e107\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eItaly\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRemote assessment of motor impairment in PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone inertial sensors; turning task analysis; QoM index; ML classification\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eObjective digital biomarker; correlates with clinical scales; low-cost home monitoring\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eLimited to turning tasks; small sample size; not suitable for population-scale screening\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmartphone-based Gait Assessment App [\u003cspan citationid=\"CR108\" class=\"CitationRef\"\u003e108\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eChina / USA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eObjective assessment of gait impairment and disease severity in PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone IMU (accelerometer, gyroscope); single- and dual-task walking; stride time and variability; cloud data upload\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eHigh validity vs. gold-standard sensors; correlates with UPDRS, cognition, and mood; low-cost and portable\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eClinic-based validation only; small sample size; focuses on gait only; not designed for large-scale screening\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmartphone-based FOG Detection System [\u003cspan citationid=\"CR109\" class=\"CitationRef\"\u003e109\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSouth Korea\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eObjective detection of freezing of gait (FOG) in PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone accelerometer \u0026amp; gyroscope; unconstrained body placement (waist, pocket, ankle); machine learning (AdaBoost); real-world gait data\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eHigh sensitivity (up to 86%); no external sensors required; practical daily-life deployment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eFocused only on FOG; small sample size; requires labeled data; not a comprehensive PD screening system\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSmartphone-based RPM [\u003cspan citationid=\"CR110\" class=\"CitationRef\"\u003e110\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eItaly\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRemote monitoring of PD patients during lockdown\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone app for gait, tapping, tremor, balance, cognition; questionnaires; telemonitoring\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eFeasible home monitoring; good patient compliance; correlates with clinical scales (UPDRS, H\u0026amp;Y)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eSmall sample size; short study duration; no control group; requires digital literacy\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"7\" nameend=\"c7\" namest=\"c1\"\u003e \u003cp\u003eSymptom fluctuation, behavior, and intervention support\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEMA eDiary for PD [\u003cspan citationid=\"CR111\" class=\"CitationRef\"\u003e111\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNetherlands\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDaily-life monitoring of motor and non-motor symptom fluctuations in PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone-based ecological momentary assessment (EMA); repeated questionnaires on affect, motor function, context; free-living monitoring\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eCaptures intraday symptom fluctuations; good internal validity; patient-centered monitoring\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eSmall sample size; subjective self-report; not designed for screening or population-scale deployment\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e9zest Exercise App [\u003cspan citationid=\"CR112\" class=\"CitationRef\"\u003e112\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eClick or tap here to enter text.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eHome-based exercise support for people with PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSmartphone app; personalized video-guided exercise; in-app assessments (STS, TUG, PDQ-8); adaptive algorithm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSafe and feasible; improves mobility, strength, and quality of life; accessible home use\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eSmall sample size; high dropout; not designed for screening or diagnosis\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003emHealth-supported exercise program [\u003cspan citationid=\"CR113\" class=\"CitationRef\"\u003e113\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eResearch\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePromote physical activity in people with PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eMobile app\u0026ndash;supported home exercise, step tracking, remote monitoring, behavioral feedback\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eImproves physical activity and mobility, especially in less active patients; safe and acceptable\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eSmall sample size; not a screening or diagnostic tool; limited generalizability\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImageVis3D Mobile for DBS [\u003cspan citationid=\"CR114\" class=\"CitationRef\"\u003e114\u003c/span\u003e]\u003c/p\u003e \u003cp\u003eClick or tap here to enter text.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUSA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eReal world\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eClinical decision support for DBS parameter selection in PD\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eMobile interactive visualization; patient-specific DBS models; visualization of electrode location and volume of tissue activated (VTA)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eFaster DBS parameter selection; comparable to standard care; intuitive mobile interface\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eRequires precomputed models; limited patient sample; focused on DBS programming, not PD screening\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eAI, artificial intelligence; ML, machine learning PD, Parkinson\u0026rsquo;s disease; PDPA, Personal Data Protection Act; VHV, Village Health Volunteers; STOP, Sentient Tracking of Parkinson\u0026rsquo;s; FOG, freezing of gait; EMA, ecological momentary assessment; QoM, Quality of Motion; STS, Sit-to-stand test; TUG, Timed Up and Go; PDQ-8, Parkinson's Disease Questionnaire-8; DBS, Deep Brain Stimulation; iRBD, Idiopathic Rapid Eye Movement Sleep Behavior Disorder; IMU, Inertial measurement unit; AUC, Area Under the Curve; UPDRS, Unified Parkinson's Disease Rating Scale; H\u0026amp;Y, Hoehn \u0026amp; Yahr Scale.\u003c/p\u003e\n\u003ch3\u003eObjectives of this study\u003c/h3\u003e\n\u003cp\u003eThis study aimed to evaluate the early implementation of a phased national roll-out the CheckPD digital screening programme across 10 provinces in Thailand, focusing on reach, usability, real-world predictive performance, and implementation factors relevant to scale-up in a LMIC.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eStudy design and implementation framework\u003c/h2\u003e \u003cp\u003eThis mixed-methods implementation study evaluated the early phase of national deployment of a digital PD screening programme in Thailand between January 2024 and October 2025. The study was designed as a pragmatic, real-world evaluation, embedded within routine public health activities, rather than in a controlled experimental setting, in order to reflect actual conditions of use at scale. Evaluation was guided by the RE-AIM framework (Reach, Effectiveness, Adoption, Implementation, and Maintenance), which is widely used to assess the public health impact, usability, and scalability of complex interventions [\u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe RE-AIM framework enabled systematic assessment of population reach, predictive performance under real-world conditions, adoption across provinces and delivery pathways, fidelity of implementation, and early indicators of sustainability. National rollout and programme governance were coordinated by the TRCS in collaboration with the NHSO. The NHSO is Thailand\u0026rsquo;s public agency responsible for ensuring equitable access to essential health services across the continuum of care, including health promotion, disease prevention, treatment, and rehabilitation, primarily through strategic financing and reimbursement of healthcare providers. Early risk identification through population-based screening initiatives such as CheckPD aligns with NHSO\u0026rsquo;s mandate by enabling more timely and effective treatment, optimising resource allocation, and improving long-term health outcomes. The programme was aligned with Thailand\u0026rsquo;s preventive health agenda and NCD strategies, facilitating integration with existing community health infrastructure and referral pathways.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eStudy setting\u003c/h3\u003e\n\u003cp\u003eImplementation was conducted across selected to represent Thailand\u0026rsquo;s geographic, demographic, and socioeconomic diversity, including urban, peri-urban, and rural contexts (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Participating provinces included Bangkok, Nonthaburi, Pathum Thani, Samut Prakan, Chonburi, Nakhon Pathom, Phetchaburi, Nakhon Sawan, Chiang Rai, and Si Sa Ket. These provinces span central, northern, and northeastern regions and vary in population density, healthcare access, and digital connectivity. Screening activities were delivered through multiple community-based and institutional settings, including community centres, temples, district hospitals, public health outreach campaigns, and personal mobile devices. This multi-setting approach was intended to maximise inclusion of both digitally experienced users and individuals with limited digital literacy or constrained internet access, particularly older adults and residents of rural communities.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e\u003c/p\u003e \u003cp\u003eThis figure illustrates the spatial distribution of CheckPD screening participants across Thailand among the first 10 provinces included in the analysis. Provinces are shaded according to the number of screened participants, with darker shading indicating higher participation levels. The accompanying table summarises the absolute number and proportion of participants by province, while a second table indicates the number of neurologists available within each province. The number of neurologists per province was low across all included settings, highlighting a genuine limitation in local specialist availability.\u003c/p\u003e\n\u003ch3\u003eParticipants and eligibility\u003c/h3\u003e\n\u003cp\u003eAdults aged 40 years or older residing in Thailand were eligible to participate in the screening programme, reflecting epidemiological evidence that the incidence of PD, while relatively low in early adulthood, begins to rise from the fourth decade of life and increases progressively with age. In addition, longitudinal studies indicate that prodromal features of PD, including non-motor symptoms such as hyposmia, RBD, and subtle motor changes, can emerge years to decades before clinical diagnosis, often during midlife [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e, \u003cspan citationid=\"CR64\" class=\"CitationRef\"\u003e64\u003c/span\u003e, \u003cspan citationid=\"CR65\" class=\"CitationRef\"\u003e65\u003c/span\u003e]. Participation was voluntary and required provision of digital informed consent within the mobile application prior to initiation of screening. There were no exclusion criteria based on gender, educational attainment, occupation, or underlying health status, consistent with the population-level screening intent of the programme. Individuals who did not complete the consent process, who withdrew prior to submission of screening data, or who experienced technical failure that prevented capture of evaluable data were excluded from analytic datasets. No financial or material incentives were provided.\u003c/p\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003eImplementation and recruitment strategies\u003c/h2\u003e \u003cp\u003eThe CheckPD screening programme was delivered using four coordinated implementation pathways designed to maximise reach while accommodating varying levels of digital literacy and access: (1) Field screening campaigns organised by provincial public health offices and conducted as one-day or multi-day outreach events; (2) Online training\u0026ndash;activated screening sessions, in which trained community leaders or health workers facilitated local screening following remote instruction; (3) Community screening led by VHVs, with a focus on older adults and rural communities; and (4) Self-screening via app download, available nationwide throughout the study period (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003e). Volunteers and public health officers involved in field and community screening received standardised training from the TRCS, delivered through online modules and written manuals. Training covered consent procedures, step-by-step screening workflows, device setup, and basic troubleshooting to ensure consistency, data quality, and participant safety across provinces and implementation settings.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003eThe CheckPD platform and screening workflow\u003c/h2\u003e \u003cp\u003eThe CheckPD screening workflow comprises four sequential components designed for rapid, scalable population screening (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e3\u003c/span\u003e). (1) User registration and digital informed consent, where participants securely register on the CheckPD mobile application and provide electronic consent prior to screening. (2) Structured symptom and risk factor assessment, consisting of a questionnaire capturing motor symptoms, non-motor symptoms, and established risk factors for PD. (3) Guided performance of digital motor and voice tasks, including finger tapping for bradykinesia, tremor assessment, gait and balance evaluation, and structured speech recording, with in-app instructions to ensure standardised task execution. (4) Automated data processing and risk classification, in which collected data are analysed using predefined algorithms to generate an individualised PD risk profile. The entire screening process is designed to be completed within approximately 8\u0026ndash;10 minutes, supporting feasibility for large-scale, population-level deployment.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e(10) Completion of a 20-item Parkinson\u0026rsquo;s disease risk assessment questionnaire capturing motor symptoms, non-motor symptoms, and established risk factors. Component 4. Automated analysis and feedback: (11) Automated risk evaluation and classification;\u003c/p\u003e \u003cp\u003e(12) Personalised health guidance and recommendations based on screening results.