Validation of several TB-CAD chest-X-ray applications in individuals with presumptive TB visiting peripheral health institutes in Delhi State

Validation of several TB-CAD chest-X-ray applications in individuals with presumptive TB visiting peripheral health institutes in Delhi State | 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 Article Validation of several TB-CAD chest-X-ray applications in individuals with presumptive TB visiting peripheral health institutes in Delhi State Sandra Vivian Kik, Shruti Goel, Vindhya Vatsyayan, Sam Linsen, and 9 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7739612/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Before deploying digital X-ray with Computer Aided Detection (CAD) as a triage tool for tuberculosis (TB), selecting an appropriate product and threshold score is essential to identify patients requiring confirmatory TB testing. We conducted a combined retrospective case-control and prospective cross-sectional study to evaluated the performance and optimal threshold for qXR v3 (Qure.ai, India) as well as six additional CAD products in individuals with presumptive TB attending peripheral health institutes (PHIs) in India. Accuracy was assessed against a microbiological reference standard separately for adults (≥16 year) and children (6-16 year). Among 1245 adults (315 TB-positive, 930 TB-negative) and 159 children (39 TB-positive, 120 TB-negative), qXR demonstrated high accuracy both in adults (AUCROC: 0.88 [95% CI of 0.85-0.90], and children (AUCROC: 0.95 [95% CI 0.89-1.0]). and performed as good as the radiologist in both groups. Sensitivity increased with minimal loss in specificity when using the vendor recommended threshold. CAD4TB, Insight CXR, DrAid, and Genki also demonstrated high accuracy (AUCROC: adults ≥0.80, AUCROCs children ≥0.90), while InferRead DR Chest and Radify Chest performed less well. Local validation confirmed high accuracy for qXR and several other products, in identifying TB in adults and children in India, supporting their potential implementation in similar settings. Health sciences/Diseases Health sciences/Health care Health sciences/Medical research Biological sciences/Microbiology Tuberculosis Computer Aided Detection Screening Active case finding India Chest X ray Figures Figure 1 Figure 2 Figure 3 Introduction Tuberculosis (TB) is a leading cause of morbidity and mortality worldwide, with an estimated 10.8 million new cases and 1.25 million deaths annually. 1 Despite progress in TB control, the disease remains a significant public health challenge. Since 2015, the global TB incidence rate has decreased by 8.3%, but is falling short of the targeted 50% reduction by 2025 as was set out in the End TB Strategy . 1 To reduce the gap in case detection intensified efforts are required, particularly in high-burden countries. 2 India, home to the largest TB burden, accounts for over a quarter of global cases. Since 2015, India’s initiatives for early detection, treatment initiation, and community engagement to increase awareness and patient support have led to a 16% decline in TB incidence and an 18% reduction in mortality. 1 , 3 Yet, approximately 0.23 million estimated TB patients remain undiagnosed or unreported each year, including a significant number of patients with pulmonary TB (PTB). Identifying these "missing cases" is essential to break the chain of transmission. Targeted testing in primary healthcare settings is key to improving case detection. 4 One approach to increase case finding at primary care levels is the use of digital chest X-rays (CXR) systems combined with computer-aided detection (CAD) software to identify individuals with possible pulmonary TB. CAD technology facilitates faster and more accurate diagnosis and since 2021 the World Health Organization has recommended the use of this technology as an initial screening or triage test for adults. 5 Early 2025, a number of specific CAD products (and versions) were evaluated and found to meet the WHO performance standards, opening the door for country consideration. 6 CAD products identify radiographic abnormalities indicative of TB by providing a TB abnormality score. When this score is above a certain threshold, individuals are referred for confirmatory testing. Most CAD developers do not recommend the use of their product in young children (< 2 years), but suggest they could be used in older childer. 7 Evidence on the accuracy of CAD in children is scarce. The radiographic presentation of TB in infants and young children differs from that in adults and limited access to training datasets from children has hampered the development of child-specific CAD models. 8 Besides age, the CAD score distribution is influenced by other factors including country of origin, HIV status, smear status, symptoms, gender, and a prior TB history. 9–13 Thus, the prevalence of these factors in the target population may affect CAD score distribution. It is therefore vital to establish an appropriate threshold score for CAD systems to determine which CXRs are suggestive of PTB and warrant confirmatory testing. 5 , 14 , 15 We conducted a thresold validation study in accordance with the standardized calibration protocol developed by the WHO Global TB Programme and the Special Program for Research and Training in Tropical Diseases (TDR) 16 , to determine the accuracy and establish a threshold score for qXRv3 (Qure.ai, India) as the CAD product of choice for triaging individuals with presumptive TB at Peripheral Health Institutions (PHI) in Delhi. Additionally, we evaluate the accuracy of six other additional commercial CAD products, all also part of the recent WHO policy review,(CAD4TB v7, Delft Imaging, The Netherlands; Insight CXR v3.1.5.3, Lunit Insight, South Korea; Genki v3.4-2, Deeptek, India; InferRead DR Chest v1.0.1.1, Infervision, China; DrAid v2.4.4-6, Vinbrain, Vietnam; Radify Chest v3.8.0, Envisionit Deep AI, UK) using the same dataset to explore whether alternative CAD products can achieve the same accuracy and could be considered for broader implementation in similar settings in India. Materials and Methods Study design This study adopted a combined retrospective case-control and prospective cross-sectional design to create a representative chest X-rays (CXR) dataset from individuals with presumptive TB attending primary care facilities in India. Conducted under standard programmatic settings, a solely prospective study was deemed unfeasible due to the relatively low prevalence of TB among general out-patient department (OPD) attendees and the large number of required CXRs from confirmed TB cases, which would have resulted in an impractically long enrolment period. To address this, retrospective and prospective data were pooled, as suggested by the generic CAD calibration protocol. 16 Study setting The study took place at three PHIs (Badarpur, Jahangirpuri, Sangam Vihar) in Delhi and a nearby TB Chest Clinic (CC) at a district hospital (Nehru Nagar). Retrospective data came from the chest clinic, while prospective data were collection at PHIs, selected based on high visitor rates (150-200 daily), and readiness in terms of dedicated space for digital X-ray installation. Before the study, presumptive TB patients at these PHIs underwent sputum smear microscopy; if positive, they were referred for molecular testing and treatment at the chest clinic. Patients with a negative smear but persistent symptoms were also referred for evaluation by a chest physician, requiring a chest X-ray and other tests. However, there was no follow-up mechanism in place potentially leading to delay in proper diagnosis of such patients. Prospective cross-sectional data collection An ultra-portable digital chest-X-ray (dCXR) device (FDR Xair XD 2000, Fujifilm, Tokyo, Japan), without CAD, was installed at each PHI, with project staff trained by Fujifilm on its use. Prospective data collection occurred from October 1, 2022 to December 31, 2022, with at least 1.5 months of consecutive data collection at each site. OPD visitors were screened for symptoms and risk factors to verify eligibility. The following individuals were eligible for inclusion: 1) Adults and children (aged ≥10 years) presented with at least one TB symptom as per the WHO 4 symptom-screen (W4SS, prolonged cough ≥2 weeks, haemoptysis, night sweats, weight loss or fever). 2) Adults with suspected household exposure to TB. 3) Children (≥6 years) with HIV or household TB exposure. Exclusion criteria included individuals on TB treatment and pregnant women. Adults provided written informed consent, while parental consent and child oral assent were obtained per national ethical guidelines. Digital CXRs were captured, and demographic and clinical data (symptoms, comorbidities including HIV and diabetics) were recorded electronically. All participants received a CXR, followed by on-the-spot sputum collection for molecular testing, regardless of their CXR results, as part of the study. Additionally, these patients were examined by a medical officer and referred for smear microscopy and/or other tests as per the standard of care. Test results were integrated into the database. All TB cases were refferred for treatment. Retrospective case-control data collection CC attendees included individuals with presumptive TB, either as first-time visitors or referred from nearby PHIs for CXR or molecular testing. Before the study initiation, the selected CC was one of the few sites where digital CXRs in DICOM format had been available in previous years due to the presence of a Computed Radiography system (Fujifilm), which allowed for compatibility with retrospective data collection requirements. Digital CXRs (October 2020 -August 2022) were extracted from the Picture Archiving and Communication System (PACS) system and assessed for inclusion. Extracted metadata included patient ID, name, gender, age, date of birth and CXR acquisition data. CXRs were codified to a unique ‘CXR key’ which was a concatenated field of patient name, age and gender. Next, presumptive TB registrations (Q3 2020 to Q4 2022) were extracted from India’s national TB surveillance and patient management system (Nikshay), the Nucleic Acit Amplification Test (NAAT) register (all presumptive individuals who received a NAAT test), the Truenat register (all presumptive individuals who received a Truenat test (Molbio, Goa, India)), the current facility register (all diagnosed TB patients currently seeking care at the chest clinic), and the diagnosed facility register (all TB patients who were diagnosed at the chest clinic). A ‘Nikshay key’ (concatenated patient name, age and gender) was used for record linkage via an 80% fuzzy match (through an Excel add-on) between the CXR key and the Nikshay key. Additional filters were used ensuring accurate matching including: 1) a 100% match on patient gender; 2) an age difference ≤1 year (to account for recall errors or data entry mistakes); 3) a maximum 30-day difference between CXR and the diagnosis date (to account for delays but exclude CXRs conducted for disease progression monitoring). Data was deduplicated and anonymized before sharing with radiologists for re-reading and the data team for CAD analysis. Retrospective CXR inclusion criteria matched prospective eligibility requirements, ensuring availability of molecular test results. Where possible, the following data was extracted from Nikshay and further complemented by information from the patient’s records; age, gender, HIV status, history of TB, history of smoking, household contact, CXR acquisition date, presence of TB symptoms, sputum smear result, NAAT test and result, culture result, comorbidities. Anonymization All digital CXRs (Digital Imaging and Communications in Medicine (DICOM format)) were de-identified using DICOM Anonymizer software and a unique patient identifier replaced personal information before secure upload to FIND’s server to allow for CAD analysis. Index test: CAD software installation and CXR processing The primary aim of the study was to evaluate qXR version 3 (Qure.AI, Mumbai, India) as the selected product for a subsequent implementation study in the participating PHIs. However, to increase the usefulness of this unique dataset, and to allow for head-to-head product comparison, we also evaluated the following six additional products: CAD4TB version 7 (Delft Imaging, ‘s-Hertogenbosch, The Netherlands), Insight CXR version 3.1.5.3 (Lunit, Seoul, South Korea), Genki version 3.4-2 (DeepTek Medical Imaging Private Limited, Pune, India), InferRead DR Chest version 1.0.1.1 (InferVision, Beijing, China), DrAid version 2.4 4-6 (VinBrain, Hanoi, Vietnam), Radify Chest version 3.8.0 (Envisionit Deep AI, Cobham, UK). All these products were also part of the recent WHO policy review. CAD products were installed on separate virtual machines within FIND’s digital infrastructure for independent accuracy assessment. 17 Vendors were restricted from access post-installation. CXRs were processed per vendor instructions. Each product produced a TB abnormality score ranging between 0-1 (qXR, Genki, InferRead DR Chest, DrAid, Radify Chest) or 0-100 (CAD4TB, Insight CXR) and scores were extracted and merged for further analysis. CXRs that could not be processed by one or more CAD products were excluded from the analysis to eanable a head-to-head comparison between products. Separate analyses were conducted for adults (≥16 years) and children (6-16 years). CAD products had differing minimum age recommendations, and some have a separate paediatric model. An age cut-off of 16 years was chosen to distinghuis children from adults, because this aligned with the majority of the vendor recommendations (Table 1). Only for Genki and Radify Chest, the recommended age for the peadiatric model was lower (15 years) or higher (18 years).For the analysis in children, for qXR and CAD4TB, the same model as for adults was used. For Genki, DrAid and Radify Chest, a different, dedicated paediatric TB model was used. InferRead DR Chest is not recommended for use in individuals below 16 years and was therefore not evaluated in children. Since Insight CXR is only recommended for age 13 years and above, the analysis for this product was restricted to children between 13 and 16 years. Reference standard: microbiologically confirmation The accuracy of CAD products was compared against a microbiological reference standard (MRS). TB cases were defined as those with a positive microbiological test (Xpert, Truenat, Line Probe Assay or culture) on a baseline sputum sample collected within 30 days of the CXR date, while non-TB cases were those who had only negative microbiological test results. Individuals with missing or indeterminate test results were excluded from the analysis. Comparator test: CXR interpretation by radiologist A single radiologist retrospectively interpreted all CXRs, classifying them into five categories: 1) Abnormal CXR with findings suggestive of active TB; 2) Abnormal CXR with findings suggesting of old, healed TB; 3) Abnormal CXR not suggestive of TB; 4) Normal CXR; 5) Other, non-pulmonary findings. Images classified as category 1 were considered TB, while all others were non-TB. The radiologist was blinded to the TB test results and CAD scores. Sample size The sample size was calculated to detect CAD products meeting the WHO’s target product profile (WHO TPP) (90% sensitivity, 70% specificity) with 5% alpha and 80% power. This required minimally 283 confirmed TB cases and 660 non-TB cases. Statistical analysis Categorical variables were reported as counts and percentages, and continuous variables as medians and interquartile ranges (IQRs). Receiver Operating Characteristics (ROC) analysis was conducted to compute the area under the curve (AUC) with 95% confidence interval (CI). For the threshold analysis, thresholds were selected that achieved 90% sensitivity, 80% specificity, matched with the sensitivity or specificity of the radiologist and those recommended by the vendor. Analyses were stratified by age group (adults ≥16 years, vs children 6-16 years). Ethical approval The study was approved by the Institutional Review Board of Maulana Azad Medical College (IRB number IEC/MAMC/86/04/2021/No491) on October 18, 2021. All methods were performed in accordance with the relevant guidelines and regulations, including the Declaration of Helsinki. Written informed consent was obtained from all participants aged 18 years and older, and from the legal guardians of participants under the age of 18 years. Role of the funding source The funder had no role in the study design, data collection, analysis, interpretation, or manuscript preparation. Results A total of 1209 individuals with presumptive TB attended, with 1096 (91%) providing consent and undergoing dCXR. Due to missing age, gender, NAAT results or radiological test results, 213 individuals were excluded. . Lastly, 7 more were excluded due to