Evaluating the Usability and Practicality of AI-Enabled Smartphone-based Obstetric Ultrasound in Sierra Leone: A Mixed-Methods Study

Evaluating the Usability and Practicality of AI-Enabled Smartphone-based Obstetric Ultrasound in Sierra Leone: A Mixed-Methods Study | 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 Evaluating the Usability and Practicality of AI-Enabled Smartphone-based Obstetric Ultrasound in Sierra Leone: A Mixed-Methods Study Abu Dim Din Sesay, Amie Lompri Koroma, Anke van der Kwaak, Enya Seguin, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6710084/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Apr, 2026 Read the published version in BMC Pregnancy and Childbirth → Version 1 posted 14 You are reading this latest preprint version Abstract Background: In Sierra Leone, access to WHO-recommended obstetric ultrasound before 24 weeks of gestation is limited. The introduction of Artificial Intelligence (AI)-enabled smartphone-based obstetric ultrasound offers potential for improving accessibility and quality of maternal healthcare. This study, conducted in 2023, evaluates the usability, practicality, and sustainable adoption of this technology in the Tonkolili district, where it has been implemented as part of a pilot program since 2020. Methods: A mixed-methods approach was used, analyzing quantitative data from 2,315 obstetric scans performed by 81 healthcare providers across seven health facilities in Tonkolili district from October 2020 to March 2023. Data were analyzed using Stata version 17, applying a mixed-effects logistic regression model to identify factors influencing scan quality. Primary qualitative data were collected through interviews, focus group discussions, and observations with healthcare providers and clients. The Non-Adoption, Abandonment, Scale-up, Spread, and Sustainability (NASSS) framework informed the topic guide and guided qualitative analysis, which was conducted using NVIVO software. Results: The study revealed that 83.8% of obstetric scans were of sufficient quality for remote or AI analysis, with 59% of healthcare providers achieving the 80% threshold of sufficient quality scans, based on data distribution. Tutorial videos (OR: 14.1, 95% CI: 6.40-31.12, p < 0.001) and healthcare provider's skill sets were key factors in improving scan quality. The device was easily adopted by healthcare providers and well-received by clients. However, infrastructure limitations, supply chain issues, lack of comprehensive guidelines, and funding constraints were identified as barriers to its broader impact. Conclusion: AI-enabled obstetric ultrasound is a practical tool for healthcare providers in Sierra Leone. With the help of tutorial videos, healthcare providers were able to perform quality scans despite varying skill levels. The device’s simplicity and ability to produce clear, analysable scans make it a valuable tool for improving maternal healthcare at the PHC level. However, challenges remain, including the need for more comprehensive training, better integration of ultrasound findings into broader care, and infrastructure improvements. Addressing these barriers and ensuring proper guidelines will enhance its effectiveness in improving maternal and child health outcomes. Maternal health Antenatal care Obstetric ultrasound Artificial Intelligence Sufficient Quality Task shifting Healthcare provider Sierra Leone Figures Figure 1 1. Background Obstetric ultrasound plays a crucial role in Antenatal Care (ANC), allowing healthcare providers to assess factors such as gestational age, fetal growth, placental function, and the presence of anomalies or complications. This information is vital for making informed decisions about pregnancy management. Due to the importance of ultrasound, the World Health Organization (WHO) recommends that all pregnant women receive one early ultrasound before 24 weeks of gestation ( 1 ). Despite these recommendations, Low- and Middle-Income countries (LMICs) lag far behind in utilizing ultrasound. Limited resources lead to a shortage of ultrasound equipment and trained personnel ( 2 ), while unreliable access to electricity and internet connectivity further hinders the implementation and sustainability of digital solutions ( 3 , 4 ). In Sierra Leone, many government facilities lack ultrasound equipment and trained sonographers. A Rapid Emergency Obstetric and Newborn Care (EmONC) Assessment Report from 2017 stated that ultrasound machines were available in only 53% of district hospitals and recommended equipping all district hospitals with functional machines, along with providing appropriate training for their maintenance ( 5 ). Global studies have shown that obstetric scans can be effectively performed with minimal training using the “Obstetric Sweep Protocol” ( 6 – 10 ). A study in Peru found that after eight hours of training, users achieved over 95% accuracy in key obstetric assessments, such as fetal count, presentation, and placental position ( 9 ). This approach has the potential to make ultrasound more accessible and aligns with WHO recommendations on task shifting ( 11 ). While evidence on the impact of hand-held ultrasound devices remains limited for Sierra Leone, studies in other LMICs suggest that integrating point-of-care ultrasound into routine ANC improves clinic attendance. A cohort study in Tanzania reported a rise in the percentage of women attending four or more ANC visits (from 27.2–60.3%; p = 0.001) ( 12 ). Artificial Intelligence (AI) is being used in ultrasound technology to help healthcare providers make faster and more accurate pregnancy-related diagnoses, especially in low-resource settings ( 6 , 13 – 20 ). This study evaluated the usability, practicality, and adoption of an Artificial Intelligence (AI) enabled portable ultrasound device that has been piloted in Tonkolili district since 2020. 1.1 Description of the device The piloted tool is a smartphone-based ultrasound device and software (Fig. 1 ) designed to improve access to obstetric imaging in low-resource settings. The device requires a probe and gel for scanning and employs the "Obstetric Sweep Protocol," to produce images that can be used for remote analysis or AI to estimate gestational age, detect multiple pregnancies, determine placental location, and assess fetal position ( 21 ). The device is portable and easy to use, requiring approximately one hour of training for healthcare providers. It operates offline for scanning but requires internet access for healthcare providers to upload scans for remote analysis by ultrasound professionals and to receive the results. An AI-enabled version was introduced in 2023, enabling automatic mobile application analysis and delivering results within seconds. Using a traffic light system, the device alerts users to potential obstetric risks and the need for referral. 1.2 Pilot Implementation of the Device in Sierra Leone In 2020, a pilot program introduced the device in Gbonkolenken Chiefdom, Tonkolili District, Sierra Leone. Seven portable ultrasound devices were deployed across six peripheral health facilities, chosen for their proximity to the referral hospital. The goal of the pilot was to assess the device’s effectiveness in resource-limited primary care settings for early detection of pregnancy complications. The pilot had two phases: Phase 1 introduced the device at a referral hospital during ANC visits; providers were trained and women received free scans. Phase 2 focused on usability and practicality by healthcare providers at the primary healthcare level including Community Health Officers (CHOs), Community Midwives, Community Health Assistants (CHAs), State-Enrolled Community Health Nurses (SECHNs) and Maternal and Child Health Aides (MCHAs). 2. Methods Study design The study, conducted in 2023, employed a mixed-methods approach to evaluate the usability, practicality, and long-term adoption of a smartphone-based AI-enabled obstetric ultrasound device in Sierra Leone. Data from 2,315 obstetric scans performed by 81 healthcare providers across seven facilities in Tonkolili district between October 2020 and March 2023 were analyzed to assess healthcare providers' scanning performance and factors influencing scan quality. Additionally, to explore factors affecting the sustainable implementation and adoption of the device in the district, qualitative data were collected through interviews, focus group discussions, and observations with healthcare providers, clients, and key informants, guided by the Non-adoption, Abandonment, Scale-up, Spread, and Sustainability (NASSS) framework. A. Quantitative method Data source Electronic scanning records from pregnant women who underwent obstetric scans using the smartphone-based device between October 2020 and March 2023 were analyzed. Data included client ID, healthcare provider ID, scan date/time, app version, facility type, and scan quality. The dataset captured more variables such as the reason for insufficient quality scan, fetus count, etc., which are not used in this study. A separate database captured healthcare provider characteristics such as gender, staff cadre, and facility affiliation. The seven participating facilities included one Community Health Post (CHP), three Community Health Centers (CHC), two Maternal and Child Health Posts (MCHP), and one hospital. Key Variables The primary outcome variable was scan quality, categorized as sufficient quality (scans with clear images that could be analysed for the specified parameters) and insufficient quality (scans with poor image quality that were inadequate for analysis, often due to suboptimal user performance). Independent variables included scan frequency (categorized into experience levels), healthcare provider cadre (grouped into skill levels), facility type, and app version. App versions were broadly classified into those with or without tutorial videos, where tutorial-equipped versions intended to enhance provider performance. Quantitative data analysis Data were exported to Stata version 17 for analysis. Descriptive statistics characterized healthcare providers and scan quality distributions, while categorical variables were summarized using frequencies and percentages. A mixed-effects logistic regression model was used to assess factors influencing scan quality, including scan frequency, app version, healthcare provider cadre, and facility type. Initial bivariate logistic regression was followed by a multivariate regression model to adjust for confounders. Due to multicollinearity, app version was omitted from the final model as it was strongly associated with facility type. The models calculated (adjusted) odds ratios ((a)OR), 95% confidence intervals (CI), and p-values to determine the significance of the associations, using a significance level of p < 0.05. A subgroup analysis assessed the effectiveness of app versions with tutorial videos on scan quality for first-time users. This helped to account for experience as a potential confounding factor. B. Qualitative method Study Population and Sampling The qualitative component included six in-depth interviews (IDIs) with frontline healthcare providers, three key informant interviews (KIIs) with hospital and DHMT staff, and two focus group discussions (FGDs) —one with six healthcare providers and another with six female clients (pregnant, and lactating women) who underwent obstetric scans with the device. Additionally, participant observations were conducted during the practices of three healthcare providers. Purposive sampling was used for IDIs and KIIs, while FGDs followed a convenience sampling approach. Clients were selected from records based on experiences within the past three months to minimize recall bias. Theoretical framework The study applied the (NASSS) framework developed by Greenhalgh et al. (2017) (22), which guided the development of the topic guide and analysis. This study focused on all seven main domains and 19 of the 24 subdomains, ensuring a comprehensive exploration of factors influencing adoption and sustainability. Data collection Data collection took place over seven days (June 15-21, 2023) in Tonkolili district. Semi-structured topic guides were used for KIIs, IDIs, and FGDs, as detailed in the Research Table (Appendix A). KIIs were conducted in English, while IDIs and FGDs were held in the local Creole language. KIIs and IDIs lasted approximately 45 minutes, while FGDs ranged from 60–75 minutes. The data collection techniques are summarized in Table 1: Table 1 : Data collection procedures Procedure Number Participants Research Issues Explored Key Informant Interviews (KIIs) 3 DHMT staff: 2 Hospital management: 1 Roles in the pilot, policy decisions, and perspectives on the pilot and device implementation. In-Depth Interviews (IDIs) 6 Healthcare providers (e.g. nurses, midwives, CHO): 6 Experiences with the device, including usability, perceived effectiveness, and challenges faced during use. Focus Group Discussions (FGDs) 2 groups (12 participants) Healthcare providers: 1 group (6 participants) Clients: 1 group (6 participants) Barriers, facilitators, and overall influences related to device usage. Participatory Observation Healthcare providers performing scans on pregnant women: 3 Real-time interactions with clients, explanation of procedures, communication of diagnoses, referral and next steps. Data analysis Audio recordings were manually transcribed and translated from the local vernacular to English. Anonymized transcripts were coded and analyzed in NVIVO software (version 14) using a coding framework. Thematic coding was conducted deductively (using predefined NASSS categories) and inductively (creating new codes as needed). Ethical considerations Ethical approval was obtained from KIT Tropical Institute (reference S-208) and the Sierra Leone Ethics and Scientific Review Committee (reference 001/06/2023). Informed consent was obtained from all participants, ensuring understanding of research procedures, potential risks, and benefits, with the opportunity to withdraw voluntarily. To ensure anonymity and confidentiality, all personally identifiable data were coded and securely stored on password-protected devices. Only the researchers had access to the passwords. The data will be kept confidential for one year before being disposed of. 3. Results 3.1 Description of Study Participants Among the 81 healthcare providers who conducted scans 57% were female, while 33% (27 of 81) had missing gender data. Despite this, these missing values accounted for only 1.2% of the total scans conducted (27 of 2,315), suggesting minimal impact on the overall findings. In terms of professional roles, MCHAs constituted a significant proportion, making up 26% (21 of 81) of healthcare providers but contributing to 43.6% of all scans performed. SECHNs represented 9% (7 of 81), performed 19.5% (452 of 2,315) of the scans (Table 2). For the interviews with 24 healthcare providers, the majority (19 of 24) were female. Educational backgrounds among healthcare providers varied, with 4 having tertiary education, 14 having secondary education, 2 with primary education, and 4 with no formal education. Clients also had diverse maternal experiences, with five having prior childbirth experience, while one was experiencing her first pregnancy. 3.2 Scanning Performance A total of 2,315 scans were conducted between October 2020 and March 2023, with a median of 8 scans per healthcare provider (IQR: 36). Among these, 83.8% were of sufficient quality for remote or AI analysis, while 16.2% were considered insufficient. Notably, 59.3% of healthcare providers achieved an 80% or higher rate of sufficient-quality scans, meeting the predefined threshold. Midwife students and Community Health Assistants had the lowest percentages of high-quality scans, with 70.7% (29 of 41) and 72.3% (73 of 101) of their scans deemed sufficient, respectively. The findings also revealed disparities across healthcare facilities. At one CHC, 17.3% (14 of 81) of the healthcare providers performed the highest number of scans, accounting for 28.6% (663 of 2315) of the total. The best scan quality, with 92.3% of its scans rated as sufficient, was found at one of the MCHPs. In contrast, the referral hospital had the largest number of healthcare providers (35.8%) but conducted the fewest scans (3.5%) and had the lowest quality, with only 43.2% of scans meeting the sufficient quality standard. A closer look revealed that the vast majority (26 of 29) of healthcare providers at this hospital had used the device only once. The descriptive characteristics of healthcare providers and scans conducted are shown ( Table 2). Table 2: Descriptive characteristics of healthcare providers and scans conducted Characteristics Healthcare providers N=81 Number of scans (N=2,315) Scans of sufficient quality n % n % n % Sex of healthcare provider: Female 46 56.8 1,897 81.9 1602 84.4 Male 8 9.9 391 16.9 328 83.9 Missing 27 33.3 27 1.2 10 37.0 Healthcare provider cadre: CHOs 3 3.7 231 10.0 202 87.5 Midwives 4 4.9 154 6.6 133 86.4 CHAs 3 3.7 101 4.3 73 72.3 SECHNs 7 8.7 452 19.5 369 81.5 MCHAs 21 25.9 1,011 43.6 862 85.3 Student CHOs 1 1.2 22 1.0 18 81.8 Student midwives 3 3.7 41 1.8 29 70.7 SRNs 3 3.7 145 6.3 128 88.3 Student MCHAs 1 1.2 8 0.4 8 100.0 TBAs 4 4.9 42 1.8 41 97.6 CHVs 4 4.9 81 3.5 67 82.7 Missing 27 33.3 27 1.2 Health facility: LHMC 29 35.8 81 3.5 35 43.2 Yele CHC 14 17.3 663 28.6 584 88.1 Mayepoh CHC 18 22.2 558 24.1 472 84.6 Manowo CHC 6 7.4 515 22.2 422 81.9 Mansumana CHP 6 7.4 239 10.3 192 80.3 Petifu Mayepoh MCHP 4 4.9 129 5.6 119 92.3 Warema MCHP 4 4.9 130 5.6 116 89.2 App capability (tutorial videos): With tutorial videos 2,234 96.5 1,905 85.3 Without tutorial videos 81 3.5 35 43.2 Frequency of scan: 1st scan 81 3.5 56 69.1 2nd-10th scans 416 18.0 337 81.0 11th-30th scans 549 23.7 457 83.2 31st-50th scans 379 16.4 317 83.6 51st-100th scans 444 19.2 384 86.5 101st & above scans 446 19.3 389 87.2 Total number of scans One scan 27 33.3 27 1.2 10 37.0 2-10 scans 16 19.8 90 3.9 69 76.7 11-30 scans 16 19.8 269 11.6 219 81.4 31-50 scans 7 8.6 289 12.5 234 81.0 51-100 scans 9 11.1 594 25.7 508 85.5 101 & above scans 6 7.4 1046 45.2 900 86.0 Quality of scan Scans with sufficient quality 1,940 83.8 Scans insufficient quality 375 16.2 3.3 Factors Associated with Sufficient Scan Quality The results of the bivariate and multivariate analyses for factors associated with obtaining scans of sufficient quality are presented in Table 3. Bivariate analysis revealed a significant positive association between using an app with tutorial videos and obtaining sufficient-quality scans (OR: 14.1, 95% CI: 6.40–31.12, p < 0.001). However, the app variable was excluded from the multivariate analysis due to multicollinearity with health facility types. In a subgroup analysis of first-time app users, control for experience as a confounder (Table 4), the association remained significant (OR: 12.2, 95% CI: 4.11–36.32, p < 0.001). Primary health facilities (CHCs, CHPs, MCHPs) had significantly higher odds of obtaining scans of sufficient quality compared to the hospital. Specifically, MCHPs demonstrated the highest odds of sufficient scan quality (aOR: 46.1, 95% CI: 11.19-189.97, p < 0.001). Medium-skilled (aOR: 0.28, p = 0.004), low-skilled with formal training (aOR: 0.32, p = 0.004), and very low-skilled workers in training (aOR: 0.34, p = 0.020) had lower odds of obtaining sufficient-quality scans compared to high-skilled workers. While scan frequency was linked to quality in bivariate analysis, no significant associations were found in multivariate analysis. Table 3: Factors associated with obtaining scans of sufficient quality (Fixed effects output) Bivariate analysis ( N obs= 2,315 & N groups= 81 ) Multivariate analysis (N obs=2,288 & N groups =54) Factor OR 95% CI P-value aOR 95% CI P-value App capability Without tutorial video 1 With tutorial video 14.1 6. 