\u003c/p\u003e \u003cp\u003eTo enhance usability and accessibility, the application incorporates Thai-language localisation, audio-visual guidance, enlarged interface elements, and a linear, stepwise workflow. These design features were intentionally implemented to reduce cognitive load, support users with varying levels of digital literacy, and minimise task-related errors, particularly among older adults and individuals with motor or cognitive challenges. In addition, a step-by-step video tutorial demonstrating how to use the application and complete each screening task is provided to further support user onboarding and correct task execution (Supplementary data 1).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003eOutcomes and evaluation measures\u003c/h2\u003e \u003cp\u003ePrimary implementation outcomes were defined in accordance with the RE-AIM framework and included reach (number of app downloads, initiated screenings, and completed screenings), adoption (participation by province and by implementation pathway), implementation fidelity (task completion and dropout rates), and usability. Usability was assessed using the System Usability Scale (SUS) and the short User Experience Questionnaire (UEQ-S), capturing both pragmatic and hedonic dimensions of user experience [\u003cspan citationid=\"CR66\" class=\"CitationRef\"\u003e66\u003c/span\u003e, \u003cspan citationid=\"CR67\" class=\"CitationRef\"\u003e67\u003c/span\u003e]. Secondary outcomes included AI-based PD risk classification, system performance indicators (including application crash rate and offline success rate), and qualitative feedback from volunteers and public health officers regarding usability, user trust, and integration into existing workflows.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis and data visualisation\u003c/h2\u003e \u003cp\u003eQuantitative analyses were conducted to characterise programme reach, user engagement, and task completion patterns during real-world implementation of the CheckPD platform. All analyses were performed using Python version 3.12.10, with the pandas library used for data handling and descriptive analyses and matplotlib for data visualisation\u003c/p\u003e \u003cp\u003eDescriptive statistics were used throughout, consistent with the pragmatic and implementation-focused aims of the study. Continuous variables are reported as means with standard deviations, and categorical variables as counts and percentages.\u003c/p\u003e \u003cp\u003eTo examine age-related patterns of engagement, participants were stratified into five predefined age groups: \u0026lt;40, 40\u0026ndash;49, 50\u0026ndash;59, 60\u0026ndash;69, and \u0026ge;\u0026thinsp;70 years. For each age group, task outcomes were categorised as complete, incomplete, or unattempted. The number and proportion of participants in each category were calculated such that percentages within each age group totalled 100%. These analyses were used to assess age-related differences in task adherence and dropout across the screening workflow.\u003c/p\u003e \u003cp\u003eTask-level engagement was further analysed by calculating completion rates for each individual screening task within the CheckPD application. Each task was coded as a binary outcome, with completion coded as \u0026lsquo;1\u0026rsquo; and non-completion coded as \u0026lsquo;0\u0026rsquo;. For bilateral tasks (e.g. dual finger tapping and pinch-to-size), a task was considered complete only if both left- and right-sided components were successfully completed. Task completion rates were expressed as the percentage of participants who completed each task. Tasks were ranked from highest to lowest completion rate and visualised using funnel plots to illustrate cumulative attrition and identify stages of the screening workflow associated with the greatest participant dropout. These analyses were intended to highlight usability- and implementation-related barriers, particularly for tasks requiring greater sensor precision, balance stability, or environmental setup.\u003c/p\u003e \u003cp\u003eIn addition, multivariable logistic regression analysis was performed to explore factors associated with completion of the full screening protocol. The dependent variable was task completion status (completed versus not completed). Independent variables included selected sociodemographic and contextual factors, including educational attainment and province of residence. Results are presented as odds ratios with 95% confidence intervals. Model fit was assessed using the Omnibus test of model coefficients, Nagelkerke pseudo R\u0026sup2;, and the Hosmer\u0026ndash;Lemeshow goodness-of-fit test.\u003c/p\u003e \u003cp\u003eNo hypothesis-driven inferential statistical testing beyond this exploratory regression analysis was undertaken, as the primary objective of the study was to evaluate real-world feasibility, engagement, and implementation performance, rather than to establish causal relationships. Analyses of AI predictive performance, including calculation of positive predictive value (PPV) based on neurologist verification, were conducted separately and are described in the following section.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003eAI evaluation and clinical verification\u003c/h2\u003e \u003cp\u003eCheckPD classifies users as \u0026lsquo;normal\u0026rsquo; or \u0026lsquo;at risk\u0026rsquo; using an ensemble machine-learning model trained on multimodal input data derived from questionnaire responses and sensor-based motor and voice tasks, with the method described previously [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e]. Participants classified as at risk were advised to seek further clinical evaluation through standard healthcare pathways. AI performance metrics were calculated only amongst participants who were flagged as at risk and subsequently underwent neurological assessment, considered as the gold standard for diagnosis of PD. Participants classified as screen-negative were not routinely clinically verified as part of this implementation programme; therefore, population-level diagnostic accuracy could not be estimated.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003eUsability and user experience assessment\u003c/h2\u003e \u003cp\u003eUsability and user experience were assessed in a representative sample of participants following completion of the screening process. Validated Thai versions of the System Usability Scale (SUS) and the short User Experience Questionnaire (UEQ-S) were administered. UEQ-S results were analysed using standardised benchmark comparisons to assess pragmatic quality (e.g., clarity, efficiency, ease of use) and hedonic quality (e.g., interest, stimulation, perceived innovation).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec17\" class=\"Section2\"\u003e \u003ch2\u003eData sources, management, and governance\u003c/h2\u003e \u003cp\u003eData for this implementation study were derived from the CheckPD digital screening platform and its associated clinical screening and analytics infrastructure, as illustrated in the system architecture and data flow diagram (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e4\u003c/span\u003e). The CheckPD ecosystem comprises three core components: (1) the CheckPD mobile application for population-level data capture, (2) a web-based screening module for clinical and questionnaire-based assessments, and (3) a Business Intelligence (BI) dashboard for monitoring programme performance and implementation outcomes.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe CheckPD mobile application serves as the primary source of multimodal screening data. During routine use, participants generate real-time data including demographic information, questionnaire responses, motor assessments (finger tapping, tremor, gait, and balance), and speech recordings. Structured application data are stored as JavaScript Object Notation (JSON) files, while speech recordings are stored as waveform audio (WAV) files. All raw application data are housed within a NoSQL database operated by the TRCS, which functions as the secure primary data repository. To ensure data integrity and continuity, daily backups are performed through a dedicated web application, with archived copies stored on encrypted cloud storage and local hard disk drives.\u003c/p\u003e \u003cp\u003eFor secondary use, analysis, and reporting, selected structured data, primarily demographic and screening-related variables, are transferred from the TRCS NoSQL database to a structured SQL Data Warehouse managed internally by a team at Chulalongkorn Centre of Excellence for Parkinson\u0026rsquo;s Disease and Related Disorders (ChulaPD; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e\u003ca href=\"http://www.chulapd.org\" target=\"_blank\"\u003ewww.chulapd.org\u003c/a\u003e\u003c/span\u003e\u003cspan address=\"http://www.chulapd.org\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). Data migration occurs on a daily and weekly schedule, depending on data type and operational requirements. An automated migration pipeline transfers JSON and WAV files using three unique identifiers: a general system identifier, the Thai national identification number, and a record-specific identifier. This automated process includes built-in error detection, with notifications issued to the ChulaPD data team in the event of transfer failures or inconsistencies. Only records with neurologist-confirmed diagnostic labels (PD or control) are included in the analytic migration workflow.\u003c/p\u003e \u003cp\u003eClinical diagnostic data are generated through a dedicated physician-facing web application. Authorised neurologists review participant-level screening outputs and assign diagnostic classifications, categorised as \u0026lsquo;PD\u0026rsquo; or \u0026lsquo;not PD\u0026rsquo;. Diagnostic access and labelling privileges are restricted to approved personnel, and all labelled records are stored exclusively within the SQL Data Warehouse. This separation of raw data storage and curated diagnostic datasets supports data minimisation, traceability, and role-based access control.\u003c/p\u003e \u003cp\u003eProgramme monitoring and implementation evaluation are supported by the BI dashboard, which integrates data from both the CheckPD and Screening components. Using visual analytics tools, including Looker Studio, the dashboard provides near real-time summaries of application downloads, screening completion rates, diagnostic distributions, task-level adherence, and system usage patterns. This infrastructure enables continuous monitoring of reach, adoption, implementation fidelity, and system performance throughout the national rollout.\u003c/p\u003e \u003cp\u003eData governance across the CheckPD platform is designed to comply with Thailand\u0026rsquo;s PDPA. Governance mechanisms include role-based access control, separation of identifiable and analytic datasets, controlled data migration, and secure storage managed by national and academic partners. Collectively, this architecture supports secure, scalable, and auditable use of digital health data for population-level PD screening and implementation research.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec18\" class=\"Section2\"\u003e \u003ch2\u003eEthical considerations and data protection\u003c/h2\u003e \u003cp\u003eThe TRCS acted as the designated data controller, with ChulaPD serving as the data processor. Prior to initiating any screening or assessment, all participants were required to provide explicit approval for data collection through a digital informed consent process embedded within the CheckPD platform, in accordance with approvals granted by the relevant ethics and regulatory bodies. All personal and health-related data were protected through end-to-end encryption, employing Advanced Encryption Standard 256-bit (AES-256) encryption for data at rest and Transport Layer Security (TLS) version 1.3 for data in transit. Data were stored on an ISO/IEC 27001-certified server infrastructure operated by the TCRS. Analytical activities were conducted exclusively on de-identified datasets under approval from the relevant ethics committees. Ethics approval was obtained from the Institutional Review Board of the Faculty of Medicine, Chulalongkorn University (IRB No. 0804/65), as well as from the Central Research Ethics Committee (CREC) under the approved protocol entitled \u0026lsquo;Flipping the Paradigm of Parkinson\u0026rsquo;s Disease: A Model of National \u0026lsquo;Eat, Move, Sleep\u0026rsquo; Digital Interventions to Prevent or Slow the Rise of Non-Communicable Diseases in Thailand\u0026rsquo; (CREC No. CREC023/68BR-MED06; Certificate Number COA-CREC105/2025). In accordance with Thailand\u0026rsquo;s PDPA (B.E. 2562, 2019), Data Protection Impact Assessments were performed on an annual basis to evaluate and mitigate potential risks related to data processing and security.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003eReporting standards and implementation framework alignment\u003c/h2\u003e \u003cp\u003eThis study was designed and reported in alignment with principles from the RE-AIM framework for implementation research, with explicit reporting of reach, adoption, implementation fidelity, and early indicators of maintenance. Elements of the STROBE guidelines for observational studies were followed where applicable, including transparent reporting of study setting, participant eligibility, data sources, and outcome measures [\u003cspan citationid=\"CR68\" class=\"CitationRef\"\u003e68\u003c/span\u003e]. Given the pragmatic, implementation-focused nature of the programme, no randomisation or hypothesis-driven comparisons were undertaken, and reporting emphasised real-world feasibility, usability, and scalability rather than causal inference.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec21\" class=\"Section2\"\u003e \u003ch2\u003eParticipant demographics and CheckPD app usage\u003c/h2\u003e \u003cp\u003eBetween January 2024 and October 2025, the CheckPD platform recorded 30,327 application downloads nationwide, reflecting broad uptake during the national rollout. The present analysis focuses on users from the first 10 provinces included in the rollout, selected based on completed implementation governance and stable data pipelines, resulting in 18,520 users who initiated screening and provided evaluable data (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e5\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eParticipants had a mean age of 56.91\u0026thinsp;\u0026plusmn;\u0026thinsp;11.89 years and spanned the predefined inclusion age range of 40 to \u0026ge;\u0026thinsp;70 years (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). The screened population was predominantly female, comprising 14,004 women (76.0%) and 4,460 men (24.0%). Amongst the analysed cohort, 13,381 participants (72%) completed all screening tasks, while 5,139 (28%) had incomplete assessments. Following screening, 730 individuals flagged as \u0026lsquo;at risk\u0026rsquo; subsequently sought further neurological evaluation (Supplementary Data 2).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDemographic characteristics of CheckPD users from the first 10 provinces included in the national screening rollout (n\u0026thinsp;=\u0026thinsp;18,520).