CXR CAD processing issues, leaving a total of 876 presumptive TB cases (772 adults; 41 TB positive, 731 TB negative, and104 children; 2 TB positive and 102 TB negative) for analysis. Retrospective data collection from the chest clinic added 535 presumptive TB cases (480 adults, 55 children). Seven digital CXRs (all from adults) were excluded due to CAD processing issues, leaving 528 individuals (473 adults; 274 TB-positive, 199 TB-negative and 55 children; 37 TB-positive, 18 TB-negative) with complete data. As a result, the combined prospective and retrospective dataset included 1404 participants (1245 adults, 159 children) for analysis including 315 TB-positive and 930 TB-negative adults, and 39 TB-positive and 120 TB-negative children (Figure 1). All together, we had data from. The majority of adults fell in the 16-35 year age category and nearly 47% were female. Risk factors data were limited and not systematically captured, but suggested low prevalence of HIV and diabetes in this population. qXR performance in adults and children The receiver operatoring characteristic and overall performance (AUCROC) of qXR against the microbiological reference standard are shown in Figures 2 (adults) and 3 (children). qXR had an AUCROC of 0.88 (95% CI of 0.85-0.90) in adults and 0.95 (95% CI 0.89-1.00) in children. Results for qXR v4 are shown in Supplement Fig. 2. While qXR did not meet WHO TPP triage test targets for adults, it did for children. When selecting a threshold that achieves 90% sensitivity, qXR had 62% specificity (95% CI 59-65%) in adults and 91% (95% CI 84-98%) in children. At a 70% specificity, sensitivity was 84% (95% CI 80%-88%) in adults and 97% (95% CI 90-100%) in children. The radiologist’s accuracy was 71% sensitivity (95% CI 66-76%) and 83% specificity (95% CI 80-85%) in adults and 85% (95% CI 69-94%) sensitivity and 91% (95% CI 84-95%) specificity in children. Matching thresholds to the radiologist’s performance showed that qXR performed similar or better than the radiologist in both groups (Table 3). qXR threshold selection for implementation Three qXR threshold scenarios were considered for a population of 1000 adults with 5% TB prevalence (Table 4). When CXR interpretation by a radiologist would be replaced by using qXR with a threshold of 0.88 (radiologist-matched sensitivity), the same number of TB cases would be found, but require 29 fewer confirmatory tests. When a threshold of 0.50 (vendor-recommended) would be used, six more TB cases are found, requiring 91 extra confirmatory tests. Lowering the threshold further to 0.12 (90% sensitivity), 10 additional TB cases would be found compared to the current standard of care with radiologist CXR interpretation, but requiring 209 extra confirmatory tests. For children, the vendor-recommended threshold had slightly higher sensitivity (87% vs 85%) and specificity (95% vs 91%) than the radiologist, therefore detecting one more TB case required 37 fewer follow-up tests. Based on these considerations a qXR threshold of 0.5 was chosen for the subsequent implementation study. Performance of other products in adults Among adults, CAD4TB (AUCROC 0.83, 95% CI 0.80-0.86), Insight CXR (0.83, 95% CI 0.80-0.86), and DrAid (0.82, 95% CI 0.79-0.85) performed similar to qXR, followed by Genki (0.80, 95% CI 0.77-0.83). Radify Chest 0.78 (95% CI 0.75-0.81) and InferRead DR Chest 0.77 (95% CI 0.74-0.81) had lower accuracy. No product met the WHO TPP targets for triage. At 90% sensitivity, specificity of qXR was highest (62%), followed by CAD4TB, DrAid and Genki (specificity ~40%), while Radify Chest, Insight CXR and InferRead DR Chest had specificities below 31%. At 70% specificity, qXR reached 84% sensitivity, followed by CAD4TB, DrAid, Insight CXR and Genki (sensitivity ~80%). Radify Chest and InferRead DR Chest had lower sensitivities. Vendor-recommended thresholds prioritized either high sensitivity (qXR, Insight CXR, DrAid, InferRead DR Chest) or a balance of sensitivity and specificity (CAD4TB, Genki and Radify Chest). When threshold were matched to the radiologist’s accuracy, qXR, Insight CXR, CAD4TB and DrAid outperformed the radiologist. Genki and InferRead DR Chest had similar performance, while Radify Chest did not reach the radiologist’s accuracy. Accuracy of other products in children For children, AUCROCs were >0.90 for all products except for Radify Chest (0.67, 95% CI 0.58-0.76). Insight CXR analysis was limited to children ≥13 years (n=87), but restricting to this age group did not significantly change results for any of the other products (Figure S1). At 90% sensitivity, all products except Radify Chest had ≥77% specificity, with qXR the highest (91%) (Table 3). At 70% specificity, most products had ≥90% sensitivity, except Radify Chest. Vendor-recommended thresholds for most products achieved ≥80% sensitivity, but some had low specificity (Radify Chest 54%, Insight CXR 57%). Only qXR and CAD4TB had ≥95% specificity. The radiologist accuracy was considerably higher in children than in adults (sensitivity: 85%, 95% CI 69-94%; specificity: 91%, 95% CI 84%-95%). If threshold matched radiologist’s accuracy, qXR and CAD4TB outperformed, while DrAid only had slightly better specificity when matching radiologist sensitivity. Insight CXR performed the same, Genki slightly lower, and Radify Chest did not reach the radiologist’s accuracy. Discussion To our knowledge this is the first CAD threshold calibration study using the WHO-TDR protocol, combining prospective and retrospective data to evaluate CAD products for TB detection from Indian primary care facilities. Our findings confirmed that qXR performed well in both adults and children, although it did not meet WHO’s target for a triage test in adults. Our threshold analysis showed qXR outperformed the radiologist, the current standard of care. Lowering the threshold to the vendor-recommended threshold increased sensitivity from 71% (radiologist-matched) to 82% with only a minimal specificity drop (86% to 74%), making this the preferred threshold for the implementation study. Similar to qXR, CAD4TB, Insight CXR, DrAid, and Genki demonstrated strong accuracy in adults, with CAD4TB, Insight CXR, and DrAid matching radiologist performance. In children, qXR, as well as CAD4TB and DrAid met WHO’s triage test criteria, highlighting their potential for use in this population. The rapid rise of AI-driven TB-CAD products, accelerated by the COVID-19 pandemic, has outpaced systematic validation efforts and only some products have been assessed in individual studies untill the recent WHO policy update. 9,11,11,12,18–20 As part of this WHO policy update, 8 TB-CAD products were evaluated on global datasets of which 6 were deemed to be of sufficiently high accuracy to be recommended for community or facility based TB screening in adults. 6 While our primary goal was to validate qXR, we leveraged our dataset to evaluate six additional CAD products as well as the latest version of qXR (v4), all of which also part of the WHO evaluation. Similar to the findings from the WHO report, we found that CAD4TB, Insight CXR, DrAid and Genki performed well, and comparable to qXR and the radiologist. 6 Radify Chest, which did not meet the WHO standards, also showed lower accuracy in our study that only assessed the TB abnomality scores of the CAD products. Note that many products, including Radify, produce additional qualitative output measures which could aid a human reader, but these were not considered in our study. InferRead reached high accuracy in the WHO ealuation (AUC of 0.81, 95% CI 0.79-0.83 for facility based screening), but peformend less well in our adult dataset. This underscores the need and usefulness of assessing and comparing different products on local data from the intended target population. One of the drawbacks of the WHO-TDR threshold setting approach is the extensive data collection requirement, with, ideally prospective sputum collection and testing to confirm specificity. We were able to carry this out for a few months thanks to donor funding, but due to the inefficient use of molecular resources, many implementors prefer using the vendor recommended threshold without any prior validation. A more pragmatic, resource limited approach to threshold determination would be helpful to encourage implementors to determine the threshold based on a number of key programmatic indicators, during the early implementation phase. CAD in children This study is among the first assessing the performance of several CAD products in children 21,22 , an agegroup for which WHO has no recommendation on the use of these products yet due to limited evidence. Moreover, most products are also not labelled for use in children below the age of 4. While some studies reported lower CAD4TB accuracy in younger children, we found high accuracy in older children for several CAD products. 21,22 Our results in children should be taken with some caution, as the sample size was small and did not reach our minimum target, but they underscore the need for further research. Children account for 12% of TB cases worldwide, and 11% of the TB cases in India and .given CAD’s non-invasive nature, it could significantly aid paediatric TB detection. Limitations Our study included 60% retrospective data from a chest clinic rather than a PHI, potentially introducing selection bias. Although the chest clinic investigated the same target population, the selection of patients from the chest clinic might not fully represent those that would be attending PHIs. Secondly, clinically diagnosed TB cases in the retrospective dataset were classified as microbiologically negative, which may have affected accuracy estimates. Lastly, evolving population characteristics could impact the external validity of our findings. For all of these reasons, continuous monitoring of TB positivity rates among CAD-positive cases at PHIs is necessary to ensure sensitivity remains stable. Conclusion This study, conducted under programmatic conditions, established a dataset for local CAD performance assessment and threshold calibration using the WHO-TDR protocol. Our findings supported the implementation of ultra-portable digital CXR with qXR in Delhi PHIs as a valuable tool for triaging individuals with presumptive TB. Additionally, CAD4TB, Insight CXR, DrAid and Genki demonstrated high accuracy, warranting broader consideration for TB triaging in similar settings across India. Declarations Funding Foreign, Commonwealth & Development Office (FCDO). Author Contribution The study was conceived by SVK, SG, VV, AK, KH, TD, MC, MR and SM. Data collection was led by SG, VV, BKV, AK and SM. Data cleaning and verification was done by SVK, SG, VV, SL, AK. Data analysis and interpretation of results was done by SVK, SG, VV, SL, AK, KH, TD, MC, MR, AK, SM. SVK wrote the first draft of the manuscript. All authors had full access to all the data in the study and had final responsibility for the decision to submit for publication. All authors reviewed an earlier version of the manuscript and contributed to and approved the final manuscript. Acknowledgement We thank Dr. Umesh Kumar, Dr. Deep Mani, Dr. C. Healer, Dr. Kanika Bharadwaj, Arnab Pal, Akash Dey, and Harkesh Dabas for their strategic guidance during the concept and execution of the study, and Joseph Harwell, Nagalingeswaran Kumarasamy Rattan Ichhpujani for providing clinical and research guidance. We also express our thanks to Abhinav Sharma, Arpit Tushar, Azad Kumar, Shivam Sharma, Archana Srivas, Dharmender Saxena, Naresh Chauhan, and Vikesh Kumar who were members of the field task force. We thank Mikashmi Kohli and Aurélien Mace for technical assistance during the writing of the manuscript.The installation and use of the different CAD software evaluated in this manuscript was provided free of charge by all CAD vendors to FIND. CAD vendors did not have any role in the study design, data collection, analysis, the decision to publish or the preparation of the manuscript.This work was funded in whole by the Foreign, Commonwealth & Development Office (FCDO). The FCDO had no role in the study design, data collection, analysis, interpretation, or manuscript preparation. Data Availability The anonymized dataset used in this study and a datadictionary can be made available upon reasonable request to the corresponding author. Chest X-ray images will not be provided as these are withheld to reserve their use for independent product evaluations by the authors’ institutions. References World Health Organization. Global Tuberculosis Report 2024 . (World Health Organization, Geneva, 2024). Reid, M. et al. Scientific advances and the end of tuberculosis: a report from the Lancet Commission on Tuberculosis. Lancet Lond. Engl. 402 , 1473–1498 (2023). National TB Elimination Program. India TB Report 2024 . (Central TB Division, Ministry of Health and Family Welfare, 2024). Martinson, N. A. et al. Evaluating systematic targeted universal testing for tuberculosis in primary care clinics of South Africa: A cluster-randomized trial (The TUTT Trial). PLoS Med. 20 , e1004237 (2023). World Health Organization. WHO Consolidated Guidelines on Tuberculosis. Module 2: Screening - Systematic Screening for Tuberculosis Disease . (2021). World Health Organization. Use of Computer-Aided Detection Software for Tuberculosis Screening: WHO Policy Statement . https://www.who.int/publications/i/item/9789240110373 (2025). StopTB Partnership & FIND. AI4HLTH - StopTB Partnership and FIND resource centre on computer-aided detection products. https://www.ai4hlth.org/. DuPont, M. et al. Computer-Aided Reading of Chest Radiographs for Pediatric Tuberculosis: Current Status and Future Directions. 2024.10.08.24314837 Preprint at https://doi.org/10.1101/2024.10.08.24314837 (2024). Tavaziva, G. et al. Chest X-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: an individual patient data meta-analysis of diagnostic accuracy. Clin. Infect. Dis. 74 , 1390–1400 (2021). Qin, Z. Z. et al. Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms. Lancet Digit. Health 3 , e543–e554 (2021). Qin, Z. Z. et al. Comparing different versions of computer-aided detection products when reading chest X-rays for tuberculosis. PLOS Digit. Health 1 , e0000067 (2022). Fehr, J. et al. CAD4TB software updates: different triaging thresholds require caution by users and regulation by authorities. Int. J. Tuberc. Lung Dis. 27 , 157–160 (2023). Vanobberghen, F. et al. Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms. ERJ Open Res. 10 , 00508–02023 (2024). World Health Organization. WHO Operational Handbook on Tuberculosis. Module 2: Screening - Systematic Screening for Tuberculosis Disease . (2021). TDR & World Health Organization. Generic CAD calibration study protocol. Hwang, E. J. et al. AI for Detection of Tuberculosis: Implications for Global Health. Radiol. Artif. Intell. 6 , e230327 (2024). Codlin, A. J. et al. Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis. Sci. Rep. 11 , 23895 (2021). Qin, Z. Z. et al. Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software. Lancet Digit. Health 6 , e605–e613 (2024). Worodria, W. et al. An independent, multi-country head-to-head accuracy comparison of automated chest x-ray algorithms for the triage of pulmonary tuberculosis. medRxiv 2024.06.19.24309061 (2024) doi:10.1101/2024.06.19.24309061. Palmer, M. et al. Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children. PLOS Glob. Public Health 3 , e0001799 (2023). Edem, V. F. et al. Accuracy of CAD4TB (Computer-Aided Detection for Tuberculosis) on paediatric chest radiographs. Eur. Respir. J. 64 , 2400811 (2024). Tables Table 1. Specifications of the CAD products Product information Product name qXR CAD4TB Insight CXR Genki InferRead DR Chest DrAid Radify Chest Product version V3 V7 V3.1.5.3 V3.4-2 V1.0.1.1 V2.4 4-6 V3.8.0 Company name Qure.ai Delft Imaging Systems Lunit Insight Deeptek Infervision Vinbrain Envisionit Deep AI Country head office India The Netherlands South Korea India China Vietnam UK Score range 0-1 0-100 0-100 0-1 0-1 0-1 0-1 Manufacturer recommended minimum age 6 years and older 4 years and older 13 years 0–14 years paediatric model, 15 years and older adult model 16 years and older 3-15 years paediatric model, 16 years and older adult model 6-17 years paediatric model, 18 years and older adult model Manufacturer recommended threshold 0.5 60 15 0.2 (paediatric model), 0.3 (adult model) 0.17 0.8 (peadiatric model), 0.25 (adult model) 0.2 (peadiatric model), 0.2 (adult model) Table 2. Demographic and clinical characteristics of the study population Adults Children All TB No TB All TB No TB Variable N % N % N % N % N % N % Total 1245 100 315 100 930 100 159 39 120 Site Badarpur PHI 226 18.2 22 7.0 204 21.9 41 25.8 2 5.1 39 32.5 Jahangirpuri PHI 144 11.6 6 1.9 138 14.8 21 13.2 0 0.0 21 17.5 Sangam Vihar PHI 402 32.3 13 4.1 389 41.8 42 26,4 0 0.0 42 35.0 Nehru Nagar Chest Clinic 473 38.0 274 87.0 199 21.4 55 34.6 37 94.9 18 15.0 Data collection method Prospective 772 62.0 41 13.0 731 78.6 104 65.4 2 5.1 102 85.0 Retrospective 473 38.0 274 87.0 199 21.4 55 34.6 37 94.9 18 15.0 Age group (year) 6-15 0 0 0 0 0 0 159 100 39 100 120 100 16-35 702 56.4 231 73.3 471 50.6 0 0 0 0 0 0 36-55 331 26.6 52 16.5 279 30.0 0 0 0 0 0 0 55+ 212 17.0 32 10.2 180 19.4 0 0 0 0 0 0 Gender Female 580 46.6 139 44.1 441 47.4 79 49.7 27 69.2 52 43.3 Male 665 53.4 176 55.9 489 52.6 80 50.3 12 30.8 68 56.7 Type of NAAT test done Xpert 1047 84.1 222 70.5 825 88.7 132 83.0 23 59.0 109 90.8 First line LPA 14 1.1 14 4.4 0 0.0 6 3.8 6 15.4 0 0.0 Truenat 184 14.8 79 25.1 105 11.3 21 13.2 10 25.6 11 9.2 HIV status Non-reactive 403 32.4 205 65.1 198 21.3 50 31.4 29 74.4 21 17.5 Reactive 1 0.1 1 0.3 0 0.0 0 0 0 0 0 0.0 Unknown 841 67.6 109 34.6 732 78.7 109 68.6 10 25.6 99 82.5 Diabetics status Diabetic 43 3.4 13 4.1 29 3.1 0 0 0 0 0 0 Non-diabetic 453 36.4 134 42.5 319 34.4 76 47.8 23 59.0 53 44.2 Unknown 750 60.2 168 53.3 582 62.6 83 52.2 16 41.0 67 55.8 LPA=line probe assay, TB=tuberculosis, PHI=peripheral health institute Table 3. Accuracy measures of CAD products for the detection of microbiologically confirmed tuberculosis, evaluated among adults and children for different scenario’s Threshold score Sensitivity (95% CI) Specificity (95% CI) Threshold score Sensitivity (95% CI) Specificity (95% CI) Adults Children Scenario A - threshold to match 90% sensitivity Scenario A - threshold to match 90% sensitivity qXR 0.12 90% (86-93) 62% (59-65) qXR 0.21 90% (77-100) 91% (84-98) CAD4TB 14 90% (86-93) 42% (39-45) CAD4TB 26 90% (77-100) 77% (66-88) Insight CXR 13 90% (87-94) 29% (26-32) Insight CXR †,‡ 46 87% (74-97) # 84% (75-93) Genki 0.01 90% (87-94) 38% (35-41) Genki † 0.09 90% (77-100) 77% (64-88) InferRead DR Chest 0.12 90% (86-93) 27% (24-30) InferRead DR Chest ^ DrAid 0.17 90% (86-93) 40% (38-44) DrAid † 0.88 90% (77-100) 84% (73-100) Radify Chest 0.06 90% (87-93) 31% (28-34) Radify Chest † 0.03 87% (74-97) # 38% (25-50) Scenario B - threshold to match 70% specificity Scenario B - threshold to match 70% specificity qXR 0.35 84% (80-88) 71% (68-74) # qXR 0.04 97% (90-100) 70% (57-80) CAD4TB 34 81% (76-85) 70% (67-72) CAD4TB 21 94% (84-100) 73% (61-84) # Insight CXR 60 80% (75-84) 71% (68-74) # Insight CXR †,‡ 14 94% (84-100) 57% (45-70) # Genki 0.11 80% (76-85) 69% (66-72) # Genki † 0.09 90% (77-100) 77% (64-88) # InferRead DR Chest 0.27 74% (69-78) 69% (66-72) # InferRead DR Chest ^ DrAid 0.52 80% (76-84) 70% (67-73) DrAid † 0.76 97% (90-100) 70% (55-82) Radify Chest 0.07 77% (72-82) 70% (67-73) Radify Chest † 0.9 55% (39-71) 71% (59-84) # Scenario C - vendor recommended threshold Scenario C - vendor recommended threshold qXR 0.5 82% (77-86) 74% (71-76) qXR 0.5 (0.54) ∞ 87% (74-97) 95% (88-100) CAD4TB 60 67% (62-72) 87% (85-89) CAD4TB 60 (62) ∞ 81% (68-94) 96% (91-100) Insight CXR 15 89% (85-92) 32% (29-35) Insight CXR †,‡ 15 (14) ∞ 94% (84-100) 57% (45-70) Genki 0.3 75% (70-80) 78% (75-80) Genki † 0.2 (0.09) ∞ 90% (77-100) 77% (66-100) InferRead DR Chest 0.17 83% (79-87) 43% (40-46) InferRead DR Chest ^ DrAid 0.25 (0.26) ∞ 88% (84-91) 55% (51-58) DrAid † 0.8 (0.76) ∞ 97% (90-100) 70% (57-80) Radify Chest 0.2 (0.07) ∞ 77% (72-82) 70% (67-73) Radify Chest † 0.2 (0.04) ∞ 84% (71-94) 54% (41-66) Scenario D - threshold to match sensitivity of radiologist (71%) Scenario D - threshold to match sensitivity of radiologist (85%) qXR 0.88 71% (66-76) 86% (83-88) qXR 0.54 87% (74-97) # 95% (88-100) CAD4TB 54 71% (66-76) 86% (83-88) CAD4TB 50 84% (71-97) # 95% (88-100) Insight CXR 92 71% (66-76) 89% (87-91) Insight CXR †,‡ 66 84% (71-97) # 91% (82-98) Genki 0.38 71% (66-77) 81% (78-83) Genki † 0.61 87% (74-97) # 88% (79-96) InferRead DR Chest 0.36 71% (66-76) 78% (75-80) InferRead DR Chest ^ DrAid 0.93 71% (66-76) 85% (82-87) DrAid † 0.95 84% (71-97) # 96% (91-100) Radify Chest 0.76 71% (66-76) 79% (76-82) Radify Chest † 0.04 84% (71-94) # 54% (41-66) Scenario E - threshold to match specificity of radiologist (83%) Scenario E - threshold to match specificity of radiologist (91%) qXR 0.84 74% (69-79) 83% (80-85) qXR 0.21 90% (77-100) 91% (84-98) CAD4TB 49 72% (67-77) 83% (81-85) CAD4TB 39 87% (71-97) 91% (84-98) Insight CXR 83 76% (71-81) 82% (79-84) # Insight CXR †,‡ 66 84% (71-97) 91% (82-98) Genki 0.43 68% (63-73) 83% (81-85) Genki † 0.92 81% (65-94) 91% (84-98) InferRead DR Chest 0.44 68% (62-73) 83% (80-85) InferRead DR Chest ^ DrAid 0.91 72% (67-77) 83% (81-86) DrAid † 0.95 84% (71-97) 96% (91-100) # Radify Chest 0.78 62% (57-68) 83% (80-85) Radify Chest † 0.94 16% (3-29) 89% (80-96) # # The closest sensitivity or specificity to the described scenario. †Peadiatric TB model used. ‡ Analysis restricted to children aged 13-16 year. ^ Not evaluated for children, since vendor recommended age is 16 years and above. ∞ In brackets the closest actual threshold score observed in the data. CAD=computer aided detection Table 4. Effect in terms of number of follow-up tests done and TB cases detected of different threshold scores for qXR in a population of 1000 adults or children with a 5% TB prevalence if examined with chest X-ray and examined by a radiologist or qXR Effect per 1000 individuals tested with CXR Scenario Threshold Sensitivity Specificity TB prevalence True positives (TP) False positives (FP) True negatives (TN) False negatives (FN) Number of follow-up test (TP+FP) Difference in number of follow-up tests Difference in number TB patients detected Adults Radiologist reading – current practice 71% 83% 5% 35 162 788 15 197 Reference Reference qXR threshold matching radiologist sensitivity 0.88 71% 86% 5% 35 133 817 15 168 -29 0 qXR threshold matching vendor recommendation 0.50 82% 74% 5% 41 247 703 9 288 91 6 qXR threshold matching 90% sensitivity 0.12 90% 62% 5% 45 361 589 5 406 209 10 Children Radiologist reading – current practice 85% 91% 5% 43 86 865 8 128 Reference Reference qXR threshold matching radiologist sensitivity 0.54 # 87% 95% 5% 44 48 903 7 91 -37 1 qXR threshold matching vendor recommendation 0.54 # 87% 95% 5% 44 48 903 7 91 -37 1 qXR threshold matching 90% sensitivity 0.21 90% 91% 5% 45 86 865 5 131 3 3 # The closest threshold to the vendor recommend threshold. TB=tuberculosis Additional Declarations No competing interests reported. Supplementary Files Supplementaryinformation.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 03 Nov, 2025 Reviewers agreed at journal 02 Nov, 2025 Reviews received at journal 31 Oct, 2025 Reviews received at journal 17 Oct, 2025 Reviewers agreed at journal 13 Oct, 2025 Reviewers agreed at journal 13 Oct, 2025 Reviewers invited by journal 02 Oct, 2025 Editor assigned by journal 02 Oct, 2025 Editor invited by journal 01 Oct, 2025 Submission checks completed at journal 01 Oct, 2025 First submitted to journal 01 Oct, 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-7739612","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":528613018,"identity":"80729d89-d3b6-4044-8587-ddc08709b090","order_by":0,"name":"Sandra Vivian Kik","email":"","orcid":"","institution":"Foundation for Innovative New Diagnostics","correspondingAuthor":false,"prefix":"","firstName":"Sandra","middleName":"Vivian","lastName":"Kik","suffix":""},{"id":528613019,"identity":"11c28c71-b88a-4d29-81f8-2f62aa840eb7","order_by":1,"name":"Shruti Goel","email":"","orcid":"","institution":"William J. Clinton Foundation","correspondingAuthor":false,"prefix":"","firstName":"Shruti","middleName":"","lastName":"Goel","suffix":""},{"id":528613020,"identity":"9abbcee1-7c5f-4294-9e11-70262325c443","order_by":2,"name":"Vindhya Vatsyayan","email":"data:image/png;base64,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","orcid":"","institution":"Clinton Health Access Initiative","correspondingAuthor":true,"prefix":"","firstName":"Vindhya","middleName":"","lastName":"Vatsyayan","suffix":""},{"id":528613023,"identity":"914c4469-4ea1-4f84-ab6f-c7c13e20fc32","order_by":3,"name":"Sam Linsen","email":"","orcid":"","institution":"Foundation for Innovative New Diagnostics","correspondingAuthor":false,"prefix":"","firstName":"Sam","middleName":"","lastName":"Linsen","suffix":""},{"id":528613027,"identity":"2c03f727-86e8-4977-accc-69c37fcf83e3","order_by":4,"name":"Aurelie Kamoun","email":"","orcid":"","institution":"Foundation for Innovative New Diagnostics","correspondingAuthor":false,"prefix":"","firstName":"Aurelie","middleName":"","lastName":"Kamoun","suffix":""},{"id":528613028,"identity":"a83102f1-64e2-48c9-b6a3-c6483521cd83","order_by":5,"name":"Anju Garg","email":"","orcid":"","institution":"Maulana Azad Medical College","correspondingAuthor":false,"prefix":"","firstName":"Anju","middleName":"","lastName":"Garg","suffix":""},{"id":528613031,"identity":"12dcf87e-fd76-455d-8334-d02e3e7e53a4","order_by":6,"name":"Bhagirath Kumar Vashishat","email":"","orcid":"","institution":"Delhi State Tuberculosis Office","correspondingAuthor":false,"prefix":"","firstName":"Bhagirath","middleName":"Kumar","lastName":"Vashishat","suffix":""},{"id":528613033,"identity":"a83fb14c-d86d-42f4-a546-7fe62c5d19a3","order_by":7,"name":"Katy Hayward","email":"","orcid":"","institution":"Clinton Health Access Initiative","correspondingAuthor":false,"prefix":"","firstName":"Katy","middleName":"","lastName":"Hayward","suffix":""},{"id":528613039,"identity":"65b1202d-b0a6-4eab-9670-ba7742a1b079","order_by":8,"name":"ThuVan Dinh","email":"","orcid":"","institution":"Clinton Health Access Initiative","correspondingAuthor":false,"prefix":"","firstName":"ThuVan","middleName":"","lastName":"Dinh","suffix":""},{"id":528613040,"identity":"d497902c-26ae-46e9-ac23-52e49334d3a4","order_by":9,"name":"Michael Campbell","email":"","orcid":"","institution":"Clinton Health Access Initiative","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Campbell","suffix":""},{"id":528613044,"identity":"05166eab-3d91-43f8-85c8-da3daae15b47","order_by":10,"name":"Morten Ruhwald","email":"","orcid":"","institution":"Foundation for Innovative New Diagnostics","correspondingAuthor":false,"prefix":"","firstName":"Morten","middleName":"","lastName":"Ruhwald","suffix":""},{"id":528613045,"identity":"d471fdf3-0441-4244-ad1e-db4418d09935","order_by":11,"name":"Ashwani Khanna","email":"","orcid":"","institution":"Maulana Azad Medical College","correspondingAuthor":false,"prefix":"","firstName":"Ashwani","middleName":"","lastName":"Khanna","suffix":""},{"id":528613051,"identity":"184e3bd4-5ef4-4130-83e5-0882f59052df","order_by":12,"name":"Shamim Mannan","email":"","orcid":"","institution":"William J. Clinton Foundation","correspondingAuthor":false,"prefix":"","firstName":"Shamim","middleName":"","lastName":"Mannan","suffix":""}],"badges":[],"createdAt":"2025-09-29 08:23:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7739612/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7739612/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93612461,"identity":"db0d42b2-4339-4d8b-b38d-70d7209b337c","added_by":"auto","created_at":"2025-10-15 16:19:49","extension":"jpg","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":217075,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1Flowchartparticipantsv104AUG25.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/07f696e144b464ae800c595e.jpg"},{"id":93613448,"identity":"0a23ff7a-6b19-4ceb-9fe7-64b8ed240c87","added_by":"auto","created_at":"2025-10-15 16:27:49","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1180380,"visible":true,"origin":"","legend":"","description":"","filename":"ValidationofTBCADforuseinPHCsinIndiaCHAIstudyv1201102025Clean.docx","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/3759f4ee666515093785a5f2.docx"},{"id":93610900,"identity":"cfaec1d0-a44e-452f-be61-8e4593959146","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"json","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14145,"visible":true,"origin":"","legend":"","description":"","filename":"8d8de0ebf6734fe198e6156374e89d93.json","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/88878686d4837171f0daf35b.json"},{"id":93610898,"identity":"176b24b2-4b64-49de-92c5-bf5b1a7f6f33","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":152356,"visible":true,"origin":"","legend":"","description":"","filename":"8d8de0ebf6734fe198e6156374e89d931enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/d376f286185b5d916f044be4.xml"},{"id":93613938,"identity":"3442444d-db5a-4ddd-a7f1-5606f823519b","added_by":"auto","created_at":"2025-10-15 16:35:49","extension":"jpg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":217075,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1Flowchartparticipantsv104AUG25.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/3e6f6f4c1c352b486b53f3c5.jpg"},{"id":93613450,"identity":"675e21c6-7a92-4e7d-abe0-e7148a41e5d9","added_by":"auto","created_at":"2025-10-15 16:27:49","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":217075,"visible":true,"origin":"","legend":"","description":"","filename":"Figure1Flowchartparticipantsv104AUG25.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/dc106ebd8b5257655ec8f26c.jpeg"},{"id":93613451,"identity":"234478ad-ea35-467d-b833-9c9900353013","added_by":"auto","created_at":"2025-10-15 16:27:49","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":445628,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/70736cbae97c7c64ed116169.jpeg"},{"id":93612467,"identity":"2134fc58-5555-473e-95df-d3d13af2f5e5","added_by":"auto","created_at":"2025-10-15 16:19:49","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":422489,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/bffbec7cfb5d2499cf30ba2a.jpeg"},{"id":93612464,"identity":"f4f50151-1d04-48a8-a2c7-21f48f987336","added_by":"auto","created_at":"2025-10-15 16:19:49","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124827,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/4c9bcbc16b94eff55c96f32c.png"},{"id":93610912,"identity":"8000f844-3693-42ed-b9bf-04c17eebf0f9","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":363789,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/3fe298924eeb64d7d82744b0.jpeg"},{"id":93613940,"identity":"8554d60b-0649-4985-b50c-c7057557e6a0","added_by":"auto","created_at":"2025-10-15 16:35:49","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":342823,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/fe615822eed47d51631e651a.jpeg"},{"id":93610914,"identity":"dc9a1158-ae18-4180-91ec-ba1680f1884c","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"jpeg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":334358,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/7788a2e9a84643e1fb83ed8c.jpeg"},{"id":93610903,"identity":"e0c323e3-09d5-4f51-ad1a-89c4869661d3","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67228,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure1Flowchartparticipantsv104AUG25.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/6f8710683596345940fbcebb.png"},{"id":93613939,"identity":"d61d7e63-95ff-4aa9-948d-39789c9294d5","added_by":"auto","created_at":"2025-10-15 16:35:49","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67228,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineFigure1Flowchartparticipantsv104AUG25.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/ca7f200d4c25521e4dfa0980.png"},{"id":93610910,"identity":"e6219247-6747-469a-a79d-5b1984e05b02","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109482,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/c804d87b879614d34cb4e71e.png"},{"id":93610917,"identity":"9ed2a16c-a82d-4a2e-95ea-ef7e197d5200","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90381,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/f5ea08f821f88a8c6a5019dd.png"},{"id":93610908,"identity":"5341e306-054d-40c6-8ebb-43f0a82e8c75","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30778,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/4cf393b9a95887c990af6182.png"},{"id":93612469,"identity":"21074b02-78ee-4c48-b3b5-5ae80ea6509d","added_by":"auto","created_at":"2025-10-15 16:19:49","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":74067,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/d0016b190b5efbad7fca33cb.png"},{"id":93610902,"identity":"454f0e79-e38e-4b20-8c9e-4acee29ced12","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":59797,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/49afe3495cef34e798fcc8ac.png"},{"id":93613454,"identity":"b65aaeab-6fb8-4551-a9f1-de0db96796f8","added_by":"auto","created_at":"2025-10-15 16:27:49","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":58127,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/5d3a810ca1a427d201398a9e.png"},{"id":93612474,"identity":"3112adea-d9a0-4e23-8ba0-61b1447045da","added_by":"auto","created_at":"2025-10-15 16:19:49","extension":"xml","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":148896,"visible":true,"origin":"","legend":"","description":"","filename":"8d8de0ebf6734fe198e6156374e89d931structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/ca1567c764a05c574b7cc985.xml"},{"id":93610916,"identity":"83a3b941-4a40-4c5c-b519-ca752518a773","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"html","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":157696,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/9061444384abc5fff08691de.html"},{"id":93613937,"identity":"d94a6af0-ca44-4565-8c69-5e93be3c5195","added_by":"auto","created_at":"2025-10-15 16:35:49","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":217075,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003eFlow diagram of participants enrolled in the study and those included in the final analysis\u003c/strong\u003e\u003c/em\u003e\u003c/p\u003e","description":"","filename":"Figure1Flowchartparticipantsv104AUG25.