40-31.12 <0.001*** Staff cadre a High skilled 1 Medium skilled 0.4 0.14-1.16 0.091 0.28 0.11-0.66 0.004** Low skilled with formal training 0.6 0.22-1.59 0.301 0.32 0.15-0.70 0.004** Very low skilled in training 0.6 0.18-1.86 0.356 0.34 0.14-0.85 0.020* Low skilled without formal training 0.95 0.27-3.35 0.937 0.39 0.13-1.15 0.089 Health Facility type Hospital 1 CHCs 12.7 5.86-27.65 <0.001*** 19.3 5.90-63.07 <0.001*** CHPs 9.1 3.44-23.89 <0.001*** 18.4 4.61-73.30 <0.001*** MCHPs 28.5 10.11-80.37 <0.001*** 46.1 11.19-189.97 <0.001*** Frequency of scan: 1st scan 1 2nd-10th scans 2.1 1.18-3.76 0.012* 0.99 0.46-2.13 0.971 11th-30th scans 2.4 1.35-4.35 0.003** 1.13 0.52-2.43 0.759 31st-50th scans 3 1.60-5.60 0.001** 1.40 0.63-3.12 0.411 51st-100th scans 2.7 1.45-5.13 0.002** 1.27 0.57-2.83 0.556 101st & above scans 3.4 1.74-6.54 <0.001*** 1.54 0.68-3.50 0.304 a missing 27 (33.3%) healthcare providers * Significant at p-value < 0.05 **Significant at p-value < 0.01 *** Significant at p-value < 0.001, cOR =Crude Odds Ratios, aOR =adjusted Odds Ratios, N obs =Number of observations, N groups =Number of groups of healthcare providers. Please note that the reduced number of observations to 2,288 and healthcare provider’s groups to 54 in the multivariate analysis is attributable to missing values within the “staff cadre” variable. Table 4: Sub-group analysis of first-time users of each category of the app version Bivariate analysis (N=81) Factor Total scans Sufficient quality scans OR 95% CI P-value App capability Without tutorial videos 29 9 31.0 1 With tutorial videos 52 44 84.6 12.2 4.11-36.32 <0.001 Qualitative findings under the NASSS domains The qualitative analysis identified eight themes, of which seven aligned with the NASSS framework including condition, technology, value proposition, adopters, organization, wider system, embedding and adaptation over time. One additional theme, focusing on Quality of care, emerged and was explored separately (see Appendix C ). 3.4 The Condition The domain of condition examines knowledge, perceptions, and sociocultural values on obstetric ultrasound use. Healthcare providers and key informants acknowledged its role in detecting high-risk pregnancies, while clients expressed satisfaction with its ability to ensure maternal and fetal well-being. Women also viewed hospital referrals as indicators of priority cases. However, concerns also emerged regarding over-reliance on the device, potentially diminishing fundamental skills like physical examination and communication: “The scan works so well that now, we are super attached to it. I am worried that we are depending on it for almost everything. What happens if it gets faulty or is not available? We are losing our skills in the process” (IDI with healthcare provider). The risk of abandoning conventional diagnostic methods was evident in findings that showed physical examinations were frequently omitted during routine check-ups. Some healthcare providers reported that the device aided in identifying additional conditions, such as Sexually Transmitted Infections (STIs), by allowing them to detect vaginal odors during abdominal scans. Although this was described as an unexpected benefit of using the device, such diagnoses should have been possible through proper physical examination "We can smell vaginal odor during the scan process and perform further examinations. The scan helps us to be proactive" (IDI with healthcare provider). Sociocultural factors were reported to pose minimal barriers, as the scan’s perceived accuracy fostered widespread community acceptance. This trust encouraged healthcare engagement and compliance with referrals, often reinforced by local leaders. Women appreciate machines more than our manual hands. There is high community acceptance” (KII with DHMT Staff). “When women refuse referrals, chiefs step in, and they comply” (IDI with healthcare provider). Despite widespread acceptance of ultrasound, some women reported limited emotional support from their male partners. While financial contributions were common, emotional involvement was less evident. Many women described this lack of engagement as reflective of cultural norms that frame maternal health as solely a woman’s responsibility. “He (Partner) gives me money for the hospital but never willingly accompanies me unless the nurses request it” (FGD with Client). 3.5 The Technology This section highlights healthcare providers' experiences with the device, focusing on its user interface, efficiency, and feasibility at the primary healthcare (PHC) level. Healthcare providers found the device easy to use, aided by smartphone familiarity and tutorial videos. Instant results were valued, facilitating timely care and referrals, with the traffic light system proving useful in risk categorization. “We find it easy to perform the six sweeps as videos are displayed, and we just follow the visual directions… because it’s a machine, it’s easier to use” (FGD with healthcare providers). Healthcare providers found it easy to integrate the device into their routines, improving their diagnostic skills and contributing to better overall care delivery . They also noted reduced workloads and faster diagnoses, freeing up time for other duties and enhancing overall performance. “It was easy to integrate into our routine. We trained colleagues, and everyone in the maternity unit can use the device well” (IDI with healthcare provider). “The scan reduces the time spent on listening for a fetal heartbeat and determining gestational periods, which are difficult to do manually” (IDI with healthcare provider). However, despite claims of reduced workload, observations revealed that healthcare providers were often overwhelmed due to high demand for ultrasounds. At least 60 pregnant women per day attended an ANC clinic per facility, and all underwent scans, regardless of having had a recent scan. With a maximum of three staff per primary health facility, the healthcare provider-to-client ratio stood at 1:23, far exceeding the global standard of 1:5. The increased utilization of the technology has highlighted a staffing shortfall that the device alone cannot resolve. 3.6 The Perceived Value This component explores participants’ perspectives on the device’s importance, emphasizing its intrinsic benefits and broader impact. Obstetric ultrasound availability was mentioned to increase ANC attendance and facility deliveries. This surge has facilitated the implementation of other health interventions, such as immunizations and malaria screenings. “Pregnant women are coming for scans, and this indirectly helps in strengthening other ANC services like TT (Tetanus Toxoid) and malaria checks” (IDI with healthcare provider). The device was believed to reduce maternal and fetal deaths, by improving diagnostic accuracy and enabling early identification of high-risk pregnancies. Healthcare providers highlighted its role in mitigating misdiagnosis, particularly by empowering lower-cadre staff to enhance their diagnostic skills through hands-on use. “Misdiagnosis was common, but the scan enables volunteers and lower cadre staff to self-train and improve skills” (IDI with healthcare provider). Clients also noted that the scan helped alleviate fears about potential health risks and increased their trust in diagnoses. “Many women have died or had stillbirths without knowing it. But since the scan, we haven’t heard of such cases” (FGD with Clients). However, while participants reported reduced mortality, these claims were difficult to verify due to a lack of clinical record audits. Additionally, improvements may stem from broader health interventions like health education campaigns, making it challenging to isolate the specific impact of the device. Healthcare providers observed increased client engagement, noting that obstetric ultrasound empowered women to take a more active role in healthcare decisions. However, they also acknowledged a critical gap in interpersonal care. Many women seek empathy, respect, and emotional support—needs that are often unmet due to time constraints, limited training in client-centered care, and broader systemic challenges. Addressing this gap is crucial, as emotional support significantly influences client satisfaction and adherence to care. 3.7 Adopters For the factors shaping the adoption and implementation of the device, healthcare providers credited the device’s ease of use and tutorial-based training for its successful adoption. The device was described as user-friendly, practical, easy to operate and improved access and early referrals at primary care levels. However, overall staff education levels were cited as a challenge. While basic device use was easy to learn, interpreting results and linking them to clinical actions required more advanced midwifery and obstetric knowledge. This skills gap risked misdiagnosis and reduced the device’s potential benefits. “My technical background as a midwife helps me link the result with the woman’s overall health" (IDI with healthcare provider). Clients' decisions to undergo scans were influenced by socioeconomic factors, including transportation issues, illiteracy, high costs at advanced facilities, the challenge of leaving other children behind, and anxiety about referrals. While some clients were discouraged by these barriers, others were motivated by the knowledge gained from a diagnosis, prompting them to seek care to protect their health and that of their babies. 3.8 Organizational Factors This domain delves into the infrastructure and funding requirements necessary for integrating health technologies within health facilities. Findings revealed an urgent need to improve primary health facilities infrastructure nationwide, especially for power and internet connectivity. Currently, health facilities depend heavily on intermittent support from development partners, who provide temporary access to solar energy and internet services. However, sustainable solutions for electricity and network connectivity have not yet been established by the government. Primary health facilities in the pilot program benefited from donor-supported infrastructure, such as electricity and internet, but many others across the country lack these resources. Both healthcare providers and clients expressed dissatisfaction with the health system despite the free healthcare initiative, citing issues such as shortages of life-saving drugs and poorly lit delivery rooms. “The clinics need more medication for maternity. Nurses tell us we need more care, but most times there is no medication for treatment” (FGD with Clients). Furthermore, barriers such as stockouts and the lack of necessary medical supplies, particularly gel for scanning, were also identified. Since gel is not included in routine health supplies, providers were often forced to ask clients to purchase supplies, adding financial strain. Insufficient examination beds exacerbated workloads and contributed to delays. “ With such a huge workload, we need at least 2 beds for scans and general assessments” (IDI with healthcare provider). Limited funding remains a major challenge for investing in innovative healthcare technologies. Sierra Leone’s dependency on donors raises concerns about the scalability and sustainability of technologies. Although the device is more affordable than traditional ultrasound machines, its annual subscription fee poses a financial burden. Efforts to scale the program are further complicated by local councils' tendency to prioritize administrative and personnel expenses over recurring technology costs. 3.9 Wider System Factors This segment explores how policy gaps, socio-economic factors, and cultural norms affect digital health use. Healthcare Providers highlighted the absence of clear guidelines on obstetric ultrasound, leading to inconsistent practices like frequent, unnecessary scans. This strained resources, increased workload, and diverted attention from high-need cases. Clear protocols on scan frequency were seen as vital for improving efficiency and care quality. “We need guidelines to know, for example, the maximum number of scans a woman need before delivery and the frequency of scans. Now we are scanning randomly.” (IDI with healthcare provider) Corruption and inconsistent service fees were significant barriers for clients. Many reported experiencing preferential treatment, bribery, and inconsistent charges for services meant to be free. Some were even denied scans unless they paid, undermining trust in the healthcare system and placing a financial burden on struggling families. “Payment is also discriminatory. Some women pay, while others don’t for the same service. If you don’t pay, they’ll say the device isn’t available and refer us to the hospital, even if it’s unnecessary” (FGD with Clients). Despite these challenges, clients trusted the obstetric ultrasound results, appreciating its clear and consistent diagnoses, which boosted their confidence in their baby’s health and healthcare providers, contrasting with previous experiences of conflicting diagnoses. 3.10 Embedding and Adaptation Over Time. This domain underscores the role of key stakeholders in creating an environment conducive to long-term technology adoption. Key informants reported limited involvement in national decision-making and identified structural and systemic gaps that hinder adaptation. These include the lack of a viable market for medical equipment, insufficiently trained biomedical engineers, and inadequate financial commitment from the government and other stakeholders. A lack of coordination among stakeholders in tailoring digital health technologies to Sierra Leone's context was a critical barrier. Previous attempts to introduce similar technologies failed due to digitalization challenges and low digital literacy. Financial sustainability was also a concern, particularly with technologies requiring ongoing subscription fees. “Allocating the budget for the procurement of some BabyCheckers is something to consider in the annual district health budget and planning, but in the case of the BabyChecker device, a yearly subscription fee adds to the funding and sustainability concerns” (KII with DHMT Staff). Despite these challenges, stakeholders expressed optimism about the device's potential to address Sierra Leone's high Maternal Mortality Ratio (MMR). However, they stressed the need for further research to secure buy-in from the Ministry of Health and Sanitation (MoHS) and ensure scalable implementation. “BabyChecker is good for the SL context that has high MMR. As a senior staff, I have a buy-in as I have seen the improvements in the piloted chiefdom. However, more research is needed to get buy-in from the MoHS to scale up” (KII with DHMT Staff) 3.11 Quality of Care Quality of care emerged as a major concern across all domains, especially regarding the duration of ANC examinations. On average, only 3–5 minutes were spent per client for both ANC assessments and scanning, far below the 30-40 minutes standard recommended by the focused ANC model (11,23). This limited time reduced care quality and led to client dissatisfaction. The rushed nature of examinations left little opportunity for healthcare providers to offer essential education, counseling, and feedback. Clients expressed frustration with the lack of communication and support. "No counseling was done before or after the scan. We assume the baby is fine if we don’t hear anything from the nurse. If your baby is not well, the nurse will refer you" (FGD with Client). Moreover, observations revealed lapses in privacy and consent. Clients’ upper bodies were unnecessarily exposed during observations, and consent was rarely obtained. Such practices undermine patient dignity and trust. High patient volumes worsened these problems, as healthcare providers seemed to prioritize efficiency over quality. Discussion The study shows that healthcare providers with varying skill levels can perform quality scans in resource-limited settings, indicating that diagnostic imaging can be decentralized to lower-level healthcare workers. This could expand access to essential maternal and fetal health services in underserved areas. The finding that mid- and lower-skilled providers can achieve reasonable scan quality supports the scalability of ultrasound use in resource-constrained environments, especially where skilled radiologists or sonographers are scarce. However, despite overall promising scan clarity, the low-quality threshold among medium- and lower-skilled providers suggests significant variations in performance, potentially due to differences in experience. The higher quality scans at MCHPs compared to higher-level primary facilities like CHCs and CHPs may be due to MCHPs’ focus on maternal and child health. Healthcare providers at MCHPs are likely more familiar with pregnancy and palpation techniques, and their lower patient volumes might allow for more time and attention per patient, potentially improving scan quality. The device’s user-friendly design and tutorial videos that