\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eDemographic data\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003cp\u003e(n\u0026thinsp;=\u0026thinsp;18,520)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAge\u003c/b\u003e (Mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e56.91\u0026thinsp;\u0026plusmn;\u0026thinsp;11.89\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eGender\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMale (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4460/18,520 (24%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFemale (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e14,004/18,520\u003c/p\u003e \u003cp\u003e(76%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e56/18,520 (\u0026lt;\u0026thinsp;1%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eEducation\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBachelor's degree or higher (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2,681/18,520\u003c/p\u003e \u003cp\u003e(15%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBelow Bachelor's degree (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12,679/18,520\u003c/p\u003e \u003cp\u003e(68%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3,160/18,520\u003c/p\u003e \u003cp\u003e(17%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"11\" rowspan=\"12\"\u003e \u003cp\u003e\u003cb\u003eOccupation\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCivil servant (non-teaching) (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e481/18,520\u003c/p\u003e \u003cp\u003e(3%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFarmer (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5,502/18,520\u003c/p\u003e \u003cp\u003e(30%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMerchant / Trader (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2,795/18,520\u003c/p\u003e \u003cp\u003e(15%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePetroleum/ oil exposure occupation (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9/18,520\u003c/p\u003e \u003cp\u003e(\u0026lt;\u0026thinsp;1%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrivate sector employee (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e503/18,520\u003c/p\u003e \u003cp\u003e(3%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProfessional athlete (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1/18,520\u003c/p\u003e \u003cp\u003e(\u0026lt;\u0026thinsp;1%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRetired civil servant (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e291/18,520\u003c/p\u003e \u003cp\u003e(2%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eState enterprise employee (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e121/18,520\u003c/p\u003e \u003cp\u003e(1%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTeacher / Lecturer (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e56/18,520\u003c/p\u003e \u003cp\u003e(\u0026lt;\u0026thinsp;1%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot employed (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,912/18520\u003c/p\u003e \u003cp\u003e(10%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOther (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2,981/18,520\u003c/p\u003e \u003cp\u003e(16%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3,868/18,520\u003c/p\u003e \u003cp\u003e(21%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"4\" rowspan=\"5\"\u003e \u003cp\u003e\u003cb\u003eMarital status\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSingle (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3,081/18,520\u003c/p\u003e \u003cp\u003e(17%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMarried / Partnered (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9,687/18,520\u003c/p\u003e \u003cp\u003e(52%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDivorced (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e848/18,520\u003c/p\u003e \u003cp\u003e(5%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWidowed (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,720/18,520\u003c/p\u003e \u003cp\u003e(9%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3,184/18,520\u003c/p\u003e \u003cp\u003e(17%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"6\" rowspan=\"7\"\u003e \u003cp\u003e\u003cb\u003eIncome\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo income (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e759/18,520\u003c/p\u003e \u003cp\u003e(4%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLess than 5,000 THB (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3,999/18,520\u003c/p\u003e \u003cp\u003e(22%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5,000\u0026ndash;10,000 THB (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5,403/18,520\u003c/p\u003e \u003cp\u003e(29%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e10,001\u0026ndash;20,000 THB (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,820/18,520\u003c/p\u003e \u003cp\u003e(10%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e20,001\u0026ndash;30,000 THB (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e562/18,520\u003c/p\u003e \u003cp\u003e(3%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e30,001\u0026ndash;40,000 THB (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e300/18,520\u003c/p\u003e \u003cp\u003e(2%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMore than 40,000 THB (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e610/18,520\u003c/p\u003e \u003cp\u003e(3%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5,067/18,520\u003c/p\u003e \u003cp\u003e(27%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eHistory of Smoking\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e121/18,520\u003c/p\u003e \u003cp\u003e(1%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,853/18,520\u003c/p\u003e \u003cp\u003e(10%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16,546/18,520\u003c/p\u003e \u003cp\u003e(89%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eAlcohol drinking\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e428/18,520\u003c/p\u003e \u003cp\u003e(2%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,544/18,520\u003c/p\u003e \u003cp\u003e(8%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16,548/18,520\u003c/p\u003e \u003cp\u003e(89%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eCoffee drinking\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,215/18,520\u003c/p\u003e \u003cp\u003e(7%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e762/18,520\u003c/p\u003e \u003cp\u003e(4%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16,543/18,520\u003c/p\u003e \u003cp\u003e(89%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eMilk/dairy milk product consumption\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e747/18,520\u003c/p\u003e \u003cp\u003e(4%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,230/18,520\u003c/p\u003e \u003cp\u003e(7%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16,543/18,520\u003c/p\u003e \u003cp\u003e(89%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eRegular exercise (more than 150 minutes/ week)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,086/18,520\u003c/p\u003e \u003cp\u003e(6%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e891/18,520\u003c/p\u003e \u003cp\u003e(5%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16,543/18,520\u003c/p\u003e \u003cp\u003e(89%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eInsecticide exposure\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e288/18,520\u003c/p\u003e \u003cp\u003e(2%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,689/18,520\u003c/p\u003e \u003cp\u003e(9%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16,543/18,520\u003c/p\u003e \u003cp\u003e(89%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eHistory of narcotic use\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e41/18,520\u003c/p\u003e \u003cp\u003e(\u0026lt;\u0026thinsp;1%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,936/18,520\u003c/p\u003e \u003cp\u003e(11%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16,543/18,520\u003c/p\u003e \u003cp\u003e(89%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eHistory of severe head injury\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e70/18,520\u003c/p\u003e \u003cp\u003e(\u0026lt;\u0026thinsp;1%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,906/18,520\u003c/p\u003e \u003cp\u003e(10%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNot specified (%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16,544/18,520\u003c/p\u003e \u003cp\u003e(89%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTHB, Thai Baht.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec22\" class=\"Section2\"\u003e \u003ch2\u003eCheckPD app performance\u003c/h2\u003e \u003cp\u003eOverall performance of the CheckPD app across all RE-AIM dimensions is summarised in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eRE-AIM indicators for CheckPD.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDomain\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eIndicator\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eData Source\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eValue\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eInterpretation\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eReach\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21,882 screened / 30,327 downloads\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eApp analytics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e72.15%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eHigh participation\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEffectiveness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePositive predictive value\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePositive predictive values\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e81.23%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eStrong agreement with clinical labels\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAdoption\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eActive provinces\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eTRCS records\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNationwide activation\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImplementation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMean SUS score/ completion rate\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eUsability survey\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e83/92%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eExcellent usability\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMaintenance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eIntegration into NCD programme\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eTRCS policy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eIn progress\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eEarly policy uptake\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eReach\u003c/strong\u003e \u003cp\u003eOverall programme reach, defined as the proportion of screened individuals relative to app downloads, was 72.15%, indicating high population engagement during this early phase of national implementation.\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eEffectiveness\u003c/strong\u003e \u003cp\u003eThe CheckPD app showed a positive predictive value of 81.23% based on those 730 users who were considered \u0026lsquo;at-risk\u0026rsquo; according to the app\u0026rsquo;s AI prediction during screening versus the subsequent neurologist\u0026rsquo;s diagnosis (Supplementary Data 2)\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cstrong\u003eAdoption\u003c/strong\u003e \u003cp\u003eMost CheckPD implementation activities occurred in 2025, following a preparatory period in 2024 dedicated to programme planning, system development, stakeholder engagement, and team readiness. Adoption of the CheckPD platform increased primarily during organised implementation periods, with screening activity remaining low outside these intervals (Fig.\u0026nbsp;\u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e6\u003c/span\u003e). Distinct spikes in participation were observed following online training sessions and field-based screening activities across provinces, indicating that these facilitated activities directly contributed to increased app uptake and screening completion. The highest levels of screening activity were recorded between May and September 2025, during which weekly screening volumes exceeded 1,000 participants during peak periods (Fig.\u0026nbsp;\u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e6\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eintensive outreach between May and September 2025, demonstrating the direct impact of facilitated implementation strategies on user uptake and screening participation.\u003c/p\u003e \u003cp\u003eGeographic distribution of screening participation varied across provinces (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e1\u003c/span\u003e). The highest levels of participation were observed in Nakhon Pathom, while Chonburi recorded the lowest uptake. Provinces with more than 500 screened participants were predominantly located in the central, northeastern, and selected southern regions of Thailand, reflecting regional differences in adoption associated with local implementation intensity and engagement strategies (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cstrong\u003eImplementation\u003c/strong\u003e \u003cp\u003eLevels of participation and test completion within the CheckPD programme varied across provinces and by implementation method (Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e). Across all settings, 13,381 of 18,520 participants (72%) completed the full screening protocol, while 5,139 (28%) had incomplete assessments. Volunteer-facilitated and organised implementation strategies accounted for the majority of engagement, with 6,742 participants screened through VHVs, 5,207 through community-based field screening campaigns, and 3,172 via online training-activated screening sessions whilst the remainder (2,080) were completed by self-initiated app downloads. Completion rates were consistently higher in structured, facilitated settings, particularly those involving VHVs and online training, compared with self-download pathways in several provinces (Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e).