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/904581435352985938076167.jpg"},{"id":93613445,"identity":"7cb60e6c-6434-4c59-8ed7-a9df5a29001b","added_by":"auto","created_at":"2025-10-15 16:27:49","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":233380,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eReceiver operating characteristic curves of 7 CAD products (left), assessed in adults, against a microbiological reference standard and the AUCs with corresponding confidence intervals (right)\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eResults in this figure are based on 1245 observations, including 315 individuals with confirmed TB and 930 individuals without TB, all 16 years and above and with a digital CXR images that was processed by all assessed CAD products.\u003c/p\u003e\n\u003cp\u003eAUC=area under the receiver operating characteristic curve, CAD=computer-aided detection, CXR=chest X-ray, ROC=receiver operating characteristic, TB=tuberculosis.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/39c953f6c843972d2ca2f601.png"},{"id":93610892,"identity":"14792b2a-f315-4414-a9b9-9f2cb9b7c732","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":210149,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eReceiver operating characteristic curves (left) of 7 CAD products, assessed in children, against a microbiological reference standard and the AUCs with corresponding confidence intervals (right)\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eResults in this figure are based for all products, except Insight CXR, on 159 observations, including 39 children with microbiologically confirmed TB and 120 children without TB, all between 6 and16 years and with a digital CXR images that was processed by all assessed CAD products, except for Insight CXR. Results for Insight CXR are based on the subgroup of children between 13 and 16 years, which were 87 observations, including 31 children with microbiologically confirmed TB and 56 children without TB.\u003c/p\u003e\n\u003cp\u003eAUC=area under the receiver operating characteristic curve, CAD=computer-aided detection, CXR=chest X-ray, ROC=receiver operating characteristic, TB=tuberculosis.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/a06f47a8c00fa311a02cecb5.png"},{"id":93615318,"identity":"d43dfc3e-d1c4-4c12-81ca-12f427340f7e","added_by":"auto","created_at":"2025-10-15 16:43:50","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2732397,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/cb903652-a907-4d36-b4a3-27b210ecac1d.pdf"},{"id":93610896,"identity":"6101f29c-99f0-473a-9463-1a26610732b2","added_by":"auto","created_at":"2025-10-15 16:11:49","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":579658,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementaryinformation.docx","url":"https://assets-eu.researchsquare.com/files/rs-7739612/v1/e290634498ad1b0f88c9a433.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Validation of several TB-CAD chest-X-ray applications in individuals with presumptive TB visiting peripheral health institutes in Delhi State","fulltext":[{"header":"Introduction","content":"\u003cp\u003eTuberculosis (TB) is a leading cause of morbidity and mortality worldwide, with an estimated 10.8\u0026nbsp;million new cases and 1.25\u0026nbsp;million deaths annually.\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e Despite progress in TB control, the disease remains a significant public health challenge. Since 2015, the global TB incidence rate has decreased by 8.3%, but is falling short of the targeted 50% reduction by 2025 as was set out in the \u003cem\u003eEnd TB Strategy\u003c/em\u003e.\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e To reduce the gap in case detection intensified efforts are required, particularly in high-burden countries.\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e\u003c/p\u003e\u003cp\u003eIndia, home to the largest TB burden, accounts for over a quarter of global cases. Since 2015, India\u0026rsquo;s initiatives for early detection, treatment initiation, and community engagement to increase awareness and patient support have led to a 16% decline in TB incidence and an 18% reduction in mortality.\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e,\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e Yet, approximately 0.23\u0026nbsp;million estimated TB patients remain undiagnosed or unreported each year, including a significant number of patients with pulmonary TB (PTB). Identifying these \"missing cases\" is essential to break the chain of transmission. Targeted testing in primary healthcare settings is key to improving case detection.\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e\u003c/p\u003e\u003cp\u003eOne approach to increase case finding at primary care levels is the use of digital chest X-rays (CXR) systems combined with computer-aided detection (CAD) software to identify individuals with possible pulmonary TB. CAD technology facilitates faster and more accurate diagnosis and since 2021 the World Health Organization has recommended the use of this technology as an initial screening or triage test for adults.\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u003c/sup\u003e Early 2025, a number of specific CAD products (and versions) were evaluated and found to meet the WHO performance standards, opening the door for country consideration. \u003csup\u003e6\u003c/sup\u003e CAD products identify radiographic abnormalities indicative of TB by providing a TB abnormality score. When this score is above a certain threshold, individuals are referred for confirmatory testing.\u003c/p\u003e\u003cp\u003eMost CAD developers do not recommend the use of their product in young children (\u0026lt;\u0026thinsp;2 years), but suggest they could be used in older childer.\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e Evidence on the accuracy of CAD in children is scarce. The radiographic presentation of TB in infants and young children differs from that in adults and limited access to training datasets from children has hampered the development of child-specific CAD models. \u003csup\u003e8\u003c/sup\u003e\u003c/p\u003e\u003cp\u003eBesides age, the CAD score distribution is influenced by other factors including country of origin, HIV status, smear status, symptoms, gender, and a prior TB history. \u003csup\u003e9\u0026ndash;13\u003c/sup\u003e Thus, the prevalence of these factors in the target population may affect CAD score distribution. It is therefore vital to establish an appropriate threshold score for CAD systems to determine which CXRs are suggestive of PTB and warrant confirmatory testing.\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e,\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e,\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e\u003c/p\u003e\u003cp\u003eWe conducted a thresold validation study in accordance with the standardized calibration protocol developed by the WHO Global TB Programme and the Special Program for Research and Training in Tropical Diseases (TDR) \u003csup\u003e16\u003c/sup\u003e, to determine the accuracy and establish a threshold score for qXRv3 (Qure.ai, India) as the CAD product of choice for triaging individuals with presumptive TB at Peripheral Health Institutions (PHI) in Delhi.\u003c/p\u003e\u003cp\u003eAdditionally, we evaluate the accuracy of six other additional commercial CAD products, all also part of the recent WHO policy review,(CAD4TB v7, Delft Imaging, The Netherlands; Insight CXR v3.1.5.3, Lunit Insight, South Korea; Genki v3.4-2, Deeptek, India; InferRead DR Chest v1.0.1.1, Infervision, China; DrAid v2.4.4-6, Vinbrain, Vietnam; Radify Chest v3.8.0, Envisionit Deep AI, UK) using the same dataset to explore whether alternative CAD products can achieve the same accuracy and could be considered for broader implementation in similar settings in India.\u003c/p\u003e"},{"header":"Materials and Methods","content":"\u003cp\u003e\u003cstrong\u003eStudy design\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study adopted a combined retrospective case-control and prospective cross-sectional design to create a representative chest X-rays (CXR) dataset from individuals with presumptive TB attending primary care facilities in India. Conducted under standard programmatic settings, a solely prospective study was deemed unfeasible due to the relatively low prevalence of TB among general out-patient department (OPD) attendees and the large number of required CXRs from confirmed TB cases, which would have resulted in an impractically long enrolment period. To address this, retrospective and prospective data were pooled, as suggested by the generic CAD calibration protocol. \u003csup\u003e16\u003c/sup\u003e\u0026nbsp; \u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStudy setting\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study took place at\u0026nbsp;three PHIs\u0026nbsp;(Badarpur, Jahangirpuri, Sangam Vihar) in Delhi and a nearby TB Chest Clinic (CC) at a district hospital (Nehru Nagar). Retrospective data came from the chest clinic, while prospective data were collection at PHIs, selected based on high visitor rates (150-200 daily), and readiness in terms of dedicated space for digital X-ray installation. Before the study, presumptive TB patients at these PHIs underwent sputum smear microscopy; if positive, they were referred for molecular testing and treatment at the chest clinic. Patients with a negative smear but persistent symptoms were also referred for evaluation by a chest physician, requiring a chest X-ray and other tests. However, there was no follow-up mechanism in place potentially leading to delay in proper diagnosis of such patients.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eProspective cross-sectional data collection\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAn ultra-portable digital chest-X-ray (dCXR) device (FDR Xair XD 2000, Fujifilm, Tokyo, Japan), without CAD, was installed at each PHI, with project staff trained by Fujifilm on its use. Prospective data collection occurred from October 1, 2022 to December 31, 2022, with at least 1.5 months of consecutive data collection at each site. OPD visitors were screened for symptoms and risk factors to verify eligibility. The following individuals were eligible for inclusion:\u003c/p\u003e\n\u003cp\u003e1) Adults and children (aged \u0026ge;10 years) presented with at least one TB symptom as per the WHO 4 symptom-screen (W4SS, prolonged cough \u0026ge;2 weeks, haemoptysis, night sweats, weight loss or fever).\u003c/p\u003e\n\u003cp\u003e2) Adults with suspected household exposure to TB.\u003c/p\u003e\n\u003cp\u003e3) Children (\u0026ge;6 years) with HIV or household TB exposure.\u003c/p\u003e\n\u003cp\u003eExclusion criteria included individuals on TB treatment and pregnant women.\u003c/p\u003e\n\u003cp\u003eAdults provided written informed consent, while parental consent and child oral assent were obtained per national ethical guidelines. Digital CXRs were captured, and demographic and clinical data (symptoms, comorbidities including HIV and diabetics) were recorded electronically. All participants received a CXR, followed by on-the-spot sputum collection for molecular testing, regardless of their CXR results, as part of the study. Additionally, these patients were examined by a medical officer and referred for smear microscopy and/or other tests as per the standard of care. Test results were integrated into the database. All TB cases were refferred for treatment.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRetrospective case-control data collection\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eCC attendees included individuals with presumptive TB, either as first-time visitors or referred from nearby PHIs for CXR or molecular testing. Before the study initiation, the selected CC was one of the few sites where digital CXRs in DICOM format had been available in previous years due to the presence of a Computed Radiography system (Fujifilm), which allowed for compatibility with retrospective data collection requirements.\u003c/p\u003e\n\u003cp\u003eDigital CXRs (October 2020 -August 2022) were extracted from the Picture Archiving and Communication System (PACS) system and assessed for inclusion. Extracted metadata included patient ID, name, gender, age, date of birth and CXR acquisition data. CXRs were codified to a unique \u0026lsquo;CXR key\u0026rsquo; which was a concatenated field of patient name, age and gender.\u003c/p\u003e\n\u003cp\u003eNext, presumptive TB registrations (Q3 2020 to Q4 2022) were extracted from India\u0026rsquo;s national TB surveillance and patient management system (Nikshay), the Nucleic Acit Amplification Test (NAAT) register (all presumptive individuals who received a NAAT test), the Truenat register (all presumptive individuals who received a Truenat test (Molbio, Goa, India)), the current facility register (all diagnosed TB patients currently seeking care at the chest clinic), and the diagnosed facility register (all TB patients who were diagnosed at the chest clinic). A \u0026lsquo;Nikshay key\u0026rsquo; (concatenated patient name, age and gender) was used for record linkage via an 80% fuzzy match (through an Excel add-on) between the CXR key and the Nikshay key. Additional filters were used ensuring accurate matching including: 1) a 100% match on patient gender; 2) an age difference \u0026le;1 year (to account for recall errors or data entry mistakes); 3) a maximum 30-day difference between CXR and the diagnosis date (to account for delays but exclude CXRs conducted for disease progression monitoring). Data was deduplicated and anonymized before sharing with radiologists for re-reading and the data team for CAD analysis.\u003c/p\u003e\n\u003cp\u003eRetrospective CXR inclusion criteria matched prospective eligibility requirements, ensuring availability of molecular test results. Where possible, the following data was extracted from Nikshay and further complemented by information from the patient\u0026rsquo;s records; age, gender, HIV status, history of TB, history of smoking, household contact, CXR acquisition date, presence of TB symptoms, sputum smear result, NAAT test and result, culture result, comorbidities.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAnonymization\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll digital CXRs (Digital Imaging and Communications in Medicine (DICOM format)) were de-identified using DICOM Anonymizer software and a unique patient identifier replaced personal information before secure upload to FIND\u0026rsquo;s server to allow for CAD analysis.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eIndex test: CAD software installation and CXR processing\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe primary aim of the study was to evaluate qXR version 3 (Qure.AI, Mumbai, India) as the selected product for a subsequent implementation study in the participating PHIs. However, to increase the usefulness of this unique dataset, and to allow for head-to-head product comparison, we also evaluated the following six additional products: CAD4TB version 7 (Delft Imaging, \u0026lsquo;s-Hertogenbosch, The Netherlands), Insight CXR version 3.1.5.3 (Lunit, Seoul, South Korea), Genki version 3.4-2 (DeepTek Medical Imaging Private Limited, Pune, India), InferRead DR Chest version 1.0.1.1 (InferVision, Beijing, China), DrAid version 2.4 4-6 (VinBrain, Hanoi, Vietnam), Radify Chest version 3.8.0 (Envisionit Deep AI, Cobham, UK). All these products were also part of the recent WHO policy review. CAD products were installed on separate virtual machines within FIND\u0026rsquo;s digital infrastructure for independent accuracy assessment.\u003csup\u003e17\u003c/sup\u003e Vendors were restricted from access post-installation. CXRs were processed per vendor instructions. Each product produced a TB abnormality score ranging between 0-1 (qXR, Genki, InferRead DR Chest, DrAid, Radify Chest) or 0-100 (CAD4TB, Insight CXR) and scores were extracted and merged for further analysis. CXRs that could not be processed by one or more CAD products were excluded from the analysis to eanable a head-to-head comparison between products.