support independent learning enable task shifting, allowing less specialized workers to perform tasks traditionally reserved for highly trained clinicians. Such task shifting has been recognized as a potential solution to address the limited availability of specialized clinicians and diagnostic infrastructure in LMICs (24) and is also consistent with WHO recommendations on ultrasound and task-shifting (25). However, successful integration requires more than technical training, necessitating a broader focus on healthcare delivery. The analysis suggests that, with proper training and support, even less experienced healthcare providers can perform quality ultrasound scans in resource-limited settings. Similar studies show that targeted training enables individuals with no prior ultrasound experience to conduct basic obstetric scans effectively (26–32). Clients' acceptance of ultrasound services has the potential to positively influence ANC attendance and facility deliveries, which could lead to improved maternal and fetal outcomes. Several studies have shown that ultrasound services increase the frequency of ANC visits (12,33). Rising ANC attendance could also facilitate the integration of other maternal and child health interventions like immunizations, malaria screenings, and health education. However, while these preliminary findings are promising, further research is needed to explore the long-term impact of obstetric ultrasound on maternal health outcomes. Key considerations include sustained ANC attendance beyond initial visits, potential scan overuse, and the broader implications of technology-driven care on clinical decision-making. While participants believed the device could reduce maternal and fetal mortality through early detection and referrals, verifying this is difficult without systematic record audits. Thus, evaluating ultrasound’s effectiveness requires a broader look at maternal and neonatal health indicators. While providers confidently integrated ultrasound into ANC, there was a tendency to over-rely on the device, sometimes at the expense of essential clinical procedures such as physical examinations and vital sign checks. This substitution of comprehensive care may have been influenced by the absence of clear and standardized guidelines, a concern echoed in previous studies reporting the omission of fundamental clinical procedures when ultrasound is available (34,35). Although community acceptance of the technology was high, overuse risks diminishing core clinical skills and straining already limited resources. Moreover, while the device is user-friendly, some healthcare providers, particularly those with lower formal education, faced challenges integrating the results of the device into broader maternal and child health (MCH) service delivery, potentially affecting the consistency and quality of care. These challenges are further compounded by broader system-level barriers, including unreliable power supply, poor internet connectivity, supply chain inefficiencies, and a lack of infrastructure, obstacles also identified in other research (36,37). Additionally, despite WHO and Sierra Leone’s ANC guidelines emphasizing the importance of thorough physical examinations, these are often overlooked unless clients report symptoms, which can compromise accurate diagnosis and the complementary role of obstetric ultrasound. Patients in other studies have also highlighted the need for adequate consultation time and comprehensive assessments during ANC visits (38,39). Addressing these gaps requires investment in both health system infrastructure and provider training that goes beyond technical device operation. Digital health tools like ultrasound should complement, not replace, established medical practices and patient-centered care protocols. A holistic approach that balances technological integration with clinical judgment is essential to ensure the delivery of high-quality maternal healthcare. Though the device may ease provider workloads, concerns about corruption and inequitable access persist, underscoring the need for stronger governance and accountability. Funding, particularly for PHC, emerged as a critical factor affecting the DHMT's performance to provide essential services, maintain medical supplies, and support healthcare providers effectively. Despite global calls for increased PHC funding, including the Lancet Global Health Commission’s recommendations (40), the study highlights that underfunding continues to exacerbate inequities in healthcare access, disproportionately affecting lower-income populations. A key limitation of this study is that the quantitative data were collected during the pilot phase, rather than within a structured study setup. As a result, the research had to work with the available data, which presents challenges for data interpretation and generalizability. This highlights the need for more rigorous data collection in future implementation research. Conclusion This study shows that AI-enabled obstetric ultrasound technology is a practical and usable tool for healthcare providers in Sierra Leone. Despite varying skill levels, providers were able to perform quality scans linked to the device’s user-friendly design and tutorial videos, which supported independent learning and task shifting. The device's simplicity and ability to produce clear, analysable scans make it a viable solution for primary healthcare settings with limited access to specialized care. However, challenges remain, including the need for more comprehensive training, better integration of ultrasound findings into broader maternal care, and overcoming infrastructure issues like unreliable power and inadequate supplies. Addressing these challenges, along with establishing appropriate guidelines for device use, could enhance its effectiveness and improve maternal and child health outcomes. While further research and infrastructure investment are necessary for scaling, the findings demonstrate that the device is a valuable tool for improving obstetric care in resource-limited environments. Declarations Ethics approval and consent to participate: Ethical approval was obtained from KIT (reference S-208) and the Sierra Leone Ethics and Scientific Review Committee (reference 001/06/2023). Informed consent was obtained from all participants, ensuring understanding of research procedures, potential risks, and benefits, with the opportunity to withdraw voluntarily. Consent for publication: Participants provided consent for the publication of findings. Availability of data and materials: Data sharing is restricted due to confidentiality agreements. Access to anonymized data may be available upon request and approval from the relevant authorities. Competing interests: The study received no external funding. However, the study received support from Delft Imaging for data collection but remains impartial. Funding: No direct financial support was provided for this research. Authors' contributions: Amie Lompri Koroma (ALK) and Abu Dim Din Sesay (ADS) served as the lead researchers, overseeing the entire processes of the study including data collection and analysis. Irene de Vries (IV), Mirjam Bakker (MB), and Anke van der Kwaak (AvdK) supervised the study from conceptualization to the presentation of findings, providing technical support and capacity-building assistance. Alhassan Kanu (AK) supported the review and validation of the findings whilst Abdul Mac Falama (AMF) was involved in the implementation. AMF also played a key role in the pilot project's implementation as the district medical officer of Tonkolili DHMT, where the project was conducted. Enya Sequin contributed valuable insights into the device and its pilot implementation in Tonkolili district, provided access to the quantitative data. ALK and ADS drafted the original manuscript, which underwent multiple rounds of review and editing by IV, MB, AvdK, AK, AMF, and ES, who also provided critical feedback on the advanced versions. All authors reviewed and approved the final manuscript. Acknowledgements The authors extend their sincere appreciation to the healthcare providers, pregnant and lactating women, and staff members of the Tonkolili District Health Management Team in Sierra Leone for their invaluable contributions to this study. We acknowledge Delft Imaging for funding the transportation costs during the primary data collection phase. References WHO Antenatal Care Recommendations for a Positive Pregnancy Experience. Maternal and Fetal Assessment Update: Imaging Ultrasound Before 24 Weeks of Pregnancy. 1st ed. Geneva: World Health Organization; 2022. 1 p. Destigter K, Morey G, Garra B, Rielly M, Anderson M, Kawooya M, et al. Low-Cost Teleradiology for Rural Ultrasound. In 2011. p. 290–5. Chukwu E, Garg L, Foday E, Konomanyi A, Wright R, Smart F. Electricity, Computing Hardware, and Internet Infrastructures in Health Facilities in Sierra Leone: Field Mapping Study. JMIR Med Inform. 2022 Feb 3;10(2):e30040. International Telecommunication Union Development Sector. Measuring digital development Facts and figures 2020.FactsFigures2020.pdf [Internet]. [cited 2024 Nov 3]. Available from: https://www.itu.int/en/ITU-D/Statistics/Documents/facts/FactsFigures2020.pdf United Nations Population Fund (UNFPA) Sierra Leone. Leone S. Sierra Leone Rapid Emergency Obstetric and Newborn Care (EmONC) Assessment 2017. Available from: https://sierraleone.unfpa.org/en/publications/sierra-leone-rapid-emergency-obstetric-and-newborn-care-emonc-assessment-2017 Gomes RG, Vwalika B, Lee C, Willis A, Sieniek M, Price JT, et al. A mobile-optimized artificial intelligence system for gestational age and fetal malpresentation assessment. Commun Med. 2022 Oct 11;2(1):1–9. Diagnostic Image Analysis Group [Internet]. [cited 2024 Nov 4]. BabyChecker: AI for low-cost prenatal ultrasound. Available from: https://www.diagnijmegen.nl/projects/babychecker/ Arroyo J, Marini TJ, Saavedra AC, Toscano M, Baran TM, Drennan K, et al. No sonographer, no radiologist: New system for automatic prenatal detection of fetal biometry, fetal presentation, and placental location. PLOS ONE. 2022 Feb 9;17(2):e0262107. Toscano M, Marini TJ, Drennan K, Baran TM, Kan J, Garra B, et al. Testing telediagnostic obstetric ultrasound in Peru: a new horizon in expanding access to prenatal ultrasound. BMC Pregnancy Childbirth. 2021 Apr 26;21:328. Dougherty A, Kasten M, DeSarno M, Badger G, Streeter M, Jones DC, et al. Validation of a Telemedicine Quality Assurance Method for Point-of-Care Obstetric Ultrasound Used in Low-Resource Settings. J Ultrasound Med. 2021;40(3):529–40. World Health Organization. WHO recommendations on antenatal care for a positive pregnancy experience [Internet]. Geneva: World Health Organization; 2016 [cited 2024 Sep 19]. 152 p. Available from: https://iris.who.int/handle/10665/250796 Mbuyita S, Tillya R, Godfrey R, Kinyonge I, Shabani J, Mbaruku G. Effects of introducing routinely ultrasound scanning during Ante Natal Care (ANC) clinics on number of visits of ANC and facility delivery: A cohort study. Archives of Public Health. 2015 Sep 8;73:36. Liu X, Faes L, Kale AU, Wagner SK, Fu DJ, Bruynseels A, et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 2019 Oct 1;1(6):e271–97. Iv SNM, Shrivastava D, Raka MS, Iv SNM, Shrivastava D, Raka MS. A Comprehensive Review of the Role of Artificial Intelligence in Obstetrics and Gynecology. Cureus [Internet]. 2023 Feb 12 [cited 2023 Jul 24];15(2). Available from: https://www.cureus.com/articles/122226-a-comprehensive-review-of-the-role-of-artificial-intelligence-in-obstetrics-and-gynecology AI in Radiology: Pros & Cons, Applications, and 4 Examples.V7 [Internet]. [cited 2023 Jul 24]. Available from: https://www.v7labs.com/blog/ai-in-radiology. He F, Wang Y, Xiu Y, Zhang Y, Chen L. Artificial Intelligence in Prenatal Ultrasound Diagnosis. Front Med [Internet]. 2021 [cited 2023 Jul 24];8. Available from: https://www.frontiersin.org/articles/10.3389/fmed.2021.729978 Kim YH. Artificial intelligence in medical ultrasonography: driving on an unpaved road. Ultrasonography. 2021 Jul;40(3):313–7. Heuvel, T.L.A. van den. Automated low-cost ultrasound: improving antenatal care in resource-limited settings.2019.199000.pdf [Internet]. [cited 2025 Apr 6]. Available from: https://repository.ubn.ru.nl/bitstream/handle/2066/199000/199000.pdf?sequence=1&isAllowed=y Matthew J, Skelton E, Day TG, Zimmer VA, Gomez A, Wheeler G, et al. Exploring a new paradigm for the fetal anomaly ultrasound scan: Artificial intelligence in real time. Prenat Diagn. 2022;42(1):49–59. Drukker L, Noble JA, Papageorghiou AT. Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound Obstet Gynecol. 2020;56(4):498–505. Diagnostic Image Analysis Group [Internet]. [cited 2023 Jul 24]. BabyChecker: AI for low-cost prenatal ultrasound. Available from: https://www.diagnijmegen.nl/projects/babychecker/ Greenhalgh T, Wherton J, Papoutsi C, Lynch J, Hughes G, A’Court C, et al. Beyond Adoption: A New Framework for Theorizing and Evaluating Nonadoption, Abandonment, and Challenges to the Scale-Up, Spread, and Sustainability of Health and Care Technologies. J Med Internet Res. 2017 Nov 1;19(11):e367. von Both C, Fleβa S, Makuwani A, Mpembeni R, Jahn A. How much time do health services spend on antenatal care? Implications for the introduction of the focused antenatal care model in Tanzania. BMC Pregnancy Childbirth. 2006 Jun 23;6(1):22. Abrokwa SK, Ruby LC, Heuvelings CC, Bélard S. Task shifting for point of care ultrasound in primary healthcare in low- and middle-income countries-a systematic review. EClinicalMedicine. 2022 Mar 6;45:101333. World Health Organization, PEPFAR, UNAIDS. Task shifting : rational redistribution of tasks among health workforce teams : global recommendations and guidelines. 2007;88. Kozuki N, Mullany LC, Khatry SK, Ghimire RK, Paudel S, Blakemore K, et al. Accuracy of Home-Based Ultrasonographic Diagnosis of Obstetric Risk Factors by Primary-Level Health Care Workers in Rural Nepal. Obstet Gynecol. 2016 Sep;128(3):604. Kimberly HH, Murray A, Mennicke M, Liteplo A, Lew J, Bohan JS, et al. Focused Maternal Ultrasound by Midwives in Rural Zambia. Ultrasound Med Biol. 2010 Aug 1;36(8):1267–72. Neufeld LM, Wagatsuma Y, Hussain R, Begum M, Frongillo EA. Measurement error for ultrasound fetal biometry performed by paramedics in rural Bangladesh. Ultrasound Obstet Gynecol. 2009;34(4):387–94. Rijken MJ, Lee SJ, Boel ME, Papageorghiou AT, Visser GHA, Dwell SLM, et al. Obstetric ultrasound scanning by local health workers in a refugee camp on the Thai–Burmese border. Ultrasound Obstet Gynecol. 2009;34(4):395–403. Kodaira Y, Pisani L, Boyle S, Olumide S, Orsi M, Adeniji AO, et al. Reliability of ultrasound findings acquired with handheld apparatuses to inform urgent obstetric diagnosis in a high-volume resource-limited setting. Int J Gynecol Obstet. 2021;153(2):280–6. Viner AC, Membe-Gadama G, Whyte S, Kayambo D, Masamba M, Makwakwa E, et al. Training in Ultrasound to Determine Gestational Age (TUDA): Evaluation of a Novel Education Package to Teach Ultrasound-Naive Midwives Basic Obstetric Ultrasound in Malawi. Front Glob Womens Health [Internet]. 2022 [cited 2023 Jul 20];3. Available from: https://www.frontiersin.org/articles/10.3389/fgwh.2022.880615 Vinayak S, Sande J, Nisenbaum H, Nolsøe CP. Training Midwives to Perform Basic Obstetric Point-of-Care Ultrasound in Rural Areas Using a Tablet Platform and Mobile Phone Transmission Technology—A WFUMB COE Project. Ultrasound Med Biol. 2017 Oct;43(10):2125–32. Abawollo HS, Argaw MD, Tsegaye ZT, Beshir IA, Guteta AA, Heyi AF, et al. Effects of institutionalizing limited obstetric ultrasound services on utilization of maternal and neonatal health services: a pre-post study [Internet]. In Review; 2022 Jan [cited 2023 Jul 20]. Available from: https://www.researchsquare.com/article/rs-1297883/v1 El-Jardali F, Fadlallah R. A review of national policies and strategies to improve quality of health care and patient safety: a case study from Lebanon and Jordan. BMC Health Serv Res. 2017 Aug 16;17:568. Tautz S, Jahn A, Molokomme I, Görgen R. Between fear and relief: how rural pregnant women experience foetal ultrasound in a Botswana district hospital. Soc Sci Med 1982. 2000 Mar;50(5):689–701. Chukwu E, Garg L, Foday E, Konomanyi A, Wright R, Smart F. Electricity, Computing Hardware, and Internet Infrastructures in Health Facilities in Sierra Leone: Field Mapping Study. JMIR Med Inform. 2022 Feb 3;10(2):e30040. Conteh E, Okereke M, Turay FU, Bah AS, Muhsinah A. The need for a functional pharmaceutical industry in Sierra Leone: lessons from the COVID-19 pandemic. J Pharm Policy Pract. 2022 Jul 27;15(1):46. Andersen CA, Brodersen J, Rudbæk TR, Jensen MB. Patients’ experiences of the use of point-of-care ultrasound in general practice – a cross-sectional study. BMC Fam Pract. 2021 Jun 18;22(1):116. Stark S, Worm L, Kluge M, Roos M, Burggraf L. The patient satisfaction in primary care consultation—Questionnaire (PiC): An instrument to assess the impact of patient-centred communication on patient satisfaction. PLOS ONE. 2021 Jul 16;16(7):e0254644. Hanson K, Brikci N, Erlangga D, Alebachew A, De Allegri M, Balabanova D, et al. The Lancet Global Health Commission on financing primary health care: putting people at the centre. Lancet Glob Health. 