\u003c/p\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eParticipation and screening completion outcomes of the CheckPD programme by province and implementation method among users from the first 10 provinces\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eProvince\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eImplementation method\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eParticipants\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003eTest result\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003eCompleted\u003c/b\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003eIncomplete\u003c/b\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003eNakhon Pathom\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e850 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e593 (70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e257 (30%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,694 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1,319 (78%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e375 (22%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVHVs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2,189 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1,663 (76%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e526 (24%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e402 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e296 (74%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e106 (26%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003ePhetchaburi\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e434 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e269 (62%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e165 (38%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e76 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e49 (64%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e27 (36%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e66 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e35 (53%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e31 (47%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003eSi Sa Ket\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e617 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e384 (62%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e233 (38%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e433 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e251 (58%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e182 (42%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003eNakhon Sawan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,342 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e919 (68%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e423 (32%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e887 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e670 (76%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e217 (24%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVHVs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2,452 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1,896 (77%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e556 (23%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e373 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e281 (75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e92 (25%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003eChiang Rai\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e827 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e471 (57%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e356 (43%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e146 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98 (67%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e48 (33%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVHVs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2,101 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1,571 (75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e530 (25%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e44 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e33 (75%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e11 (25%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003eNonthaburi\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e440 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e299 (68%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e141 (32%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e89 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e69 (78%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e20 (22%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e296 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e206 (70%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e90 (30%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003ePathum Thani\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e331 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e244 (74%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e87 (26%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e279 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e206 (74%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e73 (26%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e283 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e201 (71%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e82 (29%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eSamut Prakan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e365 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e303 (83%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e62 (17%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e66 (71%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e27 (29%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eBangkok\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,043 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e753 (72%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e290 (28%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eChulaPD Clinic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e276 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e170 (62%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e106 (38%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eChon Buri\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1 (100%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e90 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e65 (72%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e25 (28%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cb\u003e18,520 (100%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e13,381 (72%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e5,139 (28%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eVHVs, Village Health Volunteers.\u003c/p\u003e \u003cp\u003eAmong participants who completed screening, 1,761 individuals (13%) were classified as \u0026lsquo;at risk\u0026rsquo; by the CheckPD screening algorithm (Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e). Of these, 730 individuals underwent in-person neurological evaluation, primarily through organised field screening activities where established referral pathways and specialist access were available (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e5\u003c/span\u003e). Among the neurologist-evaluated participants, 593 were clinically diagnosed with PD, corresponding to a PPV of 81.23% for the CheckPD screening algorithm (Supplementary Data 2). The remaining individuals classified as \u0026lsquo;at risk\u0026rsquo; had not yet received specialist diagnostic assessment at the time of analysis, reflecting real-world constraints related to access, timing, and referral uptake.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDistribution of CheckPD screening algorithm risk classifications amongst participants with completed assessments, by province and implementation method\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eProvince\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eImplementation method\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eParticipants with completed test result\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c5\" namest=\"c4\"\u003e \u003cp\u003eAI prediction result\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003eAt risk\u003c/b\u003e\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003eNormal\u003c/b\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003eNakhon Pathom\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e593 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e104 (18%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e489 (82%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,319 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95 (7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1,224 (93%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVHVs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,663 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e141 (8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1,522 (92%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e296 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e15 (5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e281 (95%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003ePhetchaburi\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e269 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e30 (11%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e239 (89%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e49 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4 (8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e45 (92%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e35 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8 (23%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e27 (77%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003eSi Sa Ket\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e384 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e51 (13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e333 (87%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1 (100%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e251 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e25 (10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e226 (90%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003eNakhon Sawan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e919 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e142 (15%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e777 (85%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e670 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e51 (8%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e619 (92%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVHVs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,896 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e131 (7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1,765 (93%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e281 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e17 (6%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e264 (94%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003eChiang Rai\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e471 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e90 (19%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e381 (81%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e98 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7 (7%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e91 (93%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eVHVs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1,571 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e230 (15%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1,341 (85%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11 (33%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e22 (67%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003eNonthaburi\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e299 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e40 (13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e259 (87%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e69 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7 (10%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e62 (90%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e206 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e49 (24%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e157 (76%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003ePathum Thani\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e244 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e32 (13%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e212 (87%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOnline Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e206 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11 (5%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e195 (95%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e201 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e31 (15%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e170 (85%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eSamut Prakan\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e303 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e125 (41%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e178 (59%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e66 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e23 (35%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e43 (65%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eBangkok\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e753 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e161 (21%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e592 (79%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eChulaPD Clinic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e170 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e116 (68%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e54 (32%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eChon Buri\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eField Screening\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0 (0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0 (0%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0 (0%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSelf-download\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e65 (100%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e14 (22%)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e51 (78%)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTotal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cb\u003e13,381 (100%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cb\u003e1,761 (13%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u003cb\u003e11,620 (87%)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eVHVs, Village Health Volunteers.\u003c/p\u003e \u003cp\u003eTask completion demonstrated clear age-related gradients, with completion rates declining progressively in older age groups (Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e7\u003c/span\u003e). Funnel plot analyses further highlighted task-specific differences in completion, with questionnaire-based and voice assessments achieving the highest completion rates, while motor tasks requiring greater physical stability, precise sensor positioning, or environmental setup, such as gait, balance, and certain tremor assessments, showed lower completion rates (Fig.\u0026nbsp;\u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e8\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThis figure illustrates screening task completion rates across predefined age groups among users from the first 10 provinces included in the analysis. Completion rates declined progressively with increasing age, indicating age-related differences in engagement and ability to complete all components of the digital screening workflow.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThis funnel plot shows the proportion of participants completing each screening task, with higher completion for questionnaire and voice-based assessments and lower completion for more complex motor tasks, reflecting increasing task burden in real-world, unsupervised use.