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eSeparate analyses were conducted for adults (\u0026ge;16 years) and children (6-16 years). CAD products had differing minimum age recommendations, and some have a separate paediatric model. An age cut-off of 16 years was chosen to distinghuis children from adults, because this aligned with the majority of the vendor recommendations (Table 1). Only for Genki and Radify Chest, the recommended age for the peadiatric model was lower (15 years) or higher (18 years).For the analysis in children, for qXR and CAD4TB, the same model as for adults was used. For Genki, DrAid and Radify Chest, a different, dedicated paediatric TB model was used. InferRead DR Chest is not recommended for use in individuals below 16 years and was therefore not evaluated in children. Since Insight CXR is only recommended for age 13 years and above, the analysis for this product was restricted to children between 13 and 16 years.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eReference standard: microbiologically confirmation\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe accuracy of CAD products was compared against a microbiological reference standard (MRS). TB cases were defined as those with a positive microbiological test (Xpert, Truenat, Line Probe Assay or culture) on a baseline sputum sample collected within 30 days of the CXR date, while non-TB cases were those who had only negative microbiological test results. Individuals with missing or indeterminate test results were excluded from the analysis.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eComparator test: CXR interpretation by radiologist\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA single radiologist retrospectively interpreted all CXRs, classifying them into five categories: 1) Abnormal CXR with findings suggestive of active TB; 2) Abnormal CXR with findings suggesting of old, healed TB; 3) Abnormal CXR not suggestive of TB; 4) Normal CXR; 5) Other, non-pulmonary findings. Images classified as category 1 were considered TB, while all others were non-TB. The radiologist was blinded to the TB test results and CAD scores.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSample size\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe sample size was calculated to detect CAD products meeting the WHO\u0026rsquo;s target product profile (WHO TPP) (90% sensitivity, 70% specificity) with 5% alpha and 80% power. This required minimally 283 confirmed TB cases and 660 non-TB cases.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eStatistical analysis\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eCategorical variables were reported as counts and percentages, and continuous variables as medians and interquartile ranges (IQRs). Receiver Operating Characteristics (ROC) analysis was conducted to compute the area under the curve (AUC) with 95% confidence interval (CI). For the threshold analysis, thresholds were selected that achieved 90% sensitivity, 80% specificity, matched with the sensitivity or specificity of the radiologist and those recommended by the vendor. Analyses were stratified by age group (adults \u0026ge;16 years, vs children 6-16 years).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was approved by the Institutional Review Board of Maulana Azad Medical College (IRB number IEC/MAMC/86/04/2021/No491) on October 18, 2021. All methods were performed in accordance with the relevant guidelines and regulations, including the Declaration of Helsinki.\u0026nbsp;Written informed consent was obtained from all participants aged 18 years and older, and from the legal guardians of participants under the age of 18 years.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eRole of the funding source\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe funder had no role in the study design, data collection, analysis, interpretation, or manuscript preparation.\u003c/p\u003e"},{"header":"Results","content":"\u003cp\u003eA total of 1209 individuals with presumptive TB attended, with 1096 (91%) providing consent and undergoing dCXR. Due to missing age, gender, NAAT \u0026nbsp;results or radiological test results, 213 individuals were excluded. . Lastly, 7 more were excluded due to CXR CAD processing issues, leaving a total of 876 presumptive TB cases (772 adults; 41 TB positive, 731 TB negative, and104 children; 2 TB positive and 102 TB negative) for analysis.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eRetrospective data collection from the chest clinic added 535 presumptive TB cases (480 adults, 55 children). Seven digital CXRs (all from adults) were excluded due to CAD processing issues, leaving 528 individuals (473 adults; 274 TB-positive, 199 TB-negative and 55 children; 37 TB-positive, 18 TB-negative) with complete data. As a result, the combined prospective and retrospective dataset included 1404 participants (1245 adults, 159 children) for analysis including \u0026nbsp;315 TB-positive and 930 TB-negative adults, and 39 TB-positive and 120 TB-negative children (Figure 1).\u003c/p\u003e\n\u003cp\u003eAll together, we had data from. The majority of adults fell in the 16-35 year age category and nearly 47% were female. Risk factors data were limited and not systematically captured, but suggested low prevalence of HIV and diabetes in this population.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eqXR performance in adults and children\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe receiver operatoring characteristic and overall performance (AUCROC) of qXR against the microbiological reference standard are shown in Figures 2 (adults) and 3 (children). \u0026nbsp;qXR had an AUCROC of 0.88 (95% CI of 0.85-0.90) in adults \u0026nbsp;and 0.95 (95% CI 0.89-1.00) in children. Results for qXR v4 are shown in Supplement Fig. 2.\u003c/p\u003e\n\u003cp\u003eWhile qXR did not meet WHO TPP triage test targets for adults, it did for children. When selecting a threshold that achieves 90% sensitivity, qXR had 62% specificity (95% CI 59-65%) in adults and 91% (95% CI 84-98%) in children. At a 70% specificity, sensitivity was 84% (95% CI 80%-88%) in adults and 97% (95% CI 90-100%) in children.\u003c/p\u003e\n\u003cp\u003eThe radiologist\u0026rsquo;s accuracy was 71% sensitivity (95% CI 66-76%) and 83% specificity (95% CI 80-85%) in adults and 85% (95% CI 69-94%) sensitivity and 91% (95% CI 84-95%) specificity in children. Matching thresholds to the radiologist\u0026rsquo;s performance showed that qXR performed similar or better than the radiologist in both groups (Table 3).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eqXR threshold selection for implementation\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThree qXR threshold scenarios were considered for a population of 1000 adults with 5% TB prevalence (Table 4). When CXR interpretation by a radiologist would be replaced by using qXR with a threshold of 0.88 (radiologist-matched sensitivity), the same number of TB cases would be found, but require 29 fewer confirmatory tests. When a threshold of 0.50 (vendor-recommended) would be used, six more TB cases are found, requiring 91 extra confirmatory tests. Lowering the threshold further to 0.12 (90% sensitivity), \u0026nbsp;10 additional TB cases would be found compared to the current standard of care with radiologist CXR interpretation, but requiring 209 extra confirmatory tests. For children, the vendor-recommended threshold had slightly higher sensitivity (87% vs 85%) and specificity (95% vs 91%) than the radiologist, therefore detecting one more TB case required 37 fewer follow-up tests. Based on these considerations a qXR threshold of 0.5 was chosen for the subsequent implementation study.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePerformance of other products in adults\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAmong adults, CAD4TB (AUCROC 0.83, 95% CI 0.80-0.86), Insight CXR (0.83, 95% CI 0.80-0.86), and DrAid (0.82, 95% CI 0.79-0.85) performed similar to qXR, followed by Genki (0.80, 95% CI 0.77-0.83). Radify Chest 0.78 (95% CI 0.75-0.81) and InferRead DR Chest 0.77 (95% CI 0.74-0.81) had lower accuracy.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eNo product met the WHO TPP targets for triage. At 90% sensitivity, specificity of qXR was highest (62%), followed by CAD4TB, DrAid and Genki (specificity ~40%), while Radify Chest, Insight CXR and InferRead DR Chest had specificities below 31%. At 70% specificity, qXR reached 84% sensitivity, followed by CAD4TB, DrAid, Insight CXR and Genki (sensitivity ~80%). Radify Chest and InferRead DR Chest had lower sensitivities.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eVendor-recommended thresholds prioritized either high sensitivity (qXR, Insight CXR, DrAid, InferRead DR Chest) or a balance of sensitivity and specificity (CAD4TB, Genki and Radify Chest). When threshold were matched to the radiologist\u0026rsquo;s accuracy, qXR, Insight CXR, CAD4TB and DrAid outperformed the radiologist. Genki and InferRead DR Chest had similar performance, while Radify Chest did not reach the radiologist\u0026rsquo;s accuracy.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAccuracy of other products in children\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eFor children, AUCROCs were \u0026gt;0.90 for all products except for Radify Chest (0.67, 95% CI 0.58-0.76). Insight CXR analysis was limited to children \u0026ge;13 years (n=87), but restricting to this age group did not significantly change results for any of the other products (Figure S1).\u003c/p\u003e\n\u003cp\u003eAt 90% sensitivity, all products except Radify Chest had \u0026ge;77% specificity, with qXR the highest (91%) (Table 3). At 70% specificity, most products had \u0026ge;90% sensitivity, except Radify Chest. Vendor-recommended thresholds for most products achieved \u0026ge;80% sensitivity, but some had low specificity (Radify Chest 54%, Insight CXR 57%). Only qXR and CAD4TB had \u0026nbsp;\u0026ge;95% specificity.\u003c/p\u003e\n\u003cp\u003eThe radiologist accuracy was considerably higher in children than in adults (sensitivity: 85%, 95% CI 69-94%; specificity: 91%, 95% CI 84%-95%). If threshold matched radiologist\u0026rsquo;s accuracy, qXR and CAD4TB outperformed, while DrAid only had slightly better specificity when matching radiologist sensitivity. Insight CXR performed the same, Genki slightly lower, and Radify Chest did not reach the radiologist\u0026rsquo;s accuracy.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eTo our knowledge this is the first CAD threshold calibration study using the WHO-TDR protocol, combining prospective and retrospective data to evaluate CAD products for TB detection from Indian primary care facilities. Our findings confirmed that qXR performed well in both adults and children, although it did not meet WHO\u0026rsquo;s target for a triage test in adults. Our threshold analysis showed qXR outperformed the radiologist, the current standard of care. Lowering the threshold to the vendor-recommended threshold increased sensitivity from 71% (radiologist-matched) to 82% with only a minimal specificity drop (86% to 74%), making this the preferred threshold for the implementation study.\u003c/p\u003e\n\u003cp\u003eSimilar to qXR, CAD4TB,\u0026nbsp;Insight CXR, DrAid, and Genki demonstrated strong accuracy in adults, with CAD4TB, Insight CXR, and DrAid matching radiologist performance. In children, qXR, as well as CAD4TB and DrAid met WHO\u0026rsquo;s triage test criteria, highlighting their potential for use in this population.\u003c/p\u003e\n\u003cp\u003eThe rapid rise of AI-driven TB-CAD products, accelerated by the COVID-19 pandemic, has outpaced systematic validation efforts and only some products have been assessed in individual studies untill the recent\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003eWHO policy update. \u003csup\u003e9,11,11,12,18\u0026ndash;20\u003c/sup\u003e\u0026nbsp; As part of this WHO policy update, 8 TB-CAD products were evaluated on global datasets of which 6 were deemed to be of sufficiently high accuracy to be recommended for community or facility based TB screening in adults.\u003csup\u003e6\u003c/sup\u003e\u003c/p\u003e\n\u003cp\u003eWhile our primary goal was to validate qXR, we leveraged our dataset to evaluate six additional CAD products as well as the latest version of qXR (v4), all of which also part of the WHO evaluation. Similar to the findings from the WHO report, we found that CAD4TB, Insight CXR, DrAid and Genki performed well, and comparable to qXR and the radiologist.\u003csup\u003e6\u003c/sup\u003e Radify Chest, which did not meet the WHO standards, also showed lower accuracy in our study that only assessed the TB abnomality scores of the CAD products. Note that many products, including Radify, produce additional qualitative output measures which could aid a human reader, but these were not considered in our study. InferRead reached high accuracy in the WHO ealuation (AUC of 0.81, 95% CI 0.79-0.83 for facility based screening), but peformend less well in our adult dataset. This underscores the need and usefulness of assessing and comparing different products on local data from the intended target population.\u003c/p\u003e\n\u003cp\u003eOne of the drawbacks of the WHO-TDR threshold setting approach is the extensive data collection requirement, with, ideally prospective sputum collection and testing to confirm specificity. We were able to carry this out for a few months thanks to donor funding, but due to the inefficient use of molecular resources, many implementors prefer using the vendor recommended threshold without any prior validation. A more pragmatic, resource limited approach to threshold determination would be helpful to encourage implementors to determine the threshold based on a number of key programmatic indicators, during the early implementation phase.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCAD in children\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study is among the first assessing the performance of several CAD products in children\u003csup\u003e21,22\u003c/sup\u003e, an agegroup for which WHO has no recommendation on the use of these products yet due to limited evidence. Moreover, most products are also not labelled for use in children below the age of 4. While some studies reported lower CAD4TB accuracy in younger children, we found high accuracy in older children for several CAD products.\u003csup\u003e21,22\u003c/sup\u003e Our results in children should be taken with some caution, as the sample size was small and did not reach our minimum target, but they underscore the need for further research. Children account for 12% of TB cases worldwide, and 11% of the TB cases in India and .given CAD\u0026rsquo;s non-invasive nature, it could significantly aid paediatric TB detection.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eLimitations\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eOur study included 60% retrospective data from a chest clinic rather than a PHI, potentially introducing selection bias. Although the chest clinic investigated the same target population, the selection of patients from the chest clinic might not fully represent those that would be attending PHIs. Secondly, clinically diagnosed TB cases in the retrospective dataset were classified as microbiologically negative, which may have affected accuracy estimates. Lastly, evolving population characteristics could impact the external validity of our findings. For all of these reasons, continuous monitoring of TB positivity rates among CAD-positive cases at PHIs is necessary to ensure sensitivity remains stable.\u0026nbsp;\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study, conducted under programmatic conditions, established a dataset for local CAD performance assessment and threshold calibration using the WHO-TDR protocol. Our findings supported the implementation of ultra-portable digital CXR with qXR in Delhi PHIs as a valuable tool for triaging individuals with presumptive TB. Additionally, CAD4TB, Insight CXR, DrAid and Genki demonstrated high accuracy, warranting broader consideration for TB triaging in similar settings across India.\u0026nbsp;\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eFunding\u003c/h2\u003e\u003cp\u003eForeign, Commonwealth \u0026amp; Development Office (FCDO).\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eThe study was conceived by SVK, SG, VV, AK, KH, TD, MC, MR and SM. Data collection was led by SG, VV, BKV, AK and SM. Data cleaning and verification was done by SVK, SG, VV, SL, AK. Data analysis and interpretation of results was done by SVK, SG, VV, SL, AK, KH, TD, MC, MR, AK, SM. SVK wrote the first draft of the manuscript. All authors had full access to all the data in the study and had final responsibility for the decision to submit for publication. All authors reviewed an earlier version of the manuscript and contributed to and approved the final manuscript.