2022 May;10(5):e715–72. Additional Declarations No competing interests reported. Supplementary Files Appendices.docx Cite Share Download PDF Status: Published Journal Publication published 27 Apr, 2026 Read the published version in BMC Pregnancy and Childbirth → Version 1 posted Editorial decision: Revision requested 30 Sep, 2025 Reviews received at journal 20 Sep, 2025 Reviewers agreed at journal 16 Sep, 2025 Reviewers agreed at journal 16 Sep, 2025 Reviewers agreed at journal 16 Sep, 2025 Reviewers agreed at journal 15 Sep, 2025 Reviews received at journal 16 Aug, 2025 Reviewers agreed at journal 16 Aug, 2025 Reviewers agreed at journal 24 Jul, 2025 Reviewers invited by journal 13 Jul, 2025 Editor invited by journal 23 May, 2025 Editor assigned by journal 22 May, 2025 Submission checks completed at journal 22 May, 2025 First submitted to journal 20 May, 2025 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-6710084","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":484778423,"identity":"0e4623dc-acfb-4a6b-b8c3-97af2a5184de","order_by":0,"name":"Abu Dim Din Sesay","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYPCCAwz8zMwHgAwJGeK1SLazJYC08BCvxeA8jwGIRViLfHv7w888NXcSNxzm+fzqRo0FDwP74aMb8GkxOHPGWJrn2LPEmYd5t1nnHAM6jCct7QZeLRI5DNI8bIcT+4BajHPYgFokeMzwapGf//zxb55/hxMbDvM8M875R4QWhhsMZtK8bYcTJxzmYX6c20aEFoMzOWaWc/ueGc9sZjNjzu2T4GEj5Bf59uOPb7z5dke2n//w48853+rk+NkPH8PvMCBggsYFmwSYJKQcBBh/QGjmD8SoHgWjYBSMgpEHAN6PS7ahd+AWAAAAAElFTkSuQmCC","orcid":"","institution":"Ministry of Health and Sanitation","correspondingAuthor":true,"prefix":"","firstName":"Abu","middleName":"Dim Din","lastName":"Sesay","suffix":""},{"id":484778424,"identity":"1cca5674-e3cf-44d8-9d4c-9805983a1896","order_by":1,"name":"Amie Lompri Koroma","email":"","orcid":"","institution":"White Ribbon Alliance","correspondingAuthor":false,"prefix":"","firstName":"Amie","middleName":"Lompri","lastName":"Koroma","suffix":""},{"id":484778425,"identity":"f8e07aae-f56f-426e-81ab-dd0e48e0aa2b","order_by":2,"name":"Anke van der Kwaak","email":"","orcid":"","institution":"Royal Tropical Institute","correspondingAuthor":false,"prefix":"","firstName":"Anke","middleName":"van der","lastName":"Kwaak","suffix":""},{"id":484778426,"identity":"f952722b-a12b-484e-b407-2bc597cc7c20","order_by":3,"name":"Enya Seguin","email":"","orcid":"","institution":"Delft Imaging, Netherlands","correspondingAuthor":false,"prefix":"","firstName":"Enya","middleName":"","lastName":"Seguin","suffix":""},{"id":484778427,"identity":"63ccfcaa-9a17-45cc-8800-5e1d4d04aa16","order_by":4,"name":"Alhassan Kanu","email":"","orcid":"","institution":"Centre for Community \u0026 Public Health Improvement, Sierra Leone","correspondingAuthor":false,"prefix":"","firstName":"Alhassan","middleName":"","lastName":"Kanu","suffix":""},{"id":484778428,"identity":"c846b94f-1fa6-4a3a-9128-c084c8a30322","order_by":5,"name":"Abdul Mac Falama","email":"","orcid":"","institution":"Ministry of Health and Sanitation","correspondingAuthor":false,"prefix":"","firstName":"Abdul","middleName":"Mac","lastName":"Falama","suffix":""},{"id":484778429,"identity":"9c4fdac5-c0f9-4db6-b612-eb84a6cff63d","order_by":6,"name":"Mirjam Bakker","email":"","orcid":"","institution":"Royal Tropical Institute","correspondingAuthor":false,"prefix":"","firstName":"Mirjam","middleName":"","lastName":"Bakker","suffix":""},{"id":484778430,"identity":"7a8cd8ea-0d45-434a-8135-174972a0dee2","order_by":7,"name":"Irene de Vries","email":"","orcid":"","institution":"Royal Tropical Institute","correspondingAuthor":false,"prefix":"","firstName":"Irene","middleName":"","lastName":"de Vries","suffix":""}],"badges":[],"createdAt":"2025-05-20 17:38:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6710084/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6710084/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12884-026-09152-8","type":"published","date":"2026-04-27T15:57:11+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":87033433,"identity":"5a3fb54d-3b61-4fb0-bbb5-0f1324aa2626","added_by":"auto","created_at":"2025-07-18 13:06:12","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":236128,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003ePicture of USB-C cabled probe, the bag and the smartphone with the app showing the guidance for the first sweep of the 6-sweep protocol.\u003c/em\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-6710084/v1/3fb5ddecc948cdd43ed522ba.png"},{"id":108438793,"identity":"03c650f7-3d1f-4d19-ab2a-164fc23174f4","added_by":"auto","created_at":"2026-05-04 16:10:37","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":841729,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6710084/v1/4ea9ebdb-604f-4209-a73f-ff57f01c0acf.pdf"},{"id":87033435,"identity":"dbeb2629-ac66-44be-b7ed-a4a967db5657","added_by":"auto","created_at":"2025-07-18 13:06:12","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":38570,"visible":true,"origin":"","legend":"","description":"","filename":"Appendices.docx","url":"https://assets-eu.researchsquare.com/files/rs-6710084/v1/366080c784a2a8d116ee6c83.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eEvaluating the Usability and Practicality of AI-Enabled Smartphone-based Obstetric Ultrasound in Sierra Leone: A Mixed-Methods Study\u003c/p\u003e","fulltext":[{"header":"1. Background","content":"\u003cp\u003eObstetric ultrasound plays a crucial role in Antenatal Care (ANC), allowing healthcare providers to assess factors such as gestational age, fetal growth, placental function, and the presence of anomalies or complications. This information is vital for making informed decisions about pregnancy management. Due to the importance of ultrasound, the World Health Organization (WHO) recommends that all pregnant women receive one early ultrasound before 24 weeks of gestation (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e). Despite these recommendations, Low- and Middle-Income countries (LMICs) lag far behind in utilizing ultrasound. Limited resources lead to a shortage of ultrasound equipment and trained personnel (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e), while unreliable access to electricity and internet connectivity further hinders the implementation and sustainability of digital solutions (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eIn Sierra Leone, many government facilities lack ultrasound equipment and trained sonographers. A Rapid Emergency Obstetric and Newborn Care (EmONC) Assessment Report from 2017 stated that ultrasound machines were available in only 53% of district hospitals and recommended equipping all district hospitals with functional machines, along with providing appropriate training for their maintenance (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e). Global studies have shown that obstetric scans can be effectively performed with minimal training using the \u0026ldquo;Obstetric Sweep Protocol\u0026rdquo; (\u003cspan additionalcitationids=\"CR7 CR8 CR9\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e). A study in Peru found that after eight hours of training, users achieved over 95% accuracy in key obstetric assessments, such as fetal count, presentation, and placental position (\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e). This approach has the potential to make ultrasound more accessible and aligns with WHO recommendations on task shifting (\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e). While evidence on the impact of hand-held ultrasound devices remains limited for Sierra Leone, studies in other LMICs suggest that integrating point-of-care ultrasound into routine ANC improves clinic attendance. A cohort study in Tanzania reported a rise in the percentage of women attending four or more ANC visits (from 27.2\u0026ndash;60.3%; p\u0026thinsp;=\u0026thinsp;0.001) (\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e). Artificial Intelligence (AI) is being used in ultrasound technology to help healthcare providers make faster and more accurate pregnancy-related diagnoses, especially in low-resource settings (\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan additionalcitationids=\"CR14 CR15 CR16 CR17 CR18 CR19\" citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e). This study evaluated the usability, practicality, and adoption of an Artificial Intelligence (AI) enabled portable ultrasound device that has been piloted in Tonkolili district since 2020.\u003c/p\u003e\u003cdiv id=\"Sec2\" class=\"Section2\"\u003e\u003ch2\u003e1.1 Description of the device\u003c/h2\u003e\u003cp\u003eThe piloted tool is a smartphone-based ultrasound device and software (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e) designed to improve access to obstetric imaging in low-resource settings. The device requires a probe and gel for scanning and employs the \"Obstetric Sweep Protocol,\" to produce images that can be used for remote analysis or AI to estimate gestational age, detect multiple pregnancies, determine placental location, and assess fetal position (\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e). The device is portable and easy to use, requiring approximately one hour of training for healthcare providers. It operates offline for scanning but requires internet access for healthcare providers to upload scans for remote analysis by ultrasound professionals and to receive the results. An AI-enabled version was introduced in 2023, enabling automatic mobile application analysis and delivering results within seconds. Using a traffic light system, the device alerts users to potential obstetric risks and the need for referral.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e1.2 Pilot Implementation of the Device in Sierra Leone\u003c/h2\u003e\u003cp\u003eIn 2020, a pilot program introduced the device in Gbonkolenken Chiefdom, Tonkolili District, Sierra Leone. Seven portable ultrasound devices were deployed across six peripheral health facilities, chosen for their proximity to the referral hospital. The goal of the pilot was to assess the device\u0026rsquo;s effectiveness in resource-limited primary care settings for early detection of pregnancy complications.\u003c/p\u003e\u003cp\u003eThe pilot had two phases: Phase 1 introduced the device at a referral hospital during ANC visits; providers were trained and women received free scans. Phase 2 focused on usability and practicality by healthcare providers at the primary healthcare level including Community Health Officers (CHOs), Community Midwives, Community Health Assistants (CHAs), State-Enrolled Community Health Nurses (SECHNs) and Maternal and Child Health Aides (MCHAs).\u003c/p\u003e\u003c/div\u003e"},{"header":"2. Methods","content":"\u003cp\u003e\u003cstrong\u003eStudy design\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study, conducted in 2023, employed a mixed-methods approach to evaluate the usability, practicality, and long-term adoption of a smartphone-based AI-enabled obstetric ultrasound device in Sierra Leone. Data from 2,315 obstetric scans performed by 81 healthcare providers across seven facilities in Tonkolili district between October 2020 and March 2023 were analyzed to assess healthcare providers\u0026apos; scanning performance and factors influencing scan quality. Additionally, to explore factors affecting the sustainable implementation and adoption of the device in the district, qualitative data were collected through interviews, focus group discussions, and observations with healthcare providers, clients, and key informants, guided by the Non-adoption, Abandonment, Scale-up, Spread, and Sustainability (NASSS) framework.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eA. Quantitative method\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData source\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eElectronic scanning records from pregnant women who underwent obstetric scans using the smartphone-based device between October 2020 and March 2023 were analyzed. Data included client ID, healthcare provider ID, scan date/time, app version, facility type, and scan quality. The dataset captured more variables such as the reason for insufficient quality scan, fetus count, etc., which are not used in this study. A separate database captured healthcare provider characteristics such as gender, staff cadre, and facility affiliation. The seven participating facilities included one Community Health Post (CHP), three Community Health Centers (CHC), two Maternal and Child Health Posts (MCHP), and one hospital.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eKey Variables\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe primary outcome variable was scan quality, categorized as sufficient quality (scans with clear images that could be analysed for the specified parameters) and insufficient quality (scans with poor image quality that were inadequate for analysis, often due to suboptimal user performance). Independent variables included scan frequency (categorized into experience levels), healthcare provider cadre (grouped into skill levels), facility type, and app version. App versions were broadly classified into those with or without tutorial videos, where tutorial-equipped versions intended to enhance provider performance.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eQuantitative data analysis\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eData were exported to Stata version 17 for analysis. Descriptive statistics characterized healthcare providers and scan quality distributions, while categorical variables were summarized using frequencies and percentages. A mixed-effects logistic regression model was used to assess factors influencing scan quality, including scan frequency, app version, healthcare provider cadre, and facility type. \u0026nbsp; Initial bivariate logistic regression was followed by a multivariate regression model to adjust for confounders. Due to multicollinearity, app version was omitted from the final model as it was strongly associated with facility type. The models calculated (adjusted) odds ratios ((a)OR), 95% confidence intervals (CI), and p-values to determine the significance of the associations, using a significance level of p \u0026lt; 0.05. A subgroup analysis assessed the effectiveness of app versions with tutorial videos on scan quality for first-time users. This helped to account for experience as a potential confounding factor.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eB. Qualitative method\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStudy Population and Sampling\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe qualitative component included six in-depth interviews (IDIs) with frontline healthcare providers, three key informant interviews (KIIs) with hospital and DHMT staff, and two focus group discussions (FGDs) \u0026mdash;one with six healthcare providers and another with six female clients (pregnant, and lactating women) who underwent obstetric scans with the device. Additionally, participant observations were conducted during the practices of three healthcare providers. \u0026nbsp;Purposive sampling was used for IDIs and KIIs, while FGDs followed a convenience sampling approach. Clients were selected from records based on experiences within the past three months to minimize recall bias.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTheoretical framework\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study applied the (NASSS) framework \u0026nbsp;developed by Greenhalgh et al. (2017) (22), which guided the development of the topic guide and analysis. This study focused on all seven main domains and 19 of the 24 subdomains, ensuring a comprehensive exploration of factors influencing adoption and sustainability.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData collection\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eData collection took place over seven days (June 15-21, 2023) in Tonkolili district. Semi-structured topic guides were used for KIIs, IDIs, and FGDs, as detailed in the Research Table \u003cstrong\u003e(Appendix A).\u003c/strong\u003e\u0026nbsp; KIIs were conducted in English, while IDIs and FGDs were held in the local Creole language. KIIs and IDIs lasted approximately 45 minutes, while FGDs ranged from 60\u0026ndash;75 minutes. The data collection techniques are summarized in \u003cstrong\u003eTable 1:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 1\u003c/strong\u003e: Data collection procedures\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"603\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 123px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003eProcedure\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003eNumber\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 2px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 155px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003eParticipants\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 227px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003eResearch Issues Explored\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 123px;\"\u003e\n \u003cp\u003eKey Informant Interviews (KIIs)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 98px;\"\u003e\n \u003cp\u003e3\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 2px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 155px;\"\u003e\n \u003cp\u003eDHMT staff: 2\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eHospital management: 1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 227px;\"\u003e\n \u003cp\u003eRoles in the pilot, policy decisions, and perspectives on the pilot and device implementation.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 123px;\"\u003e\n \u003cp\u003eIn-Depth Interviews (IDIs)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 98px;\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 2px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 155px;\"\u003e\n \u003cp\u003eHealthcare providers (e.g. nurses, midwives, CHO): 6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 227px;\"\u003e\n \u003cp\u003eExperiences with the device, including usability, perceived effectiveness, and challenges faced during use.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 123px;\"\u003e\n \u003cp\u003eFocus Group Discussions (FGDs)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 98px;\"\u003e\n \u003cp\u003e2 groups (12 participants)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 2px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 155px;\"\u003e\n \u003cp\u003eHealthcare providers: 1 group (6 participants)\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eClients: 1 group (6 participants)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 227px;\"\u003e\n \u003cp\u003eBarriers, facilitators, and overall influences related to device usage.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 123px;\"\u003e\n \u003cp\u003eParticipatory Observation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 98px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 2px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 155px;\"\u003e\n \u003cp\u003eHealthcare providers performing scans on pregnant women: 3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 227px;\"\u003e\n \u003cp\u003eReal-time interactions with clients, explanation of procedures, communication of diagnoses, referral and next steps.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003eData analysis\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAudio recordings were manually transcribed and translated from the local vernacular to English. Anonymized transcripts were coded and analyzed in NVIVO software (version 14) using a coding framework. Thematic coding was conducted deductively (using predefined NASSS categories) and inductively (creating new codes as needed).