\u003c/p\u003e \u003cp\u003eMultivariable logistic regression analysis identified educational attainment and geographic context as significant predictors of screening completion (Table\u0026nbsp;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e). Participants with a Bachelor\u0026rsquo;s degree or higher were more likely to complete all screening tasks compared with those with lower educational attainment (odds ratio [OR]\u0026thinsp;=\u0026thinsp;1.528, 95% CI 1.380\u0026ndash;1.691). In contrast, residence outside Bangkok was associated with a lower likelihood of completion (OR\u0026thinsp;=\u0026thinsp;0.755, 95% CI 0.662\u0026ndash;0.860), underscoring the influence of urban\u0026ndash;rural context on implementation fidelity and user engagement (Table\u0026nbsp;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab7\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 7\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eLogistic regression analysis of user parameters that influenced the likelihood of completing the CheckPD app screening tests.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePredictors\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eExp (B)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cem\u003ep\u003c/em\u003e-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEducational status \u0026ndash; Bachelor's degree\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.528 (95%CI 1.380\u0026ndash;1.691)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eProvince \u0026ndash; Bangkok\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.755 (95%CI 0.662\u0026ndash;0.860)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eModel summary\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOmnibus tests of Model coefficients: Chi-square\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e17.393\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNagelkerke R Square\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.006\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHosmer and Lemeshow Test\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.365\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"3\"\u003e*: Statistically significant. The pseudo R-square from the Nagelkerke R-square model determined the percentage of variance. Nagelkerke R-squared \u0026ndash; an approximate measure of the proportion of explained variation. Hosmer and Lemeshow Test \u0026ndash; the goodness of fit in the logistic regression model.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cdiv id=\"Sec23\" class=\"Section3\"\u003e \u003ch2\u003eUsability outcomes\u003c/h2\u003e \u003cp\u003eResults for the usability survey showed a mean (\u0026plusmn;\u0026thinsp;SD) SUS score of 83\u0026thinsp;\u0026plusmn;\u0026thinsp;9, along with a 92% completion rate among first-time users aged 40\u0026ndash;70 years, indicating excellent usability. The median total test time was 8 minutes. Common user feedback was that the CheckPD app was \u0026ldquo;easy to understand\u0026rdquo; and \u0026ldquo;trustworthy because of the Red Cross logo\u0026rdquo;. Qualitative data confirmed emotional reassurance and confidence due to the clear prompts and branding.\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec24\" class=\"Section2\"\u003e \u003ch2\u003eUser experience (UX)\u003c/h2\u003e \u003cp\u003eThe mean (\u0026plusmn;\u0026thinsp;SD) UEQ-S scores for \u0026lsquo;efficiency\u0026rsquo; and \u0026lsquo;interesting\u0026rsquo; were 1.8\u0026thinsp;\u0026plusmn;\u0026thinsp;1.0 and 1.7\u0026thinsp;\u0026plusmn;\u0026thinsp;1.2, respectively. The overall mean pragmatic quality score was 1.6\u0026thinsp;\u0026plusmn;\u0026thinsp;1.0, while the mean hedonic quality score was 1.5\u0026thinsp;\u0026plusmn;\u0026thinsp;1.1, resulting in an overall mean user experience score of 1.6\u0026thinsp;\u0026plusmn;\u0026thinsp;0.9. A multi-bar chart comparing these results with a reference benchmark dataset indicated that the app performed well, with mean overall values and values for pragmatic quality and hedonic quality rated as \u0026lsquo;good\u0026rsquo; (Fig.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e9\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cdiv id=\"Sec25\" class=\"Section3\"\u003e \u003ch2\u003eSystem performance\u003c/h2\u003e \u003cp\u003eResults for CheckPD app stability and response time confirmed that it is suitable for field operations. System logs confirmed a crash rate of \u0026lt;\u0026thinsp;1% and an offline success rate of 93%, enabling reliable operation in remote settings. Volunteer throughput was ~\u0026thinsp;12 participants/hour.\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cdiv id=\"Sec27\" class=\"Section2\"\u003e \u003ch2\u003eOverall findings for primary and secondary outcome measures\u003c/h2\u003e \u003cp\u003eThis real-world implementation study has confirmed that the CheckPD app is a feasible and robust national PD screening platform for Thailand. Results for RE-AIM Framework parameters demonstrated that CheckPD had excellent reach and adoption with high levels of engagement and completion of tasks. The AI-driven CheckPD app also achieved high PPV (81.23%) when compared with neurologists\u0026rsquo; PD diagnoses.\u003c/p\u003e \u003cp\u003eThe observed reduction in PPV in this study compared with the original hospital-based validation study\u0026rsquo;s reported diagnostic accuracy of 91% [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e] confirms a broader and well-recognised phenomenon in AI deployment, a so-called \u0026lsquo;translation gap\u0026rsquo; or \u0026lsquo;deployment gap\u0026rsquo;. Recent reviews have documented that AI systems which perform well under controlled development or clinical-trial conditions often fail to maintain performance when deployed in diverse real-world settings, due to data heterogeneity, variable workflows, and shifts in patient population [\u003cspan citationid=\"CR69\" class=\"CitationRef\"\u003e69\u003c/span\u003e, \u003cspan citationid=\"CR70\" class=\"CitationRef\"\u003e70\u003c/span\u003e]. In addition, machine-learning research has identified \u0026lsquo;under-specification\u0026rsquo;, the tendency for equally good models on training data to behave very differently once deployed outside the development domain, as a fundamental reason for unpredictability in real-world use [\u003cspan citationid=\"CR71\" class=\"CitationRef\"\u003e71\u003c/span\u003e]. These observations strongly support the need for of adaptive validation and continuous post-deployment monitoring when scaling diagnostic AI tools [\u003cspan citationid=\"CR72\" class=\"CitationRef\"\u003e72\u003c/span\u003e]. In this respect, CheckPD\u0026rsquo;s national rollout, spanning 10 Thai provinces with diverse demographics, device types, and real-world use conditions, provides a valuable empirical example of the deployment gap in a neurological screening context. Although direct comparison of the outcomes of the two studies is not possible due to metric differences (PPV versus diagnostic accuracy), the high PPV of 81.23% suggests that CheckPD continues to identify true PD cases with high precision in real-world implementation, consistent with the high accuracy previously reported in the controlled validation study [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e]. This finding supports the robustness of CheckPD\u0026rsquo;s screening algorithm and suggests that its performance translates effectively into real-world use, even in a large, diverse population across multiple provinces.\u003c/p\u003e \u003cp\u003eThe performance of CheckPD during national implementation was influenced by several real-world factors that differed substantially from the controlled environment of the original validation study. Unlike structured testing performed under supervision, screening in community settings relies on participants\u0026rsquo; ability to follow instructions independently, which introduces variability related to digital literacy and user skill, a known barrier to effective engagement with digital health technologies and outcomes across diverse populations [\u003cspan citationid=\"CR73\" class=\"CitationRef\"\u003e73\u003c/span\u003e, \u003cspan citationid=\"CR74\" class=\"CitationRef\"\u003e74\u003c/span\u003e]. Device heterogeneity, including differences in smartphone hardware, operating systems, sensor quality, and environmental conditions, has been shown to affect sensor data quality collected in real-world settings, potentially introducing inconsistencies in health-related assessments derived from consumer-owned devices [\u003cspan citationid=\"CR75\" class=\"CitationRef\"\u003e75\u003c/span\u003e]. In addition, incomplete task completion, network connectivity issues, and variable levels of user engagement can lead to missing data and reduced evaluable datasets, reflecting known challenges in remote and unsupervised digital data collection [\u003cspan citationid=\"CR76\" class=\"CitationRef\"\u003e76\u003c/span\u003e]. These implementation realities likely contribute to deviations from controlled-study performance metrics but also reflect the authentic operational environment in which CheckPD is intended to function. Despite these challenges, the app maintained a high PPV in real-world use, suggesting resilience of the screening algorithm even under less ideal conditions and underscoring the potential for well-designed digital health tools to yield clinically meaningful results outside the laboratory.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec28\" class=\"Section2\"\u003e \u003ch2\u003eStrengths of CheckPD and implementation success factors\u003c/h2\u003e \u003cp\u003e Key facilitators of the positive results obtained with CheckPD in this study included TRCS endorsement and network, community volunteer involvement, and its user-friendly design. While other PD mobile applications have been developed primarily for symptom tracking and patient support (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e), there is limited evidence regarding digital tools designed for national population-level screening. To our knowledge, CheckPD represents the first national, app-based population screening programme for PD, implemented within a universal healthcare coverage system.\u003c/p\u003e \u003cp\u003eCheckPD differs from existing digital tools for PD in both its scope and means of deployment. A key strength of the app is that it employs multimodal analysis to evaluate a combination of different data inputs which previous studies have shown can provide valuable additional information leading to greater accuracy when compared to analysis of individual modalities alone [\u003cspan citationid=\"CR77\" class=\"CitationRef\"\u003e77\u003c/span\u003e, \u003cspan citationid=\"CR78\" class=\"CitationRef\"\u003e78\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec29\" class=\"Section2\"\u003e \u003ch2\u003eChallenges and limitations\u003c/h2\u003e \u003cp\u003eAnalysis of data from our national implementation study identified that gender, age, level of education and geographical location were all factors that influenced app engagement and test completion. Large population surveys of mobile health (mHealth) apps have also demonstrated systematic gender, age and education differences in app use and sustained engagement [\u003cspan citationid=\"CR79\" class=\"CitationRef\"\u003e79\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eOur study attracted a higher proportion of female app users than men. This pattern probably reflects gender differences in health-seeking behavior and willingness to engage with preventive digital tools, rather than underlying disease epidemiology. The over-representation of women among CheckPD users contrasts with the slightly higher prevalence of PD in men [\u003cspan citationid=\"CR80\" class=\"CitationRef\"\u003e80\u003c/span\u003e]. Similar gender imbalances have been reported across internet- and app-based preventive and mental-health interventions, where evidence suggests that women may disproportionately engage with preventive health and health monitoring technologies, and that digital health innovations can positively affect women\u0026rsquo;s access to health care and self-care[\u003cspan additionalcitationids=\"CR82\" citationid=\"CR81\" class=\"CitationRef\"\u003e81\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR83\" class=\"CitationRef\"\u003e83\u003c/span\u003e]. Our findings therefore probably reflect gendered patterns of digital health engagement rather than true PD risk, and raise the possibility that some higher-risk men are under-screened by the current digital strategy.\u003c/p\u003e \u003cp\u003eThe observed age-related patterns of test completion and dropout raise the possibility that some higher-risk individuals, particularly older men, may be under-screened by the current predominantly app-based strategy [\u003cspan additionalcitationids=\"CR85\" citationid=\"CR84\" class=\"CitationRef\"\u003e84\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR86\" class=\"CitationRef\"\u003e86\u003c/span\u003e]. Future iterations of CheckPD should therefore consider targeted outreach and tailored messaging to improve engagement among older men and other under-represented groups. These patterns also suggest a dual mechanism of attrition: younger adults (often at lower PD risk) were more likely to skip individual tasks, whereas older adults, the primary target population for PD screening, were more likely to initiate screening but not complete the full assessment workflow. This pattern may reflect motivational dropout amongst younger users and capability- or usability-related dropout amongst older users, consistent with usability research demonstrating that age-related cognitive, sensory, and visuomotor changes can hinder effective interaction with complex digital interfaces and sensor-based tasks. Consequently, datasets used for training and validating digital biomarkers may over-represent younger, digitally proficient, and more adherent users, while under-representing frailer or more impaired older adults. This form of informative missingness represents an important limitation, as it may bias estimates of model performance when digital screening tools are deployed in routine, unsupervised real-world settings [\u003cspan citationid=\"CR87\" class=\"CitationRef\"\u003e87\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eOur findings regarding educational level likely reflect the importance of digital health literacy for effective engagement with the CheckPD application. The lower completion rates observed among residents in more rural regions further highlight the value of VHVs in facilitating participation and supporting users with varying levels of digital access and literacy.