\u003c/p\u003e\u003ch2\u003eAcknowledgement\u003c/h2\u003e\u003cp\u003eWe thank Dr. Umesh Kumar, Dr. Deep Mani, Dr. C. Healer, Dr. Kanika Bharadwaj, Arnab Pal, Akash Dey, and Harkesh Dabas for their strategic guidance during the concept and execution of the study, and Joseph Harwell, Nagalingeswaran Kumarasamy Rattan Ichhpujani for providing clinical and research guidance. We also express our thanks to Abhinav Sharma, Arpit Tushar, Azad Kumar, Shivam Sharma, Archana Srivas, Dharmender Saxena, Naresh Chauhan, and Vikesh Kumar who were members of the field task force. We thank Mikashmi Kohli and Aur\u0026eacute;lien Mace for technical assistance during the writing of the manuscript.The installation and use of the different CAD software evaluated in this manuscript was provided free of charge by all CAD vendors to FIND. CAD vendors did not have any role in the study design, data collection, analysis, the decision to publish or the preparation of the manuscript.This work was funded in whole by the Foreign, Commonwealth \u0026amp; Development Office (FCDO). The FCDO had no role in the study design, data collection, analysis, interpretation, or manuscript preparation.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe anonymized dataset used in this study and a datadictionary can be made available upon reasonable request to the corresponding author. Chest X-ray images will not be provided as these are withheld to reserve their use for independent product evaluations by the authors\u0026rsquo; institutions.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eWorld Health Organization. \u003cem\u003eGlobal Tuberculosis Report 2024\u003c/em\u003e. (World Health Organization, Geneva, 2024).\u003c/li\u003e\n\u003cli\u003eReid, M. \u003cem\u003eet al.\u003c/em\u003e Scientific advances and the end of tuberculosis: a report from the Lancet Commission on Tuberculosis. \u003cem\u003eLancet Lond. Engl.\u003c/em\u003e \u003cstrong\u003e402\u003c/strong\u003e, 1473\u0026ndash;1498 (2023).\u003c/li\u003e\n\u003cli\u003eNational TB Elimination Program. \u003cem\u003eIndia TB Report 2024\u003c/em\u003e. (Central TB Division, Ministry of Health and Family Welfare, 2024).\u003c/li\u003e\n\u003cli\u003eMartinson, N. A. \u003cem\u003eet al.\u003c/em\u003e Evaluating systematic targeted universal testing for tuberculosis in primary care clinics of South Africa: A cluster-randomized trial (The TUTT Trial). \u003cem\u003ePLoS Med.\u003c/em\u003e \u003cstrong\u003e20\u003c/strong\u003e, e1004237 (2023).\u003c/li\u003e\n\u003cli\u003eWorld Health Organization. \u003cem\u003eWHO Consolidated Guidelines on Tuberculosis. Module 2: Screening - Systematic Screening for Tuberculosis Disease\u003c/em\u003e. (2021).\u003c/li\u003e\n\u003cli\u003eWorld Health Organization. \u003cem\u003eUse of Computer-Aided Detection Software for Tuberculosis Screening: WHO Policy Statement\u003c/em\u003e. https://www.who.int/publications/i/item/9789240110373 (2025).\u003c/li\u003e\n\u003cli\u003eStopTB Partnership \u0026amp; FIND. AI4HLTH - StopTB Partnership and FIND resource centre on computer-aided detection products. https://www.ai4hlth.org/.\u003c/li\u003e\n\u003cli\u003eDuPont, M. \u003cem\u003eet al.\u003c/em\u003e Computer-Aided Reading of Chest Radiographs for Pediatric Tuberculosis: Current Status and Future Directions. 2024.10.08.24314837 Preprint at https://doi.org/10.1101/2024.10.08.24314837 (2024).\u003c/li\u003e\n\u003cli\u003eTavaziva, G. \u003cem\u003eet al.\u003c/em\u003e Chest X-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: an individual patient data meta-analysis of diagnostic accuracy. \u003cem\u003eClin. Infect. Dis.\u003c/em\u003e \u003cstrong\u003e74\u003c/strong\u003e, 1390\u0026ndash;1400 (2021).\u003c/li\u003e\n\u003cli\u003eQin, Z. Z. \u003cem\u003eet al.\u003c/em\u003e Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms. \u003cem\u003eLancet Digit. Health\u003c/em\u003e \u003cstrong\u003e3\u003c/strong\u003e, e543\u0026ndash;e554 (2021).\u003c/li\u003e\n\u003cli\u003eQin, Z. Z. \u003cem\u003eet al.\u003c/em\u003e Comparing different versions of computer-aided detection products when reading chest X-rays for tuberculosis. \u003cem\u003ePLOS Digit. Health\u003c/em\u003e \u003cstrong\u003e1\u003c/strong\u003e, e0000067 (2022).\u003c/li\u003e\n\u003cli\u003eFehr, J. \u003cem\u003eet al.\u003c/em\u003e CAD4TB software updates: different triaging thresholds require caution by users and regulation by authorities. \u003cem\u003eInt. J. Tuberc. Lung Dis.\u003c/em\u003e \u003cstrong\u003e27\u003c/strong\u003e, 157\u0026ndash;160 (2023).\u003c/li\u003e\n\u003cli\u003eVanobberghen, F. \u003cem\u003eet al.\u003c/em\u003e Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms. \u003cem\u003eERJ Open Res.\u003c/em\u003e \u003cstrong\u003e10\u003c/strong\u003e, 00508\u0026ndash;02023 (2024).\u003c/li\u003e\n\u003cli\u003eWorld Health Organization. \u003cem\u003eWHO Operational Handbook on Tuberculosis. Module 2: Screening - Systematic Screening for Tuberculosis Disease\u003c/em\u003e. (2021).\u003c/li\u003e\n\u003cli\u003eTDR \u0026amp; World Health Organization. Generic CAD calibration study protocol.\u003c/li\u003e\n\u003cli\u003eHwang, E. J. \u003cem\u003eet al.\u003c/em\u003e AI for Detection of Tuberculosis: Implications for Global Health. \u003cem\u003eRadiol. Artif. Intell.\u003c/em\u003e \u003cstrong\u003e6\u003c/strong\u003e, e230327 (2024).\u003c/li\u003e\n\u003cli\u003eCodlin, A. J. \u003cem\u003eet al.\u003c/em\u003e Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis. \u003cem\u003eSci. Rep.\u003c/em\u003e \u003cstrong\u003e11\u003c/strong\u003e, 23895 (2021).\u003c/li\u003e\n\u003cli\u003eQin, Z. Z. \u003cem\u003eet al.\u003c/em\u003e Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software. \u003cem\u003eLancet Digit. Health\u003c/em\u003e \u003cstrong\u003e6\u003c/strong\u003e, e605\u0026ndash;e613 (2024).\u003c/li\u003e\n\u003cli\u003eWorodria, W. \u003cem\u003eet al.\u003c/em\u003e An independent, multi-country head-to-head accuracy comparison of automated chest x-ray algorithms for the triage of pulmonary tuberculosis. \u003cem\u003emedRxiv\u003c/em\u003e 2024.06.19.24309061 (2024) doi:10.1101/2024.06.19.24309061.\u003c/li\u003e\n\u003cli\u003ePalmer, M. \u003cem\u003eet al.\u003c/em\u003e Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children. \u003cem\u003ePLOS Glob. Public Health\u003c/em\u003e \u003cstrong\u003e3\u003c/strong\u003e, e0001799 (2023).\u003c/li\u003e\n\u003cli\u003eEdem, V. F. \u003cem\u003eet al.\u003c/em\u003e Accuracy of CAD4TB (Computer-Aided Detection for Tuberculosis) on paediatric chest radiographs. \u003cem\u003eEur. Respir. J.\u003c/em\u003e \u003cstrong\u003e64\u003c/strong\u003e, 2400811 (2024).\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eTable 1. Specifications of the CAD products\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"642\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"8\" valign=\"top\" style=\"width: 642px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eProduct information\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003eProduct name\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eInsight CXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eGenki\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eDrAid\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eRadify Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003eProduct version\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eV3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eV7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eV3.1.5.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eV3.4-2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eV1.0.1.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eV2.4 4-6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eV3.8.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003eCompany name\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eQure.ai\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eDelft Imaging Systems\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eLunit Insight\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eDeeptek\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eInfervision\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eVinbrain\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eEnvisionit Deep AI\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003eCountry head office\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eIndia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eThe Netherlands\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eSouth Korea\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eIndia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eChina\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eVietnam\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003eUK\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003eScore range\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0-1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0-100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0-100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0-1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0-1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0-1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0-1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003eManufacturer recommended minimum age\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e6 years \u0026nbsp;and older\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e4 years and older\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e13 years\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0\u0026ndash;14 years paediatric model,\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e15 years and older adult model\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e16 years and older\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e3-15 years paediatric model,\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e16 years and older adult model\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e6-17 years paediatric model,\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e18 years and older adult model\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003eManufacturer recommended threshold\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e60\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0.2 (paediatric model),\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e0.3 (adult model)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0.8 (peadiatric model),\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e0.25 (adult model)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 77px;\"\u003e\n \u003cp\u003e0.2 (peadiatric model),\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e0.2 (adult model)\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eTable 2. Demographic and clinical characteristics of the study population\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"876\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAdults\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eChildren\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAll\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTB\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNo TB\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAll\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTB\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNo TB\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eVariable\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eN\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e%\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eN\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e%\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eN\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e%\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eN\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e%\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eN\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e%\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eN\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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 valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTotal\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e1245\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e315\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e930\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e159\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e120\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSite\u003c/strong\u003e\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: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Badarpur PHI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e226\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e18.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e7.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e204\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e21.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e25.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e5.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e32.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Jahangirpuri PHI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e144\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e11.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e1.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e138\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e14.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e13.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e17.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Sangam Vihar PHI\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e402\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e32.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e4.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e389\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e41.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e26,4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e35.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Nehru Nagar Chest Clinic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e473\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e38.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e274\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e87.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e199\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e21.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e34.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e94.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e15.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eData collection method\u003c/strong\u003e\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: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Prospective\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e772\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e62.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e13.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e731\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e78.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e104\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e65.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e5.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e102\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e85.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Retrospective\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e473\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e38.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e274\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e87.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e199\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e21.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e34.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e94.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e15.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAge group (year)\u003c/strong\u003e\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: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;6-15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e159\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e120\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e100\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;16-35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e702\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e56.