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical considerations\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eEthical approval was obtained from KIT Tropical Institute (reference S-208) and the Sierra Leone Ethics and Scientific Review Committee (reference 001/06/2023). Informed consent was obtained from all participants, ensuring understanding of research procedures, potential risks, and benefits, with the opportunity to withdraw voluntarily. To ensure anonymity and confidentiality, all personally identifiable data were coded and securely stored on password-protected devices. Only the researchers had access to the passwords. The data will be kept confidential for one year before being disposed of.\u003c/p\u003e"},{"header":"3. Results","content":"\u003cp\u003e\u003cstrong\u003e3.1 Description of Study Participants\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAmong the 81 healthcare providers who conducted scans 57% were female, while 33% (27 of 81) had missing gender data. Despite this, these missing values accounted for only 1.2% of the total scans conducted (27 of 2,315), suggesting minimal impact on the overall findings. In terms of professional roles, MCHAs constituted a significant proportion, making up 26% (21 of 81) of healthcare providers but contributing to 43.6% of all scans performed. SECHNs represented 9% (7 of 81), performed 19.5% (452 of 2,315) of the scans \u003cstrong\u003e(Table 2).\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFor the interviews with 24 healthcare providers, the majority (19 of 24) were female. Educational backgrounds among healthcare providers varied, with 4 having tertiary education, 14 having secondary education, 2 with primary education, and 4 with no formal education. Clients also had diverse maternal experiences, with five having prior childbirth experience, while one was experiencing her first pregnancy.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.2 Scanning Performance\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA total of 2,315 scans were conducted between October 2020 and March 2023, with a median of 8 scans per healthcare provider (IQR: 36). Among these, 83.8% were of sufficient quality for remote or AI analysis, while 16.2% were considered insufficient. Notably, 59.3% of healthcare providers achieved an 80% or higher rate of sufficient-quality scans, meeting the predefined threshold. Midwife students and Community Health Assistants had the lowest percentages of high-quality scans, with 70.7% (29 of 41) and 72.3% (73 of 101) of their scans deemed sufficient, respectively.\u003c/p\u003e\n\u003cp\u003eThe findings also revealed disparities across healthcare facilities. At one CHC, 17.3% (14 of 81) of the healthcare providers performed the highest number of scans, accounting for 28.6% (663 of 2315) of the total. The best scan quality, with 92.3% of its scans rated as sufficient, was found at one of the MCHPs. In contrast, the referral hospital had the largest number of healthcare providers (35.8%) but conducted the fewest scans (3.5%) and had the lowest quality, with only 43.2% of scans meeting the sufficient quality standard. A closer look revealed that the vast majority (26 of 29) of healthcare providers at this hospital had used the device only once. The descriptive characteristics of healthcare providers and scans conducted are shown (\u003cstrong\u003eTable 2).\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2:\u0026nbsp;\u003c/strong\u003eDescriptive characteristics of healthcare providers and scans conducted\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"690\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eCharacteristics\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHealthcare providers\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eN=81\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 125px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNumber of scans (N=2,315)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 153px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScans of sufficient quality\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u003cstrong\u003en\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e%\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u003cstrong\u003en\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e%\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u003cstrong\u003en\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e%\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"3\" valign=\"top\" style=\"width: 412px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSex of healthcare provider:\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eFemale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e56.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e1,897\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e81.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e1602\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e84.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eMale\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e9.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e391\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e16.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e328\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e83.9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eMissing\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e33.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e1.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e37.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"3\" valign=\"top\" style=\"width: 412px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"3\" valign=\"top\" style=\"width: 412px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHealthcare provider cadre:\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eCHOs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e3.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e231\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e10.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e202\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e87.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eMidwives\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e4.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e154\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e6.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e133\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e86.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eCHAs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e3.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e101\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e4.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e73\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e72.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eSECHNs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e8.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e452\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e19.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e369\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e81.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eMCHAs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e25.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e1,011\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e43.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e862\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e85.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eStudent CHOs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e1.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e1.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e81.8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eStudent midwives\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e3.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e1.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e70.7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eSRNs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e3.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e145\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e6.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e128\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e88.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eStudent MCHAs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e1.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e0.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e100.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eTBAs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e4.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e1.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e97.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eCHVs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e4.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e3.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e82.7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eMissing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e33.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e1.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"3\" valign=\"top\" style=\"width: 412px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHealth facility:\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eLHMC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e35.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e3.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e43.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eYele CHC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e17.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e663\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e28.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e584\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e88.1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eMayepoh CHC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e22.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e558\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e24.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e472\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e84.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eManowo CHC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e7.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e515\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e22.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e422\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e81.9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eMansumana CHP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e7.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e239\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e10.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e192\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e80.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003ePetifu Mayepoh MCHP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e4.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e129\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e5.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e119\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e92.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eWarema MCHP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e4.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e130\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e5.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e116\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e89.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eApp capability (tutorial videos):\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eWith tutorial videos\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e2,234\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e96.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 97px;\"\u003e\n \u003cp\u003e1,905\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e85.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eWithout tutorial videos\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e3.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 97px;\"\u003e\n \u003cp\u003e35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e43.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFrequency of scan:\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e1st scan\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e3.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 97px;\"\u003e\n \u003cp\u003e56\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e69.1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e2nd-10th scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e416\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e18.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e337\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e81.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e11th-30th scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e549\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e23.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e457\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e83.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e31st-50th scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e379\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e16.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e317\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e83.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e51st-100th scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e444\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e19.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e384\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e86.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e101st \u0026amp; above scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e446\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e19.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e389\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e87.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTotal number of scans\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eOne scan\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e33.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e1.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e37.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e2-10 scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e19.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e90\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e3.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e76.7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e11-30 scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e19.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e269\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e11.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e219\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e81.4\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e31-50 scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e8.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e289\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e12.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e234\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e81.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e51-100 scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e11.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e594\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e25.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e508\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e85.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e101 \u0026amp; above scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e7.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e1046\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e45.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e900\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e86.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"3\" valign=\"top\" style=\"width: 412px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eQuality of scan\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eScans with sufficient quality\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e1,940\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e83.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 278px;\"\u003e\n \u003cp\u003eScans insufficient quality\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 60px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 74px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 71px;\"\u003e\n \u003cp\u003e375\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003e16.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 97px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003e3.3 Factors Associated with Sufficient Scan Quality\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe results of the bivariate and multivariate analyses for factors associated with obtaining scans of sufficient quality are presented in \u003cstrong\u003eTable 3.\u0026nbsp;\u003c/strong\u003eBivariate analysis revealed a significant positive association between using an app with tutorial videos and obtaining sufficient-quality scans (OR: 14.1, 95% CI: 6.40\u0026ndash;31.12, p \u0026lt; 0.001). However, the app variable was excluded from the multivariate analysis due to multicollinearity with health facility types. In a subgroup analysis of first-time app users, control for experience as a confounder \u003cstrong\u003e(Table 4),\u003c/strong\u003e the association remained significant (OR: 12.2, 95% CI: 4.11\u0026ndash;36.32, p \u0026lt; 0.001).\u003c/p\u003e\n\u003cp\u003ePrimary health facilities (CHCs, CHPs, MCHPs) had significantly higher odds of obtaining scans of sufficient quality compared to the hospital. Specifically, MCHPs demonstrated the highest odds of sufficient scan quality (aOR: 46.1, 95% CI: 11.19-189.97, p \u0026lt; 0.001). Medium-skilled (aOR: 0.28, p = 0.004), low-skilled with formal training (aOR: 0.32, p = 0.004), and very low-skilled workers in training (aOR: 0.34, p = 0.020) had lower odds of obtaining sufficient-quality scans compared to high-skilled workers. While scan frequency was linked to quality in bivariate analysis, no significant associations were found in multivariate analysis.