\u003c/p\u003e \u003cp\u003eAssessing the impact of missing data is critical for evaluating app-based screening tools in the field. However, in this real-world implementation, 72% of participants completed all assessment tasks, a substantial level of engagement for a multi-task, unsupervised workflow deployed at scale. This figure compares favourably with broader mHealth and digital phenotyping literature, where sustained adherence often falters outside controlled research environments. Indeed, contemporary studies suggest that real-world adherence exceeding 70% sits at the \u0026lsquo;high end\u0026rsquo; of reported benchmarks [\u003cspan citationid=\"CR88\" class=\"CitationRef\"\u003e88\u003c/span\u003e]. For context, while intensive interventions with specialised design elements can reach \u0026lsquo;exceptionally high\u0026rsquo; daily completion rates of 84%, typical real-world Ecological Momentary Assessment studies report averages closer to 67.2% [\u003cspan citationid=\"CR89\" class=\"CitationRef\"\u003e89\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eDespite exceeding these benchmarks, our data revealed distinct patterns of incomplete engagement. Completion rates declined as participant age increased, with a notable divergence in behaviour: while younger participants more frequently left specific tasks unattempted, older adults were more likely to terminate assessments mid-sequence. Funnel analyses further clarified this attrition, highlighting cumulative dropout at transitions to complex or sensor-intensive motor tasks. This suggests that a subset of higher-burden activities accounted for a disproportionate share of data loss, underscoring the delicate balance between task complexity and sustained user adherence in remote screening. These patterns are consistent with findings from smartphone-based digital phenotyping studies, in which missing sensor and task data are common and vary widely between individuals, even within well-controlled research protocols [\u003cspan citationid=\"CR90\" class=\"CitationRef\"\u003e90\u003c/span\u003e, \u003cspan citationid=\"CR91\" class=\"CitationRef\"\u003e91\u003c/span\u003e]. Analyses of large digital phenotyping cohorts, such as the mindLAMP platform, similarly show that adherence decreases as task frequency and complexity increase, with high-friction tasks disproportionately driving disengagement [\u003cspan citationid=\"CR92\" class=\"CitationRef\"\u003e92\u003c/span\u003e, \u003cspan citationid=\"CR93\" class=\"CitationRef\"\u003e93\u003c/span\u003e]. Systematic reviews of mHealth interventions consistently identify participant attrition and engagement loss as key challenges for real-world implementation [\u003cspan citationid=\"CR94\" class=\"CitationRef\"\u003e94\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e"},{"header":"Conclusions","content":"\u003cp\u003eThe CheckPD programme has demonstrated a successful transition from a validated digital prototype to a scalable, real-world national public health intervention for PD. Its strong real-world performance, reflected in a high PPV of the screening algorithm, combined with a HCD approach and robust ethical governance, positions Thailand\u0026rsquo;s implementation as a credible reference model for digital neurology and population-level brain health initiatives globally. By enabling early identification of individuals at increased risk of PD and establishing clear pathways for clinical follow-up, CheckPD supports timely intervention and behaviour-focused risk modification. This approach aligns closely with emerging prevention-oriented strategies for PD and with the WHO\u0026rsquo;s Brain Health framework, highlighting the potential of integrated digital screening programmes to contribute meaningfully to neurological disease prevention at scale.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval:\u0026nbsp;\u003c/strong\u003eThe protocol for this study was approved by the Institutional Review Board of the Faculty of Medicine, Chulalongkorn University (IRB No. 0804/65), as well as from the Central Research Ethics Committee (CREC) under the approved protocol entitled \u0026lsquo;Flipping the Paradigm of Parkinson\u0026rsquo;s Disease: A Model of National \u0026lsquo;Eat, Move, Sleep\u0026rsquo; Digital Interventions to Prevent or Slow the Rise of Non-Communicable Diseases in Thailand\u0026rsquo; (CREC No. CREC023/68BR-MED06; Certificate Number COA-CREC105/2025).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to participate:\u003c/strong\u003e Digital informed consent was obtained from all participants.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials:\u0026nbsp;\u003c/strong\u003eSupplementary materials relevant to this study are available via the ChulaPD Screening Data Repository at: https://drive.google.com/drive/folders/1UqVXnM6HEsLGmdLu2gjng96AhRaQ2ios\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests:\u0026nbsp;\u003c/strong\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding:\u003c/strong\u003e This research was funded by the following grants; the Thailand Science Research and Innovation Fund (Program Management Unit for Competitiveness, C01F670185), the National Economic and Social Development Council, Thailand Center for Excellence for Life Sciences (TC (ERP) 31/2568), National Research Council of Thailand (N42A680591, N35E680087), the Center of Excellence grants of Chulalongkorn University \u0026nbsp; (CE68_028_3000_004), and the Thai Red Cross Education and Research Committee.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions:\u003c/strong\u003e All authors contributed to editorial changes in the manuscript. All authors read and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements:\u003c/strong\u003e This national Parkinson\u0026rsquo;s disease screening initiative was conducted in honour of Her Royal Highness Princess Maha Chakri Sirindhorn, in recognition of her longstanding commitment to public health, medical education, and the wellbeing of the Thai population. The authors also gratefully acknowledge the collaboration with the National Health Security Office (NHSO), which was formally established under a Memorandum of Understanding (MOU) signed on 7 May 2024 enabling integration of the CheckPD screening programme within Thailand\u0026rsquo;s national health system and preventive health framework.\u003c/p\u003e\n\u003cp\u003eThe research team would like to express their sincere appreciation to all individuals and organisations involved in this national programme, including local collaborators, provincial coordinators, and administrative and public health personnel, whose dedication and support were essential to the successful implementation of the project. We also gratefully acknowledge the cooperation of government agencies, provincial public health offices, hospitals, and provincial Red Cross chapters across all participating provinces.\u003c/p\u003e\n\u003cp\u003eThis project was implemented through the collaboration of the following provinces and their affiliated institutions:\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eNakhon Sawan Province\u003c/strong\u003e: Governor of Nakhon Sawan phase 1 (Mr. Thawee Sermphakdikul), President of the Nakhon Sawan Provincial Red Cross Chapter (Mrs. Waraporn Sermphakdikul )and Governor of Nakhon Sawan and President of the Nakhon Sawan Provincial Red Cross Chapter phase 2 (Ms. Chutiphon Sechang), Nakhon Sawan Provincial Public Health Office (Dr. Amnart Noikham , Mr.Teera Kangkhetkron , Miss Nattaya Pattaveenontawong and Miss Wilawan Nunart) Sawanpracharak Hospital (Rattikorn Thungsuk, Chattama Chairat and Mrs.Tassanee Tabthimthai).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eNakhon Pathom Province\u003c/strong\u003e: Governor of Nakhon Pathom and President of the Nakhon Pathom Provincial Red Cross Chapter (Ms. Arocha Nantamontry), Nakhon Pathom Hospital (Dr. Surachai Chokkrchitchai), Sam Phran Hospital (Dr. Tinnakorn Chuenchom), \u0026nbsp; Nakhon Pathom Provincial Public Health Office (Mr.Suphat Katanyutita and Mr.Tawatchai Naksrisung).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eNonthaburi Province\u003c/strong\u003e: Governor of Nonthaburi (Mr. Kiattisak Trongsiri), President of the Nonthaburi Provincial Red Cross Chapter (Mrs. Phonsri Tongsiri), Nonthaburi Provincial Public Health Office (Dr. Paripon Juljerm and Mrs. Sineenart Rattanapunpanit) Pranangklao Hospital (Dr. Sakol Sookprome).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eChiang Rai Province\u003c/strong\u003e: Governor of Chiang Rai (Mr. Charin Tongsuk), President of the Chiang Rai Provincial Red Cross Chapter (Mrs. Sineenat Thongsuk) Chiang Rai Provincial Public Health Office (Dr. Ekkachai Kumlue) Chiang Rai Prachanukroh Hospital (Dr. Achara Laongnualpanich, Miss Netphit Khamhoi and Mrs. Jintana Yoongrum) Mayor of Chiang Rai City Municipality (Mr. Wanchai Jongsutanamanee).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSamut Prakan Province\u003c/strong\u003e: Governor of Samut Prakan (Mr. Suphamit Chinnasri), President of the Samut Prakan Provincial Red Cross Chapter (Miss Orawan Chinnasri), Samut Prakan Provincial Red Cross Chapter (Mrs. Kanchana Pansiri and Mr. Somsak Kaewsana) Samut Prakan Provincial Public Health Office (Mr. Prapart Phookduang and Mrs. Walaipun Sumritwatcharsai) Samut Prakan Hospital (Dr. Pimwalai Chulapimphan).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePhetchaburi Province\u003c/strong\u003e: Governor of Phetchaburi (Pol. Lt. Col. Phopchanok Chalanukhro), President of the Phetchaburi Provincial Red Cross Chapter (Mrs. Natthinee Kongbuchakiat), PhetchaburiProvincial Public Health Office (Mr. Chartchai Kitiyanun, Miss Sununtinee Rungsiriwattanakij and Miss Phiyawan Phobata) Phra Chom Klao Hospital (Dr. Attasit Nawaapisak).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSisaket Province\u003c/strong\u003e: Governor of Sisaket (Mr. Anupong Suksamonit), President of the Sisaket Provincial Red Cross Chapter (Ms. Phakanan Sila-art), Sisaket Provincial Public Health Office (Dr.Thanong Veerasangpong Ms.Sineenuch Wirasaengpong and Ms. Mali Supatti), Sisaket Hospital (Dr.Sitthipan Janpong).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePathum Thani Province\u003c/strong\u003e: Governor of Pathum Thani (Mr. Somkid Chanthamruek), President of the Pathum Thani Provincial Red Cross Chapter (Asst. Prof. Dr. Sasithorn Sujarittanakarn) Pathum Thani Provincial Public Health Office (Dr. Non Jindavech and Mr. Apichon Jeensavake) Pathum Thani Hospital (Dr. Saralee Chindamang and Ms. Kamolruetai Suphakawanich).\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eGlobal Burden of Disease Collaborators. Global age-sex-specific mortality, life expectancy, and population estimates in 204 countries and territories and 811 subnational locations, 1950\u0026ndash;2021, and the impact of the COVID-19 pandemic: a comprehensive demographic analysis for the Global Burden of Disease Study 2021. Lancet. 2024;403(10440):1989\u0026ndash;2056.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlbin R, Grotewold N. What is the Parkinson Pandemic? Mov Disord. 2023;38(12):2141\u0026ndash;4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRossi A, Berger K, Chen H, Leslie D, Mailman RB, Huang X. Projection of the prevalence of Parkinson's disease in the coming decades: Revisited. Mov Disord. 2018;33(1):156\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePayami H, Cohen G, Murchison CF, Sampson TR, Standaert DG, Wallen ZD. Population fraction of Parkinson's disease attributable to preventable risk factors. NPJ Parkinsons Dis. 2023;9(1):159.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSu D, Cui Y, He C, Yin P, Bai R, Zhu J, Lam JST, Zhang J, Yan R, Zheng X, et al. Projections for prevalence of Parkinson's disease and its driving factors in 195 countries and territories to 2050: modelling study of Global Burden of Disease Study 2021. BMJ. 2025;388:e080952.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLuo Y, Qiao L, Li M, Wen X, Zhang W, Li X. Global, regional, national epidemiology and trends of Parkinson's disease from 1990 to 2021: findings from the Global Burden of Disease Study 2021. Front Aging Neurosci. 2024;16:1498756.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhidayasiri R, Wannachai N, Limpabandhu S, Choeytim S, Suchonwanich Y, Tananyakul S, Tharathep C, Panjapiyakul P, Srismith R, Chimabutra K, et al. A national registry to determine the distribution and prevalence of Parkinson's disease in Thailand: implications of urbanization and pesticides as risk factors for Parkinson's disease. Neuroepidemiology. 2011;37(3\u0026ndash;4):222\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChaudhuri KR, Azulay JP, Odin P, Lindvall S, Domingos J, Alobaidi A, Kandukuri PL, Chaudhari VS, Parra JC, Yamazaki T, et al. Economic Burden of Parkinson's Disease: A Multinational, Real-World, Cost-of-Illness Study. Drugs Real World Outcomes; 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCunha M, Almeida H, Guimar\u0026atilde;es I, Ferreira LN. Economic burden of Parkinson\u0026rsquo;s disease and research trends: a bibliometric analysis. J Public Health 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKhan AZ, Lavu D, Neal R. Parkinson's disease: A scoping review of the quantitative and qualitative evidence of its diagnostic accuracy in primary care. Br J Gen Pract 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhidayasiri R, Phokaewvarangkul O, Sakdisornchai K, Boonpang K, Chaudhuri KR, Parsons J, Lolekha P, Chairangsaris P, Srivanitchapoom P, Benedierks S, et al. Establishing apomorphine treatment in Thailand: understanding the challenges and opportunities of Parkinson's disease management in developing countries. Expert Rev Neurother. 2020;20(6):523\u0026ndash;37.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhidayasiri R, Virameteekul S, Sukoandari B, Tran TN, Lim TT. Challenges of Parkinson\u0026rsquo;s Disease Care in Southeast Asia. In: \u003cem\u003eNeuroPsychopharmacotherapy.\u003c/em\u003e edn. Edited by Riederer P, Laux G, Nagatsu T, Le W, Riederer C. Cham: Springer International Publishing; 2020: 1\u0026ndash;21.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLim SY, Tan AH, Ahmad-Annuar A, Klein C, Tan LCS, Rosales RL, Bhidayasiri R, Wu YR, Shang HF, Evans AH et al. Parkinson's disease in the Western Pacific Region. Lancet Neurol 2019.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThailand TNS. Number of Board-Certified and Certified Neurologists in Thailand and Neurology Residency Training Capacity (1964\u0026ndash;2025). In.; 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDahodwala N, Li P, Jahnke J, Ladage VP, Pettit AR, Kandukuri PL, Bao Y, Zamudio J, Jalundhwala YJ, Doshi JA. Burden of Parkinson's Disease by Severity: Health Care Costs in the U.S. Medicare Population. Mov Disord. 2021;36(1):133\u0026ndash;42.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHjalte F, Norlin JM, Kellerborg K, Odin P. Parkinson's disease in Sweden-resource use and costs by severity. Acta Neurol Scand. 2021;144(5):592\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFindley LJ, Wood E, Lowin J, Roeder C, Bergman A, Schifflers M. The economic burden of advanced Parkinson's disease: an analysis of a UK patient dataset. J Med Econ. 2011;14(1):130\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFeigin VL, Vos T, Nichols E, Owolabi MO, Carroll WM, Dichgans M, Deuschl G, Parmar P, Brainin M, Murray C. The global burden of neurological disorders: translating evidence into policy. Lancet Neurol. 2020;19(3):255\u0026ndash;65.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWinkler AS. The growing burden of neurological disorders in low-income and middle-income countries: priorities for policy making. Lancet Neurol. 2020;19(3):200\u0026ndash;2.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDiseases GBD, Injuries C. Global incidence, prevalence, years lived with disability (YLDs), disability-adjusted life-years (DALYs), and healthy life expectancy (HALE) for 371 diseases and injuries in 204 countries and territories and 811 subnational locations, 1990\u0026ndash;2021: a systematic analysis for the Global Burden of Disease Study 2021. Lancet. 2024;403(10440):2133\u0026ndash;61.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDorsey ER, Sherer T, Okun MS, Bloem BR. The Emerging Evidence of the Parkinson Pandemic. J Parkinsons Dis. 2018;8(s1):S3\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhidayasiri R. Old problems, new solutions: harnessing technology and innovation in Parkinson's disease-evidence and experiences from Thailand. J Neural Transm (Vienna) 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhidayasiri R, Kalia LV, Bloem BR. Tackling Parkinson's Disease as a Global Challenge. J Parkinsons Dis. 2023;13(8):1277\u0026ndash;80.