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e231\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e73.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e471\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e50.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;36-55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e331\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e26.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e16.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e279\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e30.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;55+\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e212\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e17.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e10.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e180\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e19.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eGender\u003c/strong\u003e\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: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Female\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e580\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e46.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e139\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e44.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e441\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e47.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e49.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e69.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e43.3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Male\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e665\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e53.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e176\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e55.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e489\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e52.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e80\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e50.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e30.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e68\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e56.7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eType of NAAT test done\u003c/strong\u003e\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: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Xpert\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e1047\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e84.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e222\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e70.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e825\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e88.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e132\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e83.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e59.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e109\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e90.8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;First line LPA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e1.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e4.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e3.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e15.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Truenat\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e184\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e14.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e25.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e105\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e11.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e13.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e25.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e9.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHIV status\u003c/strong\u003e\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: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Non-reactive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e403\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e32.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e205\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e65.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e198\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e21.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e31.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e74.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e17.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Reactive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e0.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Unknown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e841\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e67.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e109\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e34.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e732\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e78.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e109\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e68.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e25.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e99\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e82.5\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eDiabetics status\u003c/strong\u003e\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: 66px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\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: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Diabetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e3.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e4.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e3.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Non-diabetic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e453\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e36.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e134\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e42.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e319\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e34.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e47.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e59.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e44.2\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 182px;\"\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp;Unknown\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 67px;\"\u003e\n \u003cp\u003e750\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 66px;\"\u003e\n \u003cp\u003e60.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e168\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e53.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 65px;\"\u003e\n \u003cp\u003e582\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e62.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 72px;\"\u003e\n \u003cp\u003e83\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e52.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e41.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 64px;\"\u003e\n \u003cp\u003e67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 49px;\"\u003e\n \u003cp\u003e55.8\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eLPA=line probe assay, TB=tuberculosis, PHI=peripheral health institute\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eTable 3. Accuracy measures of CAD products for the detection of microbiologically confirmed tuberculosis, evaluated among adults and children for different scenario\u0026rsquo;s\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"0\" cellspacing=\"0\" cellpadding=\"0\" width=\"945\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eThreshold score\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSensitivity (95% CI)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSpecificity (95% CI)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eThreshold score\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 111px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSensitivity\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(95% CI)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSpecificity (95% CI)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 453px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAdults\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 491px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eChildren\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 453px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario A - threshold to match 90% sensitivity\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 491px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario A - threshold to match 90% sensitivity\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e90% (86-93)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e62% (59-65)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e90% (77-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e91% (84-98)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e90% (86-93)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e42% (39-45)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e90% (77-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e77% (66-88)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInsight CXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e90% (87-94)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e29% (26-32)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInsight CXR\u003csup\u003e\u0026dagger;,\u0026Dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e87% (74-97)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e84% (75-93)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eGenki\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e90% (87-94)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e38% (35-41)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eGenki\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.09\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e90% (77-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e77% (64-88)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e90% (86-93)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e27% (24-30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003csup\u003e^\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eDrAid\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e90% (86-93)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e40% (38-44)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eDrAid\u003csup\u003e\u0026dagger;\u003c/sup\u003e \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e90% (77-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e84% (73-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eRadify Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.06\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e90% (87-93)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e31% (28-34)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eRadify Chest\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.03\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e87% (74-97)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e38% (25-50)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 453px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario B - threshold to match 70% specificity\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 491px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario B - threshold to match 70% specificity\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e84% (80-88)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (68-74)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.04\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e97% (90-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e70% (57-80)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e81% (76-85)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e70% (67-72)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e94% (84-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e73% (61-84)\u003csup\u003e#\u003c/sup\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInsight CXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e60\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e80% (75-84)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (68-74)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInsight CXR\u003csup\u003e\u0026dagger;,\u0026Dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e94% (84-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e57% (45-70)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eGenki\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e80% (76-85)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e69% (66-72)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eGenki\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.09\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e90% (77-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e77% (64-88)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e74% (69-78)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e69% (66-72)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003csup\u003e^\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eDrAid\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e80% (76-84)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e70% (67-73)\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eDrAid\u003csup\u003e\u0026dagger;\u003c/sup\u003e \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e97% (90-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e70% (55-82)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eRadify Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e77% (72-82)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e70% (67-73)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eRadify Chest\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e55% (39-71)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (59-84)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 453px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario C - vendor recommended threshold\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 491px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario C - vendor recommended threshold\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e82% (77-86)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e74% (71-76)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eqXR\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.5 (0.54)\u003csup\u003e\u0026infin;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e87% (74-97)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e95% (88-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e60\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e67% (62-72)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e87% (85-89)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e60 (62)\u003csup\u003e\u0026nbsp;\u0026infin;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e81% (68-94)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e96% (91-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInsight CXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e89% (85-92)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e32% (29-35)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInsight CXR\u003csup\u003e\u0026dagger;,\u0026Dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e15 (14)\u003csup\u003e\u0026nbsp;\u0026infin;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e94% (84-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e57% (45-70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eGenki\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e75% (70-80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e78% (75-80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eGenki\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.2 (0.09)\u003csup\u003e\u0026nbsp;\u0026infin;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e90% (77-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e77% (66-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e83% (79-87)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e43% (40-46)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003csup\u003e^\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eDrAid\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.25 (0.26)\u003csup\u003e\u0026nbsp;\u0026infin;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e88% (84-91)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e55% (51-58)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eDrAid\u003csup\u003e\u0026dagger;\u003c/sup\u003e \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.8 (0.76)\u003csup\u003e\u0026nbsp;\u0026infin;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e97% (90-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e70% (57-80)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eRadify Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.2 (0.07)\u003csup\u003e\u0026nbsp;\u0026infin;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e77% (72-82)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e70% (67-73)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eRadify Chest\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.2 (0.04)\u003csup\u003e\u0026nbsp;\u0026infin;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e84% (71-94)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e54% (41-66)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 453px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario D - threshold to match sensitivity of radiologist (71%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 491px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario D - threshold to match sensitivity of radiologist (85%)\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (66-76)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e86% (83-88)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.54\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e87% (74-97)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e95% (88-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e54\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (66-76)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e86% (83-88)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e84% (71-97)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e95% (88-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInsight CXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (66-76)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e89% (87-91)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInsight CXR\u003csup\u003e\u0026dagger;,\u0026Dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e84% (71-97)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e91% (82-98)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eGenki\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (66-77)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e81% (78-83)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eGenki\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e87% (74-97)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e88% (79-96)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.36\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (66-76)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e78% (75-80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003csup\u003e^\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eDrAid\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (66-76)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e85% (82-87)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eDrAid\u003csup\u003e\u0026dagger;\u003c/sup\u003e \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e84% (71-97)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e96% (91-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eRadify Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e71% (66-76)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e79% (76-82)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eRadify Chest\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.04\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e84% (71-94)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e54% (41-66)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 453px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario E - threshold to match specificity of radiologist (83%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"4\" valign=\"bottom\" style=\"width: 491px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario E - threshold to match specificity of radiologist (91%)\u003c/strong\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.84\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e74% (69-79)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e83% (80-85)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eqXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e90% (77-100)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e91% (84-98)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e49\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e72% (67-77)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e83% (81-85)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eCAD4TB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e87% (71-97)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e91% (84-98)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInsight CXR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e83\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e76% (71-81)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e82% (79-84)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInsight CXR\u003csup\u003e\u0026dagger;,\u0026Dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e84% (71-97)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e91% (82-98)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eGenki\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e68% (63-73)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e83% (81-85)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eGenki\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e81% (65-94)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e91% (84-98)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e68% (62-73)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e83% (80-85)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eInferRead DR Chest\u003csup\u003e^\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eDrAid\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e72% (67-77)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e83% (81-86)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eDrAid\u003csup\u003e\u0026dagger;\u003c/sup\u003e \u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e84% (71-97)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e96% (91-100)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"bottom\" style=\"width: 141px;\"\u003e\n \u003cp\u003eRadify Chest\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e0.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e62% (57-68)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e83% (80-85)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 191px;\"\u003e\n \u003cp\u003eRadify Chest\u003csup\u003e\u0026dagger;\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0.94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 111px;\"\u003e\n \u003cp\u003e16% (3-29)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"bottom\" style=\"width: 104px;\"\u003e\n \u003cp\u003e89% (80-96)\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003csup\u003e#\u003c/sup\u003eThe closest sensitivity or specificity to the described scenario. \u0026nbsp;\u0026dagger;Peadiatric TB model used. \u0026Dagger; Analysis restricted to children aged 13-16 year. \u0026nbsp;\u003csup\u003e^\u003c/sup\u003eNot evaluated for children, since vendor recommended age is 16 years and above.\u003csup\u003e\u0026nbsp;\u0026infin;\u003c/sup\u003eIn brackets the closest actual threshold score observed in the data. CAD=computer aided detection\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eTable 4. Effect in terms of number of follow-up tests done and TB cases detected of different threshold scores for qXR in a population of 1000 adults or children with a 5% TB prevalence if examined with chest X-ray and examined by a radiologist or qXR\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"1022\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"7\" valign=\"top\" style=\"width: 545px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eEffect per 1000 individuals tested with CXR\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eScenario\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eThreshold\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSensitivity\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSpecificity\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTB prevalence\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTrue positives (TP)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFalse positives (FP)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTrue negatives (TN)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFalse negatives (FN)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNumber of follow-up test (TP+FP)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eDifference in number of follow-up tests\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eDifference in number TB patients detected\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAdults\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\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: 134px;\"\u003e\n \u003cp\u003eRadiologist reading \u0026ndash; current practice\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e71%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e83%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e162\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e788\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e197\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003eReference\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003eReference\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003eqXR threshold matching radiologist sensitivity\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e71%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e86%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e133\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e817\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e168\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e-29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003eqXR threshold matching vendor recommendation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e0.50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e82%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e74%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e247\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e703\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e288\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003eqXR threshold matching 90% \u0026nbsp;sensitivity\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e0.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e90%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e62%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e361\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e589\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e406\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e209\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eChildren\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\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: 134px;\"\u003e\n \u003cp\u003eRadiologist reading \u0026ndash; current practice\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e85%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e91%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e865\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e128\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003eReference\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003eReference\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003eqXR threshold matching radiologist sensitivity\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e0.54\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e87%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e95%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e903\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e-37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003eqXR threshold matching vendor recommendation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e0.54\u003csup\u003e#\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e87%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e95%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e903\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e-37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 134px;\"\u003e\n \u003cp\u003eqXR threshold matching 90% \u0026nbsp;sensitivity\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003e90%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e91%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 89px;\"\u003e\n \u003cp\u003e5%\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 75px;\"\u003e\n \u003cp\u003e86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e865\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e131\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 85px;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003csup\u003e#\u003c/sup\u003eThe closest threshold to the vendor recommend threshold. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTB=tuberculosis\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Tuberculosis, Computer Aided Detection, Screening, Active case finding, India, Chest X ray","lastPublishedDoi":"10.21203/rs.3.rs-7739612/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7739612/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBefore deploying digital X-ray with Computer Aided Detection (CAD) as a triage tool for tuberculosis (TB), selecting an appropriate product and threshold score is essential to identify patients requiring confirmatory TB testing.\u003c/p\u003e\n\u003cp\u003eWe conducted a combined retrospective case-control and prospective cross-sectional study to evaluated the performance and optimal threshold for qXR v3 (Qure.ai, India) as well as six additional CAD products in individuals with presumptive TB attending peripheral health institutes (PHIs) in India. Accuracy was assessed against a microbiological reference standard separately for adults (≥16 year) \u0026nbsp;and children (6-16 year).\u003c/p\u003e\n\u003cp\u003eAmong 1245 adults (315 TB-positive, 930 TB-negative) and 159 children (39 TB-positive, 120 TB-negative), qXR demonstrated high accuracy both in adults (AUCROC: 0.88 [95% CI of 0.85-0.90], and children (AUCROC: 0.95 [95% CI 0.89-1.0]). and performed as good as the radiologist in both groups. Sensitivity increased with minimal loss in specificity when using the vendor recommended threshold. CAD4TB, Insight CXR, DrAid, and Genki also demonstrated high accuracy (AUCROC: adults ≥0.80, AUCROCs children ≥0.90), while InferRead DR Chest and Radify Chest performed less well.\u003c/p\u003e\n\u003cp\u003eLocal validation confirmed high accuracy for qXR and several other products, in identifying TB in adults and children in India, supporting their potential implementation in similar settings.\u003c/p\u003e","manuscriptTitle":"Validation of several TB-CAD chest-X-ray applications in individuals with presumptive TB visiting peripheral health institutes in Delhi State","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-15 16:11:44","doi":"10.21203/rs.3.rs-7739612/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-03T13:19:52+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"182629348364260324304507416825911356233","date":"2025-11-02T05:59:25+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-31T07:51:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-17T19:50:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"90965338871191791169199877542450140159","date":"2025-10-13T06:58:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"328939912332617321032785086872528091565","date":"2025-10-13T06:15:24+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-02T05:26:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-02T05:24:47+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-01T09:20:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-01T07:19:17+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-10-01T07:16:21+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"221b9d99-bda4-481e-82b4-90816b9ca79d","owner":[],"postedDate":"October 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":56180128,"name":"Health sciences/Diseases"},{"id":56180129,"name":"Health sciences/Health care"},{"id":56180130,"name":"Health sciences/Medical research"},{"id":56180131,"name":"Biological sciences/Microbiology"}],"tags":[],"updatedAt":"2026-05-20T11:54:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-15 16:11:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7739612","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7739612","identity":"rs-7739612","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}