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 3:\u0026nbsp;\u003c/strong\u003eFactors associated with obtaining scans of sufficient quality (Fixed effects output)\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"667\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"3\" style=\"width: 238px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eBivariate analysis ( N obs= 2,315 \u0026amp; N groups= 81 )\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"3\" style=\"width: 234px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eMultivariate analysis (N obs=2,288 \u0026amp; N groups =54)\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFactor\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eOR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP-value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eaOR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP-value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eApp capability\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eWithout tutorial video\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eWith tutorial video\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e14.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e6. 40-31.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026lt;0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eStaff cadre \u003csup\u003ea\u003c/sup\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eHigh skilled\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eMedium skilled\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e0.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e0.14-1.16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.091\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e0.28\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e0.11-0.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.004**\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eLow skilled with formal training \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e0.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e0.22-1.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.301\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e0.32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e0.15-0.70\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.004**\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eVery low skilled in training \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e0.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e0.18-1.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.356\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e0.34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e0.14-0.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.020*\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eLow skilled without formal training\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e0.27-3.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.937\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e0.39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e0.13-1.15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.089\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHealth Facility type\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eHospital\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eCHCs\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e12.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e5.86-27.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026lt;0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e19.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e5.90-63.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026lt;0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eCHPs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e9.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e3.44-23.89\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026lt;0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e18.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e4.61-73.30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026lt;0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003eMCHPs\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e28.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e10.11-80.37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026lt;0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e46.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e11.19-189.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026lt;0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFrequency of scan:\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e1st scan\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 101px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e2nd-10th scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e2.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e1.18-3.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.012*\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e0.99\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e0.46-2.13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.971\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e11th-30th scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e2.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e1.35-4.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.003**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e1.13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e0.52-2.43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.759\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e31st-50th scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e1.60-5.60\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.001**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e1.40\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e0.63-3.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.411\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e51st-100th scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e2.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e1.45-5.13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.002**\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e1.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e0.57-2.83\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.556\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 195px;\"\u003e\n \u003cp\u003e101st \u0026amp; above scans\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 55px;\"\u003e\n \u003cp\u003e3.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 99px;\"\u003e\n \u003cp\u003e1.74-6.54\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e\u0026lt;0.001***\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 50px;\"\u003e\n \u003cp\u003e1.54\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 101px;\"\u003e\n \u003cp\u003e0.68-3.50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 83px;\"\u003e\n \u003cp\u003e0.304\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003csup\u003ea\u0026nbsp;\u003c/sup\u003emissing 27 (33.3%) healthcare providers\u003c/p\u003e\n\u003cp\u003e* Significant at p-value \u0026lt; 0.05\u003c/p\u003e\n\u003cp\u003e**Significant at p-value \u0026lt; 0.01\u003c/p\u003e\n\u003cp\u003e*** Significant at p-value \u0026lt; 0.001, cOR =Crude Odds Ratios, aOR =adjusted Odds Ratios, N obs =Number of observations, N groups =Number of groups of healthcare providers. Please note that the reduced number of observations to 2,288 and healthcare provider\u0026rsquo;s groups to 54 in the multivariate analysis is attributable to missing values within the \u0026ldquo;staff cadre\u0026rdquo; variable.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 4:\u0026nbsp;\u003c/strong\u003eSub-group analysis of first-time users of each category of the app version\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"601\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"7\" valign=\"top\" style=\"width: 601px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eBivariate analysis (N=81)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 177px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFactor\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 87px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTotal scans\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 112px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSufficient quality scans\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eOR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eP-value\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 177px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eApp capability\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 87px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 57px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 62px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 177px;\"\u003e\n \u003cp\u003eWithout tutorial videos\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 87px;\"\u003e\n \u003cp\u003e29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 57px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e31.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 67px;\"\u003e\n \u003cp\u003e\u0026nbsp;1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 95px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 62px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 177px;\"\u003e\n \u003cp\u003eWith tutorial videos\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 87px;\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 57px;\"\u003e\n \u003cp\u003e44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 56px;\"\u003e\n \u003cp\u003e84.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 67px;\"\u003e\n \u003cp\u003e\u0026nbsp;12.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 95px;\"\u003e\n \u003cp\u003e4.11-36.32\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 62px;\"\u003e\n \u003cp\u003e\u0026lt;0.001\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003eQualitative findings under the NASSS domains\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe qualitative analysis identified eight themes, of which seven aligned with the NASSS framework including condition, technology, value proposition, adopters, organization, wider system, embedding and adaptation over time. One additional theme, focusing on Quality of care, emerged and was explored separately (see \u003cstrong\u003eAppendix C\u003c/strong\u003e).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.4 The Condition\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe domain of condition examines knowledge, perceptions, and sociocultural values on obstetric ultrasound use. Healthcare providers and key informants acknowledged its role in detecting high-risk pregnancies, while clients expressed satisfaction with its ability to ensure maternal and fetal well-being. Women also viewed hospital referrals as indicators of priority cases. However, concerns also emerged regarding over-reliance on the device, potentially diminishing fundamental skills like physical examination and communication:\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;The scan works so well that now, we are super attached to it. I am worried that we are depending on it for almost everything. What happens if it gets faulty or is not available? We are losing our skills in the process\u0026rdquo; (IDI with healthcare provider).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe risk of abandoning conventional diagnostic methods was evident in findings that showed physical examinations were frequently omitted during routine check-ups. Some healthcare providers reported that the device aided in identifying additional conditions, such as Sexually Transmitted Infections (STIs), by allowing them to detect vaginal odors during abdominal scans. Although this was described as an unexpected benefit of using the device, such diagnoses should have been possible through proper physical examination\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026quot;We can smell vaginal odor during the scan process and perform further examinations. The scan helps us to be proactive\u0026quot; (IDI with healthcare provider).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eSociocultural factors were reported to pose minimal barriers, as the scan\u0026rsquo;s perceived accuracy fostered widespread community acceptance. This trust encouraged healthcare engagement and compliance with referrals, often reinforced by local leaders.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eWomen appreciate machines more than our manual hands. There is high community acceptance\u0026rdquo; (KII with DHMT Staff).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;When women refuse referrals, chiefs step in, and they comply\u0026rdquo; (IDI with healthcare provider).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eDespite widespread acceptance of ultrasound, some women reported limited emotional support from their male partners. While financial contributions were common, emotional involvement was less evident. Many women described this lack of engagement as reflective of cultural norms that frame maternal health as solely a woman\u0026rsquo;s responsibility.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;He (Partner) gives me money for the hospital but never willingly accompanies me unless the nurses request it\u0026rdquo; (FGD with Client).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.5 The Technology\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis section highlights healthcare providers\u0026apos; experiences with the device, focusing on its user interface, efficiency, and feasibility at the primary healthcare (PHC) level. Healthcare providers found the device easy to use, aided by smartphone familiarity and tutorial videos. Instant results were valued, facilitating timely care and referrals, with the traffic light system proving useful in risk categorization.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;We find it easy to perform the six sweeps as videos are displayed, and we just follow the visual directions\u0026hellip; because it\u0026rsquo;s a machine, it\u0026rsquo;s easier to use\u0026rdquo; (FGD with healthcare providers).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eHealthcare providers found it easy to integrate the device into their routines, improving their diagnostic skills and contributing to better overall care delivery\u003cstrong\u003e\u003cem\u003e.\u0026nbsp;\u003c/em\u003e\u003c/strong\u003eThey also noted reduced workloads and faster diagnoses, freeing up time for other duties and enhancing overall performance.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;It was easy to integrate into our routine. We trained colleagues, and everyone in the maternity unit can use the device well\u0026rdquo; (IDI with healthcare provider).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;The scan reduces the time spent on listening for a fetal heartbeat and determining gestational periods, which are difficult to do manually\u0026rdquo; (IDI with healthcare provider).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eHowever, despite claims of reduced workload, observations revealed that healthcare providers were often overwhelmed due to high demand for ultrasounds. At least 60 pregnant women per day attended an ANC clinic per facility, and all underwent scans, regardless of having had a recent scan. \u0026nbsp;With a maximum of three staff per primary health facility, the healthcare provider-to-client ratio stood at 1:23, far exceeding the global standard of 1:5. The increased utilization of the technology has highlighted a staffing shortfall that the device alone cannot resolve.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.6 The Perceived Value\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis component explores participants\u0026rsquo; perspectives on the device\u0026rsquo;s importance, emphasizing its intrinsic benefits and broader impact. Obstetric ultrasound availability was mentioned to increase ANC attendance and facility deliveries. This surge has facilitated the implementation of other health interventions, such as immunizations and malaria screenings.\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;Pregnant women are coming for scans, and this indirectly helps in strengthening other ANC services like TT (Tetanus Toxoid) and malaria checks\u0026rdquo; (IDI with healthcare provider).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe device was believed to reduce maternal and fetal deaths, by improving diagnostic accuracy and enabling early identification of high-risk pregnancies. Healthcare providers highlighted its role in mitigating misdiagnosis, particularly by empowering lower-cadre staff to enhance their diagnostic skills through hands-on use.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;Misdiagnosis was common, but the scan enables volunteers and lower cadre staff to self-train and improve skills\u0026rdquo; (IDI with healthcare provider).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eClients also noted that the scan helped alleviate fears about potential health risks and increased their trust in diagnoses.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;Many women have died or had stillbirths without knowing it. But since the scan, we haven\u0026rsquo;t heard of such cases\u0026rdquo; (FGD with Clients).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eHowever, while participants reported reduced mortality, these claims were difficult to verify due to a lack of clinical record audits. Additionally, improvements may stem from broader health interventions like health education campaigns, making it challenging to isolate the specific impact of the device.