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhidayasiri R, Goetz CG. Chap. 2 - Embracing the promise of artificial intelligence to improve patient care in movement disorders. In: \u003cem\u003eHandbook of Digital Technologies in Movement Disorders.\u003c/em\u003e edn. Edited by Bhidayasiri R, Maetzler W: Academic Press; 2024: 11\u0026ndash;23.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhidayasiri R, Mathur S, Maetzler W. Chap. 1 - We are living in the Parkinson's pandemic: how can multi-stakeholders utilize digital technologies effectively? In: \u003cem\u003eHandbook of Digital Technologies in Movement Disorders.\u003c/em\u003e edn. Edited by Bhidayasiri R, Maetzler W: Academic Press; 2024: 3\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhidayasiri R. The grand challenge at the frontiers of neurotechnology and its emerging clinical applications. Front Neurol. 2024;15:1314477.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVirameteekul S, Shin C, Hirczy SS, Sarva H, Paul SS, Maetzler W, Mirelman A, Schneider RB, Hausdorff JM, Vizcarra JA et al. Assessing Digital Health Technologies for Outcome Measurement in Parkinson's Disease Drug Trials: A Systematic Review. Mov Disord 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOsei E, Mashamba-Thompson TP. Mobile health applications for disease screening and treatment support in low-and middle-income countries: A narrative review. Heliyon. 2021;7(3):e06639.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMcCool J, Dobson R, Whittaker R, Paton C. Mobile Health (mHealth) in Low- and Middle-Income Countries. Annu Rev Public Health. 2022;43:525\u0026ndash;39.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDino MJ, Thiamwong L, Xie R, Malacas MK, Hernandez R, Balbin PT, Vital JC, Rivero JA, Xi VW. Mobile health (mHealth) technologies for fall prevention among older adults in low-middle income countries: bibliometrics, network analysis and integrative review. Front Digit Health. 2025;7:1559570.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChong SOK, Pedron S, Abdelmalak N, Laxy M, Stephan AJ. An umbrella review of effectiveness and efficacy trials for app-based health interventions. NPJ Digit Med. 2023;6(1):233.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eReidy C, Papoutsi C, Kc S, Gudgin B, Laverty AA, Greaves F, Powell J. Qualitative evaluation of the implementation and national roll-out of the NHS App in England. BMC Med. 2025;23(1):20.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChawla R, Karkhanis P, Shah M, Das A, Sharma R, Almaula D, Venkatesh P, Singh HV, Kumar M, Samanta R, et al. Artificial intelligence for advancing eye care in resource-poor settings: Assessing the predictive accuracy of an AI-model for diabetic retinopathy screening in India. Glob Epidemiol. 2025;9:100209.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYu Y, Zhang S, Li H, Xue F. A bayesian network model for neurocognitive disorders digital screening in Chinese population: development and validation study. BMC Psychiatry. 2025;25(1):760.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKohrt BA, Ojagbemi A, Luitel NP, Bakolis I, Bello T, McCrone P, Taylor Salisbury T, Jordans MJD, Votruba N, Carswell K, et al. An App-Based WHO Mental Health Guide for Depression Detection: A Cluster Randomized Clinical Trial. JAMA Netw Open. 2025;8(5):e2512064.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKeynejad R, Spagnolo J, Thornicroft G. WHO mental health gap action programme (mhGAP) intervention guide: updated systematic review on evidence and impact. Evid Based Ment Health. 2021;24(3):124\u0026ndash;30.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNong TTT, Nguyen GH, Lepe A, Tran TB, Nguyen LTP, Koot JAR. Challenges and Opportunities in Digital Screening for Hypertension and Diabetes Among Community Groups of Older Adults in Vietnam: Mixed Methods Study. J Med Internet Res. 2024;26:e54127.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFritz M, Grimm M, Weber I, Yom-Tov E, Praditya B. Can social media encourage diabetes self-screenings? A randomized controlled trial with Indonesian Facebook users. NPJ Digit Med. 2024;7(1):245.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSingh DKA, Goh JW, Shaharudin MI, Shahar S. A Mobile App (FallSA) to Identify Fall Risk Among Malaysian Community-Dwelling Older Persons: Development and Validation Study. JMIR Mhealth Uhealth. 2021;9(10):e23663.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOoi CY, Ng CJ, Sales A, Teo CH. Pilot implementation study of a web-based men's health screening app in primary care during COVID-19: a mixed-methods approach. BMC Health Serv Res. 2024;24(1):1219.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRuamviboonsuk P, Tiwari R, Sayres R, Nganthavee V, Hemarat K, Kongprayoon A, Raman R, Levinstein B, Liu Y, Schaekermann M, et al. Real-time diabetic retinopathy screening by deep learning in a multisite national screening programme: a prospective interventional cohort study. Lancet Digit Health. 2022;4(4):e235\u0026ndash;44.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eInsightera. Digital 2025 Thailand: Key Highlights from We Are Social \u0026amp; Meltwater Report. In.; 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSukphan J, Kitdamrongtam P, Satjasomboon S. Rethinking Digital Access in Thailand. Rajamangala Univ Technol Tawan-ok Social Sci J. 2024;13(1):1\u0026ndash;10.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRobru K, Setthasuravich P, Pukdeewut A, Wetchakama S. Internet use for health-related purposes among older people in Thailand: an analysis of nationwide cross-sectional data. Informatics. 2024;11(3):55.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThaneewat N, Sermsri N. Development of digital literacy skills in using government applications for the elderly in Samut Prakan Province. Procedia Multidisciplinary Res. 2024;2(11):53.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSureephong P, Laothiang A, Inthawong K, Satprasoet S, Auttajinda N. Digital transformation for non-communicable disease prevention and control in Thailand by using a mixed methods approach. In: \u003cem\u003eProduct lifecycle management Leveraging AI, digital twins, and smart technologies (PLM 2024).\u003c/em\u003e Volume 741 edn. Edited by Sureephong P, Danjou C, Bouras A. Switzerland: Springer Nature; 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVichitkunakorn P, Sathirapanya C, Buathong N, Sornsenee P, Chaichulee S, Donraman T. Developing web-based interventions for alcohol use screening and alcohol education administered by village health volunteers in the community setting. Drug Alcohol Depend. 2024;264:112461.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSongserm N, Woradet S, Bureelerd O, Thongchai C, Thongprung S, Ali A. Effectiveness of Leader Village Health Volunteers Training Program on Preventing Cholangiocarcinoma in Thailand: Advantages for High-Risk Area with Limited Public Health Personnel. J Cancer Educ. 2021;36(6):1306\u0026ndash;15.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhidayasiri R, Sringean J, Phumphid S, Anan C, Thanawattano C, Deoisres S, Panyakaew P, Phokaewvarangkul O, Maytharakcheep S, Buranasrikul V, et al. The rise of Parkinson's disease is a global challenge, but efforts to tackle this must begin at a national level: a protocol for national digital screening and eat, move, sleep lifestyle interventions to prevent or slow the rise of non-communicable diseases in Thailand. Front Neurol. 2024;15:1386608.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLean PL, Sringean J, Saengmanee T, Rattanajun P, Chaisongkram A, Bhidayasiri R. Clinical characteristics and motor dysfunction in probable REM sleep behavior disorder(pRBD): Insights from CHECK-PD community-based screening project. Mov Disord 2025, 40.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSringean J, Phumphid S, Anan C, Meesri J, Rattanajun P, Wehhinhiran S, Chantadunga A, Sanengmanee T, Bhidayasiri R. The discrepancy between self-reported hyposmia and objective assessment by Sniffin\u0026rsquo; sticks in high risk of synucleinopathies and healthy controls. Mov Disord 2025, 40.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmouzadeh E, Dianat I, Faradmal J, Babamiri M. Optimizing mobile app design for older adults: systematic review of age-friendly design. Aging Clin Exp Res. 2025;37(1):248.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eArslan STA, O'Connor S, Stanmore E. Human-Centred Design of Digital Health Dashboards for Management of Health in the Care of Older Adults: A Scoping Review. Stud Health Technol Inf. 2025;329:1986\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAzadi H, Akbarzadeh-Totonchi MR, Jahani Y, Gohari SH, Khajouei R. Evaluation of mobile applications related to patients with Parkinson's disease based on their essential features and capabilities. BMC Med Inf Decis Mak. 2024;24(1):407.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMcCarthy B, Sabharwal JK, Chawla S. Old age or cognitive decline? Examining the usability of a mobile health app for older Australians. Inf Health Soc Care. 2024;49(1):83\u0026ndash;97.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYoung SR, Dworak EM, Byrne GJ, Jones CM, Yao L, Yoshino Benavente JN, Diaz MV, Curtis L, Gershon R, Wolf M, et al. Remote Self-Administration of Cognitive Screeners for Older Adults Prior to a Primary Care Visit: Pilot Cross-Sectional Study of the Reliability and Usability of the MyCog Mobile Screening App. JMIR Form Res. 2024;8:e54299.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDuracinsky M, Brown Hajdukova E, Peretz F, Sauzin J, Gouider-Khouja N, Atlani C, Dalili D. Collecting Feedback From Neurologists and Patients to Guide Development of a Parkinson Disease App (DigiPark): Qualitative, Noninterventional Study. JMIR Hum Factors. 2024;11:e55032.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTriantafyllidis A, Segkouli S, Zygouris S, Michailidou C, Avgerinakis K, Fappa E, Vassiliades S, Bougea A, Papagiannakis N, Katakis I et al. Mobile App Interventions for Parkinson's Disease, Multiple Sclerosis and Stroke: A Systematic Literature Review. Sens (Basel) 2023, 23(7).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLinares-Del Rey M, Vela-Desojo L, Cano-de la Cuerda R. Mobile phone applications in Parkinson's disease: A systematic review. Neurologia (Engl Ed). 2019;34(1):38\u0026ndash;54.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee J, Yeom I, Chung ML, Kim Y, Yoo S, Kim E. Use of Mobile Apps for Self-care in People With Parkinson Disease: Systematic Review. JMIR Mhealth Uhealth. 2022;10(1):e33944.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGlasgow RE, Vogt TM, Boles SM. Evaluating the public health impact of health promotion interventions: the RE-AIM framework. Am J Public Health. 1999;89(9):1322\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGlasgow RE, Klesges LM, Dzewaltowski DA, Estabrooks PA, Vogt TM. Evaluating the impact of health promotion programs: using the RE-AIM framework to form summary measures for decision making involving complex issues. Health Educ Res. 2006;21(5):688\u0026ndash;94.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGlasgow RE, Harden SM, Gaglio B, Rabin B, Smith ML, Porter GC, Ory MG, Estabrooks PA. RE-AIM Planning and Evaluation Framework: Adapting to New Science and Practice With a 20-Year Review. Front Public Health. 2019;7:64.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVan Den Eeden SK, Tanner CM, Bernstein AL, Fross RD, Leimpeter A, Bloch DA, Nelson LM. Incidence of Parkinson's disease: variation by age, gender, and race/ethnicity. Am J Epidemiol. 2003;157(11):1015\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePostuma RB, Berg D. Prodromal Parkinson's Disease: The Decade Past, the Decade to Come. Mov Disord. 2019;34(5):665\u0026ndash;75.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBrooke J. SUS - A quick and dirty usability scale. In: \u003cem\u003eUsability Evaluation in Industry.\u003c/em\u003e edn. Edited by Jordan PW, Thomas B, Weerdmeester BA, McClelland IL: Taylor \u0026amp; Francis; 1996: 189\u0026ndash;194.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSchrepp M, Hinderks A, Thomaschewski J. Design and Evaluation of a Short Version of the User Experience Questionnaire (UEQ-S). Int J Interact Multimedia Artif Intell. 2017;4:103.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003evon Elm E, Altman DG, Egger M, Pocock SJ, Gotzsche PC, Vandenbroucke JP, Initiative S. The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies. Lancet. 2007;370(9596):1453\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEl Arab RA, Abu-Mahfouz MS, Abuadas FH, Alzghoul H, Almari M, Ghannam A, Seweid MM. Bridging the Gap: From AI Success in Clinical Trials to Real-World Healthcare Implementation-A Narrative Review. \u003cem\u003eHealthcare (Basel)\u003c/em\u003e 2025, 13(7).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOvergaard SM, Graham MG, Brereton T, Pencina MJ, Halamka JD, Vidal DE, Economou-Zavlanos NJ. Implementing quality management systems to close the AI translation gap and facilitate safe, ethical, and effective health AI solutions. NPJ Digit Med. 2023;6(1):218.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eD\u0026rsquo;Amour A, Heller K, Moldovan D, Adlam B, Alipanahi B, Beutel A. Underspecification presents challenges for credibility in modern machine learning. J Mach Learn Res. 2022;23(266):1\u0026ndash;61.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAdnan HS, Shidani A, Clifton L, Bankhead CR, Perera-Salazar R. Implementation framework for AI deployment at scale in healthcare systems. iScience. 2025;28(5):112406.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWamala Andersson S, Gonzalez MP. Digital health literacy-a key factor in realizing the value of digital transformation in healthcare. Front Digit Health. 2025;7:1461342.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEsper CD, Valdovinos BY, Schneider RB. The Importance of Digital Health Literacy in an Evolving Parkinson's Disease Care System. J Parkinsons Dis. 2024;14(s1):S181\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHalabi R, Selvarajan R, Lin Z, Herd C, Li X, Kabrit J, Tummalacherla M, Chaibub Neto E, Pratap A. Comparative Assessment of Multimodal Sensor Data Quality Collected Using Android and iOS Smartphones in Real-World Settings. \u003cem\u003eSensors (Basel)\u003c/em\u003e 2024, 24(19).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGilbert S, Pimenta A, Stratton-Powell A, Welzel C, Melvin T. Continuous Improvement of Digital Health Applications Linked to Real-World Performance Monitoring: Safe Moving Targets? Mayo Clin Proc Digit Health. 2023;1(3):276\u0026ndash;87.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIvanova A, Shcherbak A, Nesteruk S, Bril E, Baldycheva A, Somov A. Parkinson\u0026rsquo;s disease detection through multimodal data analysis. Smart Health. 2025;38:100618.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePrashanth R, Dutta Roy S, Mandal PK, Ghosh S. High-Accuracy Detection of Early Parkinson's Disease through Multimodal Features and Machine Learning. Int J Med Inf. 2016;90:13\u0026ndash;21.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCarroll JK, Moorhead A, Bond R, LeBlanc WG, Petrella RJ, Fiscella K. Who Uses Mobile Phone Health Apps and Does Use Matter? A Secondary Data Analytics Approach. J Med Internet Res. 2017;19(4):e125.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBen-Shlomo Y, Darweesh S, Llibre-Guerra J, Marras C, San Luciano M, Tanner C. The epidemiology of Parkinson's disease. Lancet. 