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eHealthcare providers observed increased client engagement, noting that obstetric ultrasound empowered women to take a more active role in healthcare decisions. However, they also acknowledged a critical gap in interpersonal care. Many women seek empathy, respect, and emotional support\u0026mdash;needs that are often unmet due to time constraints, limited training in client-centered care, and broader systemic challenges. Addressing this gap is crucial, as emotional support significantly influences client satisfaction and adherence to care.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.7 Adopters\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFor the factors shaping the adoption and implementation of the device, healthcare providers credited the device\u0026rsquo;s ease of use and tutorial-based training for its successful adoption. The device was described as user-friendly, practical, easy to operate and improved access and early referrals at primary care levels.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eHowever, overall staff education levels were cited as a challenge. While basic device use was easy to learn, interpreting results and linking them to clinical actions required more advanced midwifery and obstetric knowledge. This skills gap risked misdiagnosis and reduced the device\u0026rsquo;s potential benefits.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026ldquo;My technical background as a midwife helps me link the result with the woman\u0026rsquo;s overall health\u0026quot; (IDI with healthcare provider).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eClients\u0026apos; decisions to undergo scans were influenced by socioeconomic factors, including transportation issues, illiteracy, high costs at advanced facilities, the challenge of leaving other children behind, and anxiety about referrals. While some clients were discouraged by these barriers, others were motivated by the knowledge gained from a diagnosis, prompting them to seek care to protect their health and that of their babies.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.8 Organizational Factors\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis domain delves into the infrastructure and funding requirements necessary for integrating health technologies within health facilities. Findings revealed an urgent need to improve primary health facilities infrastructure nationwide, especially for power and internet connectivity. Currently, health facilities depend heavily on intermittent support from development partners, who provide temporary access to solar energy and internet services. However, sustainable solutions for electricity and network connectivity have not yet been established by the government.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003ePrimary health facilities in the pilot program benefited from donor-supported infrastructure, such as electricity and internet, but many others across the country lack these resources. Both healthcare providers and clients expressed dissatisfaction with the health system despite the free healthcare initiative, citing issues such as shortages of life-saving drugs and poorly lit delivery rooms.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;The clinics need more medication for maternity. Nurses tell us we need more care, but most times there is no medication for treatment\u0026rdquo; (FGD with Clients).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFurthermore, barriers such as stockouts and the lack of necessary medical supplies, particularly gel for scanning, were also identified. Since gel is not included in routine health supplies, providers were often forced to ask clients to purchase supplies, adding financial strain. Insufficient examination beds exacerbated workloads and contributed to delays.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026ldquo;\u003cstrong\u003e\u003cem\u003eWith such a huge workload, we need at least 2 beds for scans and general assessments\u0026rdquo; (IDI with healthcare provider).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eLimited funding remains a major challenge for investing in innovative healthcare technologies. Sierra Leone\u0026rsquo;s dependency on donors raises concerns about the scalability and sustainability of technologies. Although the device is more affordable than traditional ultrasound machines, its annual subscription fee poses a financial burden. Efforts to scale the program are further complicated by local councils\u0026apos; tendency to prioritize administrative and personnel expenses over recurring technology costs.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.9 Wider System Factors\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis segment explores how policy gaps, socio-economic factors, and cultural norms affect digital health use. Healthcare Providers highlighted the absence of clear guidelines on obstetric ultrasound, leading to inconsistent practices like frequent, unnecessary scans. This strained resources, increased workload, and diverted attention from high-need cases. Clear protocols on scan frequency were seen as vital for improving efficiency and care quality.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;We need guidelines to know, for example, the maximum number of scans a woman need before delivery and the frequency of scans. Now we are scanning randomly.\u0026rdquo; (IDI with healthcare provider)\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eCorruption and inconsistent service fees were significant barriers for clients. Many reported experiencing preferential treatment, bribery, and inconsistent charges for services meant to be free. Some were even denied scans unless they paid, undermining trust in the healthcare system and placing a financial burden on struggling families.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;Payment is also discriminatory. Some women pay, while others don\u0026rsquo;t for the same service. If you don\u0026rsquo;t pay, they\u0026rsquo;ll say the device isn\u0026rsquo;t available and refer us to the hospital, even if it\u0026rsquo;s unnecessary\u0026rdquo; (FGD with Clients).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eDespite these challenges, clients trusted the obstetric ultrasound results, appreciating its clear and consistent diagnoses, which boosted their confidence in their baby\u0026rsquo;s health and healthcare providers, contrasting with previous experiences of conflicting diagnoses.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.10 Embedding and Adaptation Over Time.\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis domain underscores the role of key stakeholders in creating an environment conducive to long-term technology adoption. Key informants reported limited involvement in national decision-making and identified structural and systemic gaps that hinder adaptation. These include the lack of a viable market for medical equipment, insufficiently trained biomedical engineers, and inadequate financial commitment from the government and other stakeholders.\u003c/p\u003e\n\u003cp\u003eA lack of coordination among stakeholders in tailoring digital health technologies to Sierra Leone\u0026apos;s context was a critical barrier. Previous attempts to introduce similar technologies failed due to digitalization challenges and low digital literacy. Financial sustainability was also a concern, particularly with technologies requiring ongoing subscription fees.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;Allocating the budget for the procurement of some BabyCheckers is something to consider in the annual district health budget and planning, but in the case of the BabyChecker device, a yearly subscription fee adds to the funding and sustainability concerns\u0026rdquo; (KII with DHMT Staff).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eDespite these challenges, stakeholders expressed optimism about the device\u0026apos;s potential to address Sierra Leone\u0026apos;s high Maternal Mortality Ratio (MMR). However, they stressed the need for further research to secure buy-in from the Ministry of Health and Sanitation (MoHS) and ensure scalable implementation.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026ldquo;BabyChecker is good for the SL context that has high MMR. As a senior staff, I have a buy-in as I have seen the improvements in the piloted chiefdom. However, more research is needed to get buy-in from the MoHS to scale up\u0026rdquo; (KII with DHMT Staff)\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e3.11 Quality of Care\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eQuality of care emerged as a major concern across all domains, especially regarding the duration of ANC examinations. On average, only 3\u0026ndash;5 minutes were spent per client for both ANC assessments and scanning, far below the 30-40 minutes standard recommended by the focused ANC model (11,23). This limited time reduced care quality and led to client dissatisfaction. The rushed nature of examinations left little opportunity for healthcare providers to offer essential education, counseling, and feedback. Clients expressed frustration with the lack of communication and support.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026quot;No counseling was done before or after the scan. We assume the baby is fine if we don\u0026rsquo;t hear anything from the nurse. If your baby is not well, the nurse will refer you\u0026quot; (FGD with Client).\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eMoreover, observations revealed lapses in privacy and consent. \u0026nbsp;Clients\u0026rsquo; upper bodies were unnecessarily exposed during observations, and consent was rarely obtained. Such practices undermine patient dignity and trust. High patient volumes worsened these problems, as healthcare providers seemed to prioritize efficiency over quality.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eThe study shows that healthcare providers with varying skill levels can perform quality scans in resource-limited settings, indicating that diagnostic imaging can be decentralized to lower-level healthcare workers. This could expand access to essential maternal and fetal health services in underserved areas. The finding that mid- and lower-skilled providers can achieve reasonable scan quality supports the scalability of ultrasound use in resource-constrained environments, especially where skilled radiologists or sonographers are scarce. However, despite overall promising scan clarity, the low-quality threshold among medium- and lower-skilled providers suggests significant variations in performance, potentially due to differences in experience. The higher quality scans at MCHPs compared to higher-level primary facilities like CHCs and CHPs may be due to MCHPs\u0026rsquo; focus on maternal and child health. Healthcare providers at MCHPs are likely more familiar with pregnancy and palpation techniques, and their lower patient volumes might allow for more time and attention per patient, potentially improving scan quality.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe device\u0026rsquo;s user-friendly design and tutorial videos that support independent learning enable task shifting, allowing less specialized workers to perform tasks traditionally reserved for highly trained clinicians. Such task shifting has been recognized as a potential solution to address the limited availability of specialized clinicians and diagnostic infrastructure in LMICs (24) and is also consistent with WHO recommendations on ultrasound and task-shifting (25). However, successful integration requires more than technical training, necessitating a broader focus on healthcare delivery.\u003c/p\u003e\n\u003cp\u003eThe analysis suggests that, with proper training and support, even less experienced healthcare providers can perform quality ultrasound scans in resource-limited settings. Similar studies show that targeted training enables individuals with no prior ultrasound experience to conduct basic obstetric scans effectively (26\u0026ndash;32).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eClients\u0026apos; acceptance of ultrasound services has the potential to positively influence ANC attendance and facility deliveries, which could lead to improved maternal and fetal outcomes. Several studies have shown that ultrasound services increase the frequency of ANC visits (12,33). Rising ANC attendance could also facilitate the integration of other maternal and child health interventions like immunizations, malaria screenings, and health education. However, while these preliminary findings are promising, further research is needed to explore the long-term impact of obstetric ultrasound on maternal health outcomes. Key considerations include sustained ANC attendance beyond initial visits, potential scan overuse, and the broader implications of technology-driven care on clinical decision-making. While participants believed the device could reduce maternal and fetal mortality through early detection and referrals, verifying this is difficult without systematic record audits. Thus, evaluating ultrasound\u0026rsquo;s effectiveness requires a broader look at maternal and neonatal health indicators.\u003c/p\u003e\n\u003cp\u003eWhile providers confidently integrated ultrasound into ANC, there was a tendency to over-rely on the device, sometimes at the expense of essential clinical procedures such as physical examinations and vital sign checks. This substitution of comprehensive care may have been influenced by the absence of clear and standardized guidelines, a concern echoed in previous studies reporting the omission of fundamental clinical procedures when ultrasound is available\u0026nbsp;(34,35). Although community acceptance of the technology was high, overuse risks diminishing core clinical skills and straining already limited resources. Moreover, while the device is user-friendly, some healthcare providers, particularly those with lower formal education, faced challenges integrating the results of the device into broader maternal and child health (MCH) service delivery, potentially affecting the consistency and quality of care.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThese challenges are further compounded by broader system-level barriers, including unreliable power supply, poor internet connectivity, supply chain inefficiencies, and a lack of infrastructure, obstacles also identified in other research (36,37). Additionally, despite WHO and Sierra Leone\u0026rsquo;s ANC guidelines emphasizing the importance of thorough physical examinations, these are often overlooked unless clients report symptoms, which can compromise accurate diagnosis and the complementary role of obstetric ultrasound. Patients in other studies have also highlighted the need for adequate consultation time and comprehensive assessments during ANC visits (38,39). Addressing these gaps requires investment in both health system infrastructure and provider training that goes beyond technical device operation. Digital health tools like ultrasound should complement, not replace, established medical practices and patient-centered care protocols. A holistic approach that balances technological integration with clinical judgment is essential to ensure the delivery of high-quality maternal healthcare.\u003c/p\u003e\n\u003cp\u003eThough the device may ease provider workloads, concerns about corruption and inequitable access persist, underscoring the need for stronger governance and accountability. Funding, particularly for PHC, emerged as a critical factor affecting the DHMT\u0026apos;s performance to provide essential services, maintain medical supplies, and support healthcare providers effectively. Despite global calls for increased PHC funding, including the Lancet Global Health Commission\u0026rsquo;s recommendations (40), the study highlights that underfunding continues to exacerbate inequities in healthcare access, disproportionately affecting lower-income populations.\u003c/p\u003e\n\u003cp\u003eA key limitation of this study is that the quantitative data were collected during the pilot phase, rather than within a structured study setup. As a result, the research had to work with the available data, which presents challenges for data interpretation and generalizability. This highlights the need for more rigorous data collection in future implementation research.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study shows that AI-enabled obstetric ultrasound technology is a practical and usable tool for healthcare providers in Sierra Leone. Despite varying skill levels, providers were able to perform quality scans linked to the device\u0026rsquo;s user-friendly design and tutorial videos, which supported independent learning and task shifting. The device\u0026apos;s simplicity and ability to produce clear, analysable scans make it a viable solution for primary healthcare settings with limited access to specialized care. However, challenges remain, including the need for more comprehensive training, better integration of ultrasound findings into broader maternal care, and overcoming infrastructure issues like unreliable power and inadequate supplies. Addressing these challenges, along with establishing appropriate guidelines for device use, could enhance its effectiveness and improve maternal and child health outcomes. While further research and infrastructure investment are necessary for scaling, the findings demonstrate that the device is a valuable tool for improving obstetric care in resource-limited environments.\u0026nbsp;\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate:\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eEthical approval was obtained from KIT (reference S-208) and the Sierra Leone Ethics and Scientific Review Committee (reference 001/06/2023). Informed consent was obtained from all participants, ensuring understanding of research procedures, potential risks, and benefits, with the opportunity to withdraw voluntarily.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication:\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eParticipants provided consent for the publication of findings.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials:\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eData sharing is restricted due to confidentiality agreements. Access to anonymized data may be available upon request and approval from the relevant authorities.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests:\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study received no external funding. However, the study received support from Delft Imaging for data collection but remains impartial.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding:\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo direct financial support was provided for this research.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors\u0026apos; contributions:\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAmie Lompri Koroma (ALK) and Abu Dim Din Sesay (ADS) served as the lead researchers, overseeing the entire processes of the study including data collection and analysis. Irene de Vries (IV), Mirjam Bakker (MB), and Anke van der Kwaak (AvdK) supervised the study from conceptualization to the presentation of findings, providing technical support and capacity-building assistance. Alhassan Kanu (AK) supported the review and validation of the findings whilst Abdul Mac Falama (AMF) was involved in the implementation. AMF also played a key role in the pilot project\u0026apos;s implementation as the district medical officer of Tonkolili DHMT, where the project was conducted. Enya Sequin contributed valuable insights into the device and its pilot implementation in Tonkolili district, provided access to the quantitative data.\u003c/p\u003e\n\u003cp\u003eALK and ADS drafted the original manuscript, which underwent multiple rounds of review and editing by IV, MB, AvdK, AK, AMF, and ES, who also provided critical feedback on the advanced versions. All authors reviewed and approved the final manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors extend their sincere appreciation to the healthcare providers, pregnant and lactating women, and staff members of the Tonkolili District Health Management Team in Sierra Leone for their invaluable contributions to this study. We acknowledge Delft Imaging for funding the transportation costs during the primary data collection phase.\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eWHO Antenatal Care Recommendations for a Positive Pregnancy Experience. Maternal and Fetal Assessment Update: Imaging Ultrasound Before 24 Weeks of Pregnancy. 1st ed. Geneva: World Health Organization; 2022. 1 p. \u003c/li\u003e\n\u003cli\u003eDestigter K, Morey G, Garra B, Rielly M, Anderson M, Kawooya M, et al. Low-Cost Teleradiology for Rural Ultrasound. In 2011. p. 290\u0026ndash;5. \u003c/li\u003e\n\u003cli\u003eChukwu E, Garg L, Foday E, Konomanyi A, Wright R, Smart F. Electricity, Computing Hardware, and Internet Infrastructures in Health Facilities in Sierra Leone: Field Mapping Study. JMIR Med Inform. 2022 Feb 3;10(2):e30040. \u003c/li\u003e\n\u003cli\u003eInternational Telecommunication Union Development Sector. Measuring digital development Facts and figures 2020.FactsFigures2020.pdf [Internet]. [cited 2024 Nov 3]. Available from: https://www.itu.int/en/ITU-D/Statistics/Documents/facts/FactsFigures2020.pdf\u003c/li\u003e\n\u003cli\u003eUnited Nations Population Fund (UNFPA) Sierra Leone. Leone S. Sierra Leone Rapid Emergency Obstetric and Newborn Care (EmONC) Assessment 2017. Available from: https://sierraleone.unfpa.org/en/publications/sierra-leone-rapid-emergency-obstetric-and-newborn-care-emonc-assessment-2017\u003c/li\u003e\n\u003cli\u003eGomes RG, Vwalika B, Lee C, Willis A, Sieniek M, Price JT, et al. A mobile-optimized artificial intelligence system for gestational age and fetal malpresentation assessment. Commun Med. 2022 Oct 11;2(1):1\u0026ndash;9. \u003c/li\u003e\n\u003cli\u003eDiagnostic Image Analysis Group [Internet]. [cited 2024 Nov 4]. BabyChecker: AI for low-cost prenatal ultrasound. Available from: https://www.diagnijmegen.nl/projects/babychecker/\u003c/li\u003e\n\u003cli\u003eArroyo J, Marini TJ, Saavedra AC, Toscano M, Baran TM, Drennan K, et al. No sonographer, no radiologist: New system for automatic prenatal detection of fetal biometry, fetal presentation, and placental location. PLOS ONE. 2022 Feb 9;17(2):e0262107. \u003c/li\u003e\n\u003cli\u003eToscano M, Marini TJ, Drennan K, Baran TM, Kan J, Garra B, et al. Testing telediagnostic obstetric ultrasound in Peru: a new horizon in expanding access to prenatal ultrasound. BMC Pregnancy Childbirth. 2021 Apr 26;21:328. \u003c/li\u003e\n\u003cli\u003eDougherty A, Kasten M, DeSarno M, Badger G, Streeter M, Jones DC, et al. Validation of a Telemedicine Quality Assurance Method for Point-of-Care Obstetric Ultrasound Used in Low-Resource Settings. J Ultrasound Med. 2021;40(3):529\u0026ndash;40. \u003c/li\u003e\n\u003cli\u003eWorld Health Organization. WHO recommendations on antenatal care for a positive pregnancy experience [Internet]. Geneva: World Health Organization; 2016 [cited 2024 Sep 19]. 152 p. Available from: https://iris.who.int/handle/10665/250796\u003c/li\u003e\n\u003cli\u003eMbuyita S, Tillya R, Godfrey R, Kinyonge I, Shabani J, Mbaruku G. Effects of introducing routinely ultrasound scanning during Ante Natal Care (ANC) clinics on number of visits of ANC and facility delivery: A cohort study. Archives of Public Health. 2015 Sep 8;73:36. \u003c/li\u003e\n\u003cli\u003eLiu X, Faes L, Kale AU, Wagner SK, Fu DJ, Bruynseels A, et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 2019 Oct 1;1(6):e271\u0026ndash;97. \u003c/li\u003e\n\u003cli\u003eIv SNM, Shrivastava D, Raka MS, Iv SNM, Shrivastava D, Raka MS. A Comprehensive Review of the Role of Artificial Intelligence in Obstetrics and Gynecology. Cureus [Internet]. 2023 Feb 12 [cited 2023 Jul 24];15(2). Available from: https://www.cureus.com/articles/122226-a-comprehensive-review-of-the-role-of-artificial-intelligence-in-obstetrics-and-gynecology\u003c/li\u003e\n\u003cli\u003eAI in Radiology: Pros \u0026amp; Cons, Applications, and 4 Examples.V7 [Internet]. [cited 2023 Jul 24]. Available from: https://www.v7labs.com/blog/ai-in-radiology.\u003c/li\u003e\n\u003cli\u003eHe F, Wang Y, Xiu Y, Zhang Y, Chen L. Artificial Intelligence in Prenatal Ultrasound Diagnosis. Front Med [Internet]. 2021 [cited 2023 Jul 24];8. Available from: https://www.frontiersin.org/articles/10.3389/fmed.2021.729978\u003c/li\u003e\n\u003cli\u003eKim YH. Artificial intelligence in medical ultrasonography: driving on an unpaved road. Ultrasonography. 2021 Jul;40(3):313\u0026ndash;7. \u003c/li\u003e\n\u003cli\u003eHeuvel, T.L.A. van den. Automated low-cost ultrasound: improving antenatal care in resource-limited settings.2019.199000.pdf [Internet]. [cited 2025 Apr 6]. Available from: https://repository.ubn.ru.nl/bitstream/handle/2066/199000/199000.pdf?sequence=1\u0026amp;isAllowed=y\u003c/li\u003e\n\u003cli\u003eMatthew J, Skelton E, Day TG, Zimmer VA, Gomez A, Wheeler G, et al. Exploring a new paradigm for the fetal anomaly ultrasound scan: Artificial intelligence in real time. Prenat Diagn. 2022;42(1):49\u0026ndash;59. \u003c/li\u003e\n\u003cli\u003eDrukker L, Noble JA, Papageorghiou AT. Introduction to artificial intelligence in ultrasound imaging in obstetrics and gynecology. Ultrasound Obstet Gynecol. 2020;56(4):498\u0026ndash;505. \u003c/li\u003e\n\u003cli\u003eDiagnostic Image Analysis Group [Internet]. [cited 2023 Jul 24]. BabyChecker: AI for low-cost prenatal ultrasound. Available from: https://www.diagnijmegen.nl/projects/babychecker/\u003c/li\u003e\n\u003cli\u003eGreenhalgh T, Wherton J, Papoutsi C, Lynch J, Hughes G, A\u0026rsquo;Court C, et al. Beyond Adoption: A New Framework for Theorizing and Evaluating Nonadoption, Abandonment, and Challenges to the Scale-Up, Spread, and Sustainability of Health and Care Technologies. J Med Internet Res. 2017 Nov 1;19(11):e367. \u003c/li\u003e\n\u003cli\u003evon Both C, Fle\u0026beta;a S, Makuwani A, Mpembeni R, Jahn A. How much time do health services spend on antenatal care? Implications for the introduction of the focused antenatal care model in Tanzania. BMC Pregnancy Childbirth. 2006 Jun 23;6(1):22. \u003c/li\u003e\n\u003cli\u003eAbrokwa SK, Ruby LC, Heuvelings CC, B\u0026eacute;lard S. Task shifting for point of care ultrasound in primary healthcare in low- and middle-income countries-a systematic review. EClinicalMedicine. 2022 Mar 6;45:101333. \u003c/li\u003e\n\u003cli\u003eWorld Health Organization, PEPFAR, UNAIDS. Task shifting : rational redistribution of tasks among health workforce teams : global recommendations and guidelines. 2007;88. \u003c/li\u003e\n\u003cli\u003eKozuki N, Mullany LC, Khatry SK, Ghimire RK, Paudel S, Blakemore K, et al. Accuracy of Home-Based Ultrasonographic Diagnosis of Obstetric Risk Factors by Primary-Level Health Care Workers in Rural Nepal. Obstet Gynecol. 2016 Sep;128(3):604. \u003c/li\u003e\n\u003cli\u003eKimberly HH, Murray A, Mennicke M, Liteplo A, Lew J, Bohan JS, et al. Focused Maternal Ultrasound by Midwives in Rural Zambia. Ultrasound Med Biol. 2010 Aug 1;36(8):1267\u0026ndash;72. \u003c/li\u003e\n\u003cli\u003eNeufeld LM, Wagatsuma Y, Hussain R, Begum M, Frongillo EA. Measurement error for ultrasound fetal biometry performed by paramedics in rural Bangladesh. Ultrasound Obstet Gynecol. 2009;34(4):387\u0026ndash;94. \u003c/li\u003e\n\u003cli\u003eRijken MJ, Lee SJ, Boel ME, Papageorghiou AT, Visser GHA, Dwell SLM, et al. Obstetric ultrasound scanning by local health workers in a refugee camp on the Thai\u0026ndash;Burmese border. Ultrasound Obstet Gynecol. 2009;34(4):395\u0026ndash;403. \u003c/li\u003e\n\u003cli\u003eKodaira Y, Pisani L, Boyle S, Olumide S, Orsi M, Adeniji AO, et al. Reliability of ultrasound findings acquired with handheld apparatuses to inform urgent obstetric diagnosis in a high-volume resource-limited setting. Int J Gynecol Obstet. 2021;153(2):280\u0026ndash;6. \u003c/li\u003e\n\u003cli\u003eViner AC, Membe-Gadama G, Whyte S, Kayambo D, Masamba M, Makwakwa E, et al. Training in Ultrasound to Determine Gestational Age (TUDA): Evaluation of a Novel Education Package to Teach Ultrasound-Naive Midwives Basic Obstetric Ultrasound in Malawi. Front Glob Womens Health [Internet]. 2022 [cited 2023 Jul 20];3. Available from: https://www.frontiersin.org/articles/10.3389/fgwh.2022.880615\u003c/li\u003e\n\u003cli\u003eVinayak S, Sande J, Nisenbaum H, Nols\u0026oslash;e CP. Training Midwives to Perform Basic Obstetric Point-of-Care Ultrasound in Rural Areas Using a Tablet Platform and Mobile Phone Transmission Technology\u0026mdash;A WFUMB COE Project. Ultrasound Med Biol. 2017 Oct;43(10):2125\u0026ndash;32. \u003c/li\u003e\n\u003cli\u003eAbawollo HS, Argaw MD, Tsegaye ZT, Beshir IA, Guteta AA, Heyi AF, et al. Effects of institutionalizing limited obstetric ultrasound services on utilization of maternal and neonatal health services: a pre-post study [Internet]. In Review; 2022 Jan [cited 2023 Jul 20]. Available from: https://www.researchsquare.com/article/rs-1297883/v1\u003c/li\u003e\n\u003cli\u003eEl-Jardali F, Fadlallah R. A review of national policies and strategies to improve quality of health care and patient safety: a case study from Lebanon and Jordan. BMC Health Serv Res. 2017 Aug 16;17:568. \u003c/li\u003e\n\u003cli\u003eTautz S, Jahn A, Molokomme I, G\u0026ouml;rgen R. Between fear and relief: how rural pregnant women experience foetal ultrasound in a Botswana district hospital. Soc Sci Med 1982. 2000 Mar;50(5):689\u0026ndash;701. \u003c/li\u003e\n\u003cli\u003eChukwu E, Garg L, Foday E, Konomanyi A, Wright R, Smart F. Electricity, Computing Hardware, and Internet Infrastructures in Health Facilities in Sierra Leone: Field Mapping Study. JMIR Med Inform. 2022 Feb 3;10(2):e30040. \u003c/li\u003e\n\u003cli\u003eConteh E, Okereke M, Turay FU, Bah AS, Muhsinah A. The need for a functional pharmaceutical industry in Sierra Leone: lessons from the COVID-19 pandemic. J Pharm Policy Pract. 2022 Jul 27;15(1):46. \u003c/li\u003e\n\u003cli\u003eAndersen CA, Brodersen J, Rudb\u0026aelig;k TR, Jensen MB. Patients\u0026rsquo; experiences of the use of point-of-care ultrasound in general practice \u0026ndash; a cross-sectional study. BMC Fam Pract. 2021 Jun 18;22(1):116. \u003c/li\u003e\n\u003cli\u003eStark S, Worm L, Kluge M, Roos M, Burggraf L. The patient satisfaction in primary care consultation\u0026mdash;Questionnaire (PiC): An instrument to assess the impact of patient-centred communication on patient satisfaction. PLOS ONE. 2021 Jul 16;16(7):e0254644. \u003c/li\u003e\n\u003cli\u003eHanson K, Brikci N, Erlangga D, Alebachew A, De Allegri M, Balabanova D, et al. The Lancet Global Health Commission on financing primary health care: putting people at the centre. Lancet Glob Health. 2022 May;10(5):e715\u0026ndash;72. \u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-pregnancy-and-childbirth","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"prch","sideBox":"Learn more about [BMC Pregnancy and Childbirth](http://bmcpregnancychildbirth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/prch/default.aspx","title":"BMC Pregnancy and Childbirth","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Maternal health, Antenatal care, Obstetric ultrasound, Artificial Intelligence, Sufficient Quality, Task shifting, Healthcare provider, Sierra Leone","lastPublishedDoi":"10.21203/rs.3.rs-6710084/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6710084/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground:\u003c/h2\u003e\u003cp\u003eIn Sierra Leone, access to WHO-recommended obstetric ultrasound before 24 weeks of gestation is limited. The introduction of Artificial Intelligence (AI)-enabled smartphone-based obstetric ultrasound offers potential for improving accessibility and quality of maternal healthcare. This study, conducted in 2023, evaluates the usability, practicality, and sustainable adoption of this technology in the Tonkolili district, where it has been implemented as part of a pilot program since 2020.\u003c/p\u003e\u003ch2\u003eMethods:\u003c/h2\u003e\u003cp\u003eA mixed-methods approach was used, analyzing quantitative data from 2,315 obstetric scans performed by 81 healthcare providers across seven health facilities in Tonkolili district from October 2020 to March 2023. Data were analyzed using Stata version 17, applying a mixed-effects logistic regression model to identify factors influencing scan quality. Primary qualitative data were collected through interviews, focus group discussions, and observations with healthcare providers and clients. The Non-Adoption, Abandonment, Scale-up, Spread, and Sustainability (NASSS) framework informed the topic guide and guided qualitative analysis, which was conducted using NVIVO software.\u003c/p\u003e\u003ch2\u003eResults:\u003c/h2\u003e\u003cp\u003eThe study revealed that 83.8% of obstetric scans were of sufficient quality for remote or AI analysis, with 59% of healthcare providers achieving the 80% threshold of sufficient quality scans, based on data distribution. Tutorial videos (OR: 14.1, 95% CI: 6.40-31.12, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and healthcare provider's skill sets were key factors in improving scan quality. The device was easily adopted by healthcare providers and well-received by clients. However, infrastructure limitations, supply chain issues, lack of comprehensive guidelines, and funding constraints were identified as barriers to its broader impact.\u003c/p\u003e\u003ch2\u003eConclusion:\u003c/h2\u003e\u003cp\u003eAI-enabled obstetric ultrasound is a practical tool for healthcare providers in Sierra Leone. With the help of tutorial videos, healthcare providers were able to perform quality scans despite varying skill levels. The device\u0026rsquo;s simplicity and ability to produce clear, analysable scans make it a valuable tool for improving maternal healthcare at the PHC level. However, challenges remain, including the need for more comprehensive training, better integration of ultrasound findings into broader care, and infrastructure improvements. Addressing these barriers and ensuring proper guidelines will enhance its effectiveness in improving maternal and child health outcomes.\u003c/p\u003e","manuscriptTitle":"Evaluating the Usability and Practicality of AI-Enabled Smartphone-based Obstetric Ultrasound in Sierra Leone: A Mixed-Methods Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-18 13:06:08","doi":"10.21203/rs.3.rs-6710084/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-30T17:06:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-20T23:38:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"143916087135549918407865878328825172425","date":"2025-09-17T01:27:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"104084554334352694320067165084215003951","date":"2025-09-16T14:59:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"51438758608538527996236511526925196452","date":"2025-09-16T06:53:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"218131058586996320796233756900820759177","date":"2025-09-15T23:21:39+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-08-16T08:24:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"294844294789052492299442291541825208751","date":"2025-08-16T07:26:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"70268137956412123001923090225412554459","date":"2025-07-24T14:29:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-07-13T22:02:15+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-05-23T12:19:03+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-22T04:33:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-22T04:30:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Pregnancy and Childbirth","date":"2025-05-20T17:31:24+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-pregnancy-and-childbirth","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"prch","sideBox":"Learn more about [BMC Pregnancy and Childbirth](http://bmcpregnancychildbirth.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/prch/default.aspx","title":"BMC Pregnancy and Childbirth","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"985f1885-13d7-4ff2-ad3f-7c1c26b357d2","owner":[],"postedDate":"July 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-05-04T16:10:08+00:00","versionOfRecord":{"articleIdentity":"rs-6710084","link":"https://doi.org/10.1186/s12884-026-09152-8","journal":{"identity":"bmc-pregnancy-and-childbirth","isVorOnly":false,"title":"BMC Pregnancy and Childbirth"},"publishedOn":"2026-04-27 15:57:11","publishedOnDateReadable":"April 27th, 2026"},"versionCreatedAt":"2025-07-18 13:06:08","video":"","vorDoi":"10.1186/s12884-026-09152-8","vorDoiUrl":"https://doi.org/10.1186/s12884-026-09152-8","workflowStages":[]},"version":"v1","identity":"rs-6710084","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6710084","identity":"rs-6710084","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}