2024;403(10423):283\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTian L, Wong EL, Dong D, Cheung AW, Chan SK, Cao Y, Mok PKH, Zhou L, Xu RH. Improving mental health literacy using web- or app-based interventions: A scoping review. Digit Health. 2024;10:20552076241243133.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGrace B, Wise LA, Nieroda M, Egbunike J, Usman NO. Digital health technologies to transform women's health innovation and inclusive research. BMJ. 2025;391:e085682.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBorges do Nascimento IJ, Abdulazeem HM, Weerasekara I, Marquez J, Vasanthan LT, Deeken G, Morgan R, Tan HL, Yordi Aguirre I, Osteengaard L, et al. Transforming women's health, empowerment, and gender equality with digital health: evidence-based policy and practice. Lancet Digit Health. 2025;7(6):100858.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCen C, Peng H, Li X, Zhang Z, Hu J, Wang Z, Jiang T. Interactive interfaces and wearable technologies for enhancing health management among older adults: a systematic review. Front Med (Lausanne). 2025;12:1724828.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKannan L, Lelo de Larrea-Mancera ES, Maniglia M, Vodyanyk MM, Gallun FJ, Jaeggi SM, Seitz AR. Multidimensional relationships between sensory perception and cognitive aging. Front Aging Neurosci. 2024;16:1484494.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoon J, Huh YL, Cho HY, Kim C, Lee H, Jang DP, Cho BH. Exploring Age-Related Patterns in Smartphone Keystroke Dynamics Considering Temporal Variability: Cross-Sectional Study With AI-Based Analysis. JMIR Mhealth Uhealth. 2025;13:e80094.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHicks JL, Althoff T, Sosic R, Kuhar P, Bostjancic B, King AC, Leskovec J, Delp SL. Best practices for analyzing large-scale health data from wearables and smartphone apps. NPJ Digit Med. 2019;2:45.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCarlozzi NE, Troost J, Lombard WL, Miner JA, Graves CM, Choi SW, Wu Z, Sen S, Sander AM. Completion and Compliance Rates for an Intensive mHealth Study Design to Promote Self-Awareness and Self-Care Among Care Partners of Individuals With Traumatic Brain Injury: Secondary Analysis of a Randomized Controlled Trial. JMIR Mhealth Uhealth. 2025;13:e73772.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDaniels K, Quadflieg K, Robijns J, De Vry J, Van Alphen H, Van Beers R, Sourbron B, Vanbuel A, Meekers S, Mattheeussen M et al. From Steps to Context: Optimizing Digital Phenotyping for Physical Activity Monitoring in Older Adults by Integrating Wearable Data and Ecological Momentary Assessment. Sens (Basel) 2025, 25(3).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKiang MV, Chen JT, Krieger N, Buckee CO, Alexander MJ, Baker JT, Buckner RL, Coombs G 3rd, Rich-Edwards JW, Carlson KW, et al. Sociodemographic characteristics of missing data in digital phenotyping. Sci Rep. 2021;11(1):15408.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCurrey D, Torous J. Increasing the value of digital phenotyping through reducing missingness: a retrospective review and analysis of prior studies. BMJ Ment Health 2023, 26(1).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCalvert E, Hackett K, Torous J, Giovannetti T. Barriers and facilitators to usability of a smartphone-based digital mental health tool in older adults: Insights from a secondary analysis of mindLAMP. Int Psychogeriatr 2025:100123.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDwyer B, Flathers M, Burns J, Mikkelson J, Perlmutter E, Chen K, Ram N, Torous J. Assessing Digital Phenotyping for App Recommendations and Sustained Engagement: Cohort Study. JMIR Form Res. 2024;8:e62725.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmagai S, Pila S, Kaat AJ, Nowinski CJ, Gershon RC. Challenges in Participant Engagement and Retention Using Mobile Health Apps: Literature Review. J Med Internet Res. 2022;24(4):e35120.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBot BM, Suver C, Neto EC, Kellen M, Klein A, Bare C, Doerr M, Pratap A, Wilbanks J, Dorsey ER, et al. The mPower study, Parkinson disease mobile data collected using ResearchKit. Sci Data. 2016;3:160011.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLipsmeier F, Taylor KI, Kilchenmann T, Wolf D, Scotland A, Schjodt-Eriksen J, Cheng WY, Fernandez-Garcia I, Siebourg-Polster J, Jin L, et al. Evaluation of smartphone-based testing to generate exploratory outcome measures in a phase 1 Parkinson's disease clinical trial. Mov Disord. 2018;33(8):1287\u0026ndash;97.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNoyce AJ, Bestwick JP, Silveira-Moriyama L, Hawkes CH, Knowles CH, Hardy J, Giovannoni G, Nageshwaran S, Osborne C, Lees AJ, et al. PREDICT-PD: identifying risk of Parkinson's disease in the community: methods and baseline results. J Neurol Neurosurg Psychiatry. 2014;85(1):31\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNoyce AJ, R'Bibo L, Peress L, Bestwick JP, Adams-Carr KL, Mencacci NE, Hawkes CH, Masters JM, Wood N, Hardy J et al. PREDICT-PD: An online approach to prospectively identify risk indicators of Parkinson's disease. \u003cem\u003eMov Disord\u003c/em\u003e 2017, 32(2):219\u0026ndash;226.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eParkinson\u0026rsquo;s Disease. Early Detection and Monitoring with KeySense [\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.parkinsons-research.org/index.htm]\u003c/span\u003e\u003cspan address=\"https://www.parkinsons-research.org/index.htm]\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eArora S, Baig F, Lo C, Barber TR, Lawton MA, Zhan A, Rolinski M, Ruffmann C, Klein JC, Rumbold J, et al. Smartphone motor testing to distinguish idiopathic REM sleep behavior disorder, controls, and PD. Neurology. 2018;91(16):e1528\u0026ndash;38.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLipsmeier F, Taylor KI, Postuma RB, Volkova-Volkmar E, Kilchenmann T, Mollenhauer B, Bamdadian A, Popp WL, Cheng WY, Zhang YP, et al. Reliability and validity of the Roche PD Mobile Application for remote monitoring of early Parkinson's disease. Sci Rep. 2022;12(1):12081.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMancini M, Horak FB. Potential of APDM mobility lab for the monitoring of the progression of Parkinson's disease. Expert Rev Med Devices. 2016;13(5):455\u0026ndash;62.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStamate C, Saez Pons J, Weston D, Roussos G. PDKit: A data science toolkit for the digital assessment of Parkinson's Disease. PLoS Comput Biol. 2021;17(3):e1008833.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEllis RJ, Ng YS, Zhu S, Tan DM, Anderson B, Schlaug G, Wang Y. A Validated Smartphone-Based Assessment of Gait and Gait Variability in Parkinson's Disease. PLoS ONE. 2015;10(10):e0141694.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKuosmanen E, Wolling F, Vega J, Kan V, Nishiyama Y, Harper S, Van Laerhoven K, Hosio S, Ferreira D. Smartphone-Based Monitoring of Parkinson Disease: Quasi-Experimental Study to Quantify Hand Tremor Severity and Medication Effectiveness. JMIR Mhealth Uhealth. 2020;8(11):e21543.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePepa L, Capecci M, Andrenelli E, Ciabattoni L, Spalazzi L, Ceravolo MG. A fuzzy logic system for the home assessment of freezing of gait in subjects with Parkinsons disease. Expert Syst Appl. 2020;147:113197.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBorz\u0026igrave; L, Olmo G, Artusi CA, Fabbri M, Rizzone MG, Romagnolo A, Zibetti M, Lopiano L. A new index to assess turning quality and postural stability in patients with Parkinson's disease. Biomed Signal Process Control. 2020;62:102059.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSu D, Liu Z, Jiang X, Zhang F, Yu W, Ma H, Wang C, Wang Z, Wang X, Hu W, et al. Simple Smartphone-Based Assessment of Gait Characteristics in Parkinson Disease: Validation Study. JMIR Mhealth Uhealth. 2021;9(2):e25451.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim H, Lee HJ, Lee W, Kwon S, Kim SK, Jeon HS, Park H, Shin CW, Yi WJ, Jeon BS, et al. Unconstrained detection of freezing of Gait in Parkinson's disease patients using smartphone. Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:3751\u0026ndash;4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMotolese F, Magliozzi A, Puttini F, Rossi M, Capone F, Karlinski K, Stark-Inbar A, Yekutieli Z, Di Lazzaro V, Marano M. Parkinson's Disease Remote Patient Monitoring During the COVID-19 Lockdown. Front Neurol. 2020;11:567413.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHabets J, Heijmans M, Herff C, Simons C, Leentjens AF, Temel Y, Kuijf M, Kubben P. Mobile Health Daily Life Monitoring for Parkinson Disease: Development and Validation of Ecological Momentary Assessments. JMIR Mhealth Uhealth. 2020;8(5):e15628.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLanders MR, Ellis TD. A Mobile App Specifically Designed to Facilitate Exercise in Parkinson Disease: Single-Cohort Pilot Study on Feasibility, Safety, and Signal of Efficacy. JMIR Mhealth Uhealth. 2020;8(10):e18985.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEllis TD, Cavanaugh JT, DeAngelis T, Hendron K, Thomas CA, Saint-Hilaire M, Pencina K, Latham NK. Comparative Effectiveness of mHealth-Supported Exercise Compared With Exercise Alone for People With Parkinson Disease: Randomized Controlled Pilot Study. Phys Ther. 2019;99(2):203\u0026ndash;16.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eButson CR, Tamm G, Jain S, Fogal T, Kruger J. Evaluation of Interactive Visualization on Mobile Computing Platforms for Selection of Deep Brain Stimulation Parameters. IEEE Trans Vis Comput Graph. 2013;19(1):108\u0026ndash;17.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pubh","sideBox":"Learn more about [BMC Public Health](http://bmcpublichealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pubh/default.aspx","title":"BMC Public Health","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Parkinson’s disease, Thailand, Digital interventions, Non-communicable diseases, Healthcare policy","lastPublishedDoi":"10.21203/rs.3.rs-8565015/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8565015/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eParkinson\u0026rsquo;s disease (PD) remains underdiagnosed in Thailand, and its rising prevalence presents a growing challenge for the healthcare system. The previously validated CheckPD digital population screening platform has been implemented nationally in collaboration with the Thai Red Cross Society (TRCS) and the National Health Security Office (NHSO), enabling integration of digital PD risk screening into preventive health frameworks.\u003c/p\u003e\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eTo evaluate the early phase of a national rollout of the CheckPD platform, focusing on population reach, usability, predictive performance, and implementation factors influencing adoption and scalability across diverse real-world settings.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThis mixed-methods implementation study undertaken in 10 screening provinces in Thailand was guided by the RE-AIM framework. Usability was assessed using the System Usability Scale (SUS) and task-completion metrics. AI-predicted PD risk was compared with diagnoses made by neurologists. Qualitative feedback was collected from Village Health Volunteers and Public Health Officers. Data storage and governance complied with Thailand\u0026rsquo;s Personal Data Protection Act of 2019.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eBetween January 2024 and October 2025, 13,381 out of 21,882 users completed screening across 10 provinces (completion rate: 72%). The mean SUS score was 83, with a 92% first-time task completion rate. Programme reach was achieved through multiple channels, including Village Health Volunteers (6,742 participants), community field campaigns (5,207), online training initiatives (3,172), and self-initiated app downloads (2,080). When compared with neurologists\u0026rsquo; diagnoses, the screening demonstrated a positive predictive value of 89.15%. Key facilitators of implementation included TRCS endorsement and network support, community volunteer engagement, and user-centred app design. Logistic regression analysis identified that barriers to completing the CheckPD app screening tests included a lower educational level and a more rural geographical location suggesting some disparities in access.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eThe CheckPD programme demonstrates that national-scale digital screening for neurological disorders is feasible in a low-to-middle-income country when embedded within trusted institutions, supported by community networks, and aligned with data protection standards. Thailand\u0026rsquo;s experience provides a scalable and replicable model for implementing population-level improvements in brain health by allowing early detection and assessment of those at individuals at risk, aligning with the World Health Organization\u0026rsquo;s Brain Health framework.\u003c/p\u003e","manuscriptTitle":"National implementation of a digital Parkinson’s disease screening programme in Thailand: reach, usability, and real-world performance of the CheckPD app","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-11 14:30:47","doi":"10.21203/rs.3.rs-8565015/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-30T07:16:48+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-25T07:23:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-11T21:41:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"45632059762015788471161927058162725796","date":"2026-02-27T07:19:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"151023775862872084656811864641015374880","date":"2026-02-09T15:31:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-09T14:45:29+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"125007214336589265745935031976171674731","date":"2026-02-04T14:35:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"240376981257280145902731747921056646620","date":"2026-01-26T15:48:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"45632059762015788471161927058162725796","date":"2026-01-22T06:47:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"45632059762015788471161927058162725796","date":"2026-01-22T04:07:16+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-22T03:10:02+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-13T08:39:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-12T08:41:02+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-12T08:39:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Public Health","date":"2026-01-10T02:06:02+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-public-health","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"pubh","sideBox":"Learn more about [BMC Public Health](http://bmcpublichealth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/pubh/default.aspx","title":"BMC Public Health","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b9799380-f0a8-4632-b02d-9471a31b815a","owner":[],"postedDate":"February 11th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-04-28T10:09:52+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-11 14:30:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8565015","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8565015","identity":"rs-8565015","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}