Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index; 11 of the 20 sources its claims cite were checked for support.
Abstract
Community-based screening for tuberculosis (TB) could improve detection but is resource intensive. We set out to evaluate the accuracy of computer-aided TB screening using digital chest X-ray (CXR) to determine if this approach met target product profiles (TPP) for community-based screening. CXR images from participants in the 2016 Kenya National TB Prevalence Survey were evaluated using CAD4TBv6 (Delft Imaging), giving a probabilistic score for pulmonary TB ranging from 0 (low probability) to 99 (high probability). We constructed a Bayesian latent class model to estimate the accuracy of CAD4TBv6 screening compared to bacteriologically-confirmed TB across CAD4TBv6 threshold cut-offs, incorporating data on Clinical Officer CXR interpretation, participant demographics (age, sex, TB symptoms, previous TB history), and sputum results. We compared model-estimated sensitivity and specificity of CAD4TBv6 to optimum and minimum TPPs. Of 63,050 prevalence survey participants, 61,848 (98%) had analysable CXR images, and 8,966 (14.5%) underwent sputum bacteriological testing; 298 had bacteriologically-confirmed pulmonary TB. Median CAD4TBv6 scores for participants with bacteriologically-confirmed TB were significantly higher (72, IQR: 58-82.75) compared to participants with bacteriologically-negative sputum results (49, IQR: 44-57, p<0.0001). CAD4TBv6 met the optimum TPP; with the threshold set to achieve a mean sensitivity of 95% (optimum TPP), specificity was 83.3%, (95% credible interval [CrI]: 83.0%-83.7%, CAD4TBv6 threshold: 55). There was considerable variation in accuracy by participant characteristics, with older individuals and those with previous TB having lowest specificity. CAD4TBv6 met the optimal TPP for TB community screening. To optimise screening accuracy and efficiency of confirmatory sputum testing, we recommend that an adaptive approach to threshold setting is adopted based on participant characteristics.
Overview
CoChat Summary
TL;DR
This retrospective analysis of the 2016 Kenya National TB Prevalence Survey found that CAD4TBv6 performed well for community TB screening and met the paper’s target product profile at an overall threshold of 55. Accuracy varied by participant characteristics, with lower specificity in older people and those with previous TB, supporting adaptive thresholding.
Key findings
- Of 62,484 CXR images uploaded, 61,848 (99.0%) were analysable and included; 8,996/61,848 (14.5%) had sputum collected, and 298 had bacteriologically-confirmed TB.
- The median CAD4TBv6 score was higher in bacteriologically-confirmed TB than in bacteriologically-negative sputum results: 72 vs 49.
- Overall model estimates for CAD4TBv6 were AUC 96.7% (95% CrI 95.9%–97.4%); at a sensitivity target of 95% (optimum TPP), specificity was 83.2%–83.3% and the threshold was 55.
- Accuracy varied by subgroup: sensitivity was highest among those aged 41 years and older, those with cough >2 weeks, and those with previous TB; specificity was lowest among older participants and those with previous TB. Clinical Officer CXR interpretation as “suggestive of TB” had overall sensitivity 43.7% and specificity 89.2% for bacteriologically-confirmed TB.
Methods
- Retrospective analysis of cross-sectional individual-level data from adults (aged 15+ years) in the 2016 Kenya National TB Prevalence Survey, a population-based national survey conducted in 2015–2016 across 100 clusters.
- Analysed 61,848 participants with CXR images; CAD4TBv6 processed anonymised DICOM CXR images and generated scores from 0 to 99. Reference standard was bacteriologically-confirmed TB defined as Xpert and/or culture positive with MTB speciation.
- Primary analysis used Bayesian latent class modelling in Stan/R to estimate TB prevalence and CAD4TBv6 sensitivity, specificity, and AUC across thresholds 0–99; secondary analyses stratified by age, sex, cough >2 weeks, and previous TB history.
Limitations
- The paper states it included participants aged 15 years and above, so it could not assess CAD4TBv6 accuracy in children.
- The study only included bacteriologically-confirmed TB and did not assess accuracy in sputum-negative, clinically diagnosed TB; the paper states this explicitly.
- HIV status could not be used for stratified analysis because testing was not systematically conducted and there was substantial missing data; this is stated in the paper.
- Evident from the design: sputum collection was conditional on symptoms or abnormal CXR, so latent class modelling was needed and some reference-standard information was missing for part of the cohort.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
7 Valid · 0 Not valid · 4 Not checked · 41 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“As in other studies, we have demonstrated that CAD at varied thresholds achieves higher sensitivity than human readers [6,8,14].”
§ Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey > Discussion
What the sources say
- Partly supportedcites [6] K Murphy, 2020, Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system, Scientific Reports sourceExperimental — accuracy not yet measured
The Results (CAD4TB performance) compare CAD4TB v6 across operating points with five human readers and report a significant advantage over one non-physician reader at high sensitivities. They describe its performance as very similar to expert readers, not generally more sensitive than human readers at varied thresholds. (LLM, conf=0.86)
- Partly supportedcites [8] ZZ Qin, 2021, Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: an evaluation of five artificial intelligence algorithms, The Lancet Digital Health sourceExperimental — accuracy not yet measured
Our copy supports the framing that CAD/AI performance was assessed across varied threshold abnormality scores and that all five algorithms significantly outperformed the radiologists (Findings; Results, figure 2 threshold discussion; Discussion conclusion). However, the head-to-head comparison with human readers was constructed by matching the AI algorithms' sensitivity to that of the radiologists and reporting a specificity (and PPV) advantage at that equal sensitivity (Methods 'Data analysis'; Results, table 3 paragraph) — no passage states that CAD achieves higher sensitivity than human readers. The sensitivity-versus-readers direction of the citing sentence is therefore not attributed to this source; the supported part is the threshold-varying superiority in specificity/overall accuracy over three radiologists in metropolitan Dhaka. (LLM, conf=0.72)
- Partly supportedcites [14] M Breuninger, 2014, Diagnostic accuracy of computer-aided detection of pulmonary tuberculosis in chest radiographs: a validation study from sub-Saharan Africa, PLoS One sourceExperimental — accuracy not yet measured
Table 4 (Results; page unavailable) shows that CAD4TB reached 95% sensitivity at one cut-off, exceeding the expert reader’s highest listed sensitivity of 84%. But the clinical officer reached 97% at the ‘any abnormality’ threshold, and the Results compare CAD with readers at matched sensitivities. The paper therefore supports higher sensitivity at some thresholds, not a general advantage over human readers. (LLM, conf=0.87)
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“and was 97.0% (95% CrI: 96.5%-97.5%) among participants with cough for two weeks or longer”
§ Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey > Results > Model estimated TB prevalence and accuracy of clinical officer CXR interpretation, sputum testing and CAD4TBv6 screening
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The posterior mean estimate of the AUC for CAD4TBv6 was 96.7% (95% CrI: 95.9%-97.4%).”
§ Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey > Results > Model estimated TB prevalence and accuracy of clinical officer CXR interpretation, sputum testing and CAD4TBv6 screening
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we estimated that the overall sensitivity of Clinical Officer CXR interpretation as “suggestive of TB” for bacteriologically-confirmed TB was 43.7% (95% CrI: 23.8–66.4%)”
§ Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey > Results > Model estimated TB prevalence and accuracy of clinical officer CXR interpretation, sputum testing and CAD4TBv6 screening
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“With CAD4TBv6 thresholds set to achieve a specificity of 70% (minimum TPP) or 80% (optimum TPP), mean sensitivity was 98.3% (95% CrI: 97.6–99.8%) and 96.2% (95.0–97.3%).”
§ Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey > Results > Model estimated TB prevalence and accuracy of clinical officer CXR interpretation, sputum testing and CAD4TBv6 screening
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
27 more claims
Create a free account to see all 52 claims and to verify the 2 references still open.
- Probably not a substantial claim. 8
- It may state two separate claims as one. 17
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“To date, only one study has attempted to address this problem in a principled way, using latent class analyses (LCA) to account for the missingness in tuberculosis status [11].”
From Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms. (2024) · cites this paper as [11]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Some developers recommend a threshold score for universal use, above which an individual would be classified as having abnormalities suggestive of tuberculosis [6, 7]. Other developers, such as CAD4TB (Delft Imaging Systems, Netherlands), recommend scores tailored to each setting due to variation in CAD abnormality scores between different software and populations [5, 6, 8–13]”
From Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms. (2024) · cites this paper as [11]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Lastly, specificity was poorer in those with history of tuberculosis, as expected and corresponding to findings in other settings [11, 17, 23, 43].”
From Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms. (2024) · cites this paper as [11]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey > Results > CAD4TBv6 scores by sputum testing and bacteriological TB status
“Sputum was collected from 8,996/61,848 (14.5%) participants, of whom 298 (3.3%) had bacteriologically-confirmed TB.”
§ Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey > Abstract
“Of 63,050 prevalence survey participants, 61,848 (98%) had analysable CXR images, and 8,966 (14.5%) underwent sputum bacteriological testing; 298 had bacteriologically-confirmed pulmonary TB.”
Citations
Cites
Global tuberculosis report (2014)
Gabbasova, L. A., & Who, E. R. E. (2014) · Cited by 12,702
Chakaya, J., Khan, M., Ntoumi, F., Aklillu, E., Fatima, R., Mwaba, P., Kapata, N., Mfinanga, S., Hasnain, S. E., Katoto, P. D. M. C., et al. (2021) · International Journal of Infectious Diseases · doi:10.1016/j.ijid.2021.02.107 · Cited by 1,104 · cited 1×
“With over 95% tuberculosis (TB) cases and deaths occurring in developing countries, there is need for substantially improved case detection to find the “missing millions” and accelerate action to achieve the sustainable development goals to end TB by 2030 [1–4].”
The General Data Protection Regulation: An Opportunity for the HCI Community?
Thelisson, E., Sharma, K., Salam, H., & Dignum, V. (2018) · Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3170427.3170632 · Cited by 991
Active case finding of tuberculosis: historical perspective and future prospects.
Golub, J. E., Mohan, C., Comstock, G. W., & Chaisson, R. E. (2005) · PubMed · Cited by 341
Frascella, B., Richards, A. S., Sossen, B., Emery, J. C., Odone, A., Law, I., Onozaki, I., Esmail, H., & Houben, R. M. G. J. (2021) · Clinical Infectious Diseases · doi:10.1093/cid/ciaa1402 · Cited by 315
Perlman, D. C., El‐Sadr, W. M., Nelson, E. T., Matts, J. P., Telzak, E. E., Salomon, N., Chirgwin, K., & Hafner, R. (1997) · Clinical Infectious Diseases · doi:10.1086/514546 · Cited by 295
Qin, Z. Z., Ahmed, S., Sarker, M. S., Paul, K., Adel, A. S. S., Naheyan, T., Barrett, R., Banu, S., & Creswell, J. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(21)00116-3 · Cited by 290
Qin, Z. Z., Sander, M. S., Rai, B., Titahong, C. N., Sudrungrot, S., Laah, S. N., Adhikari, L. M., Carter, E. J., Puri, L., Codlin, A. J., et al. (2019) · Scientific Reports · doi:10.1038/s41598-019-51503-3 · Cited by 289
Toman's Tuberculosis: Case Detection, Treatment and Monitoring: Questions and Answers
Frieden, T. R. (2004) · Cited by 264
Community-wide Screening for Tuberculosis in a High-Prevalence Setting
Marks, G. B., Nguyen, N. V., Nguyen, P. T. B., Nguyen, T.-A., Nguyen, H. B., Tran, K. H., Nguyen, S. V., Luu, K. B., Tran, D. T. T., Vo, Q. T. N., et al. (2019) · New England Journal of Medicine · doi:10.1056/nejmoa1902129 · Cited by 230
Research works printed but not linked: 9
- World Health Organization, 2020, Global tuberculosis report 2020
- World Health Organization, 2020, Tuberculosis key facts
- World Health Organization, 2015, The END TB Strategy
- World Health Organization, 2014, High-priority target product profiles for new tuberculosis diagnostics: report of a consensus meeting.
- World Health Organization, 2011, Tuberculosis prevalence surveys: a handbook.
- DI Systems, 2019, Xray systems
- World Health Organization, 1968, Principles and practice of screening for disease / J. M. G. Wilson, G. Jungner
- D. Imaging, 2021, Delft Imaging
- B Hochhegger, 2012, The chest and aging: radiological findings., Jornal brasileiro de pneumologia: publicacao oficial da Sociedade Brasileira de Pneumologia e Tisilogia, 38, 656
Cited by
Kagujje, M., Kerkhoff, A. D., Nteeni, M., Dunn, I., Mateyo, K. J., & Muyoyeta, M. (2022) · Clinical Infectious Diseases · doi:10.1093/cid/ciac679 · Cited by 44
Community-based active-case finding for tuberculosis: navigating a complex minefield
MacPherson, P., Shanaube, K., Phiri, M. D., Rickman, H. M., Horton, K. C., Feasey, H. R. A., Corbett, E. L., Burke, R. M., & Rangaka, M. X. (2024) · BMC Global and Public Health · doi:10.1186/s44263-024-00042-9 · Cited by 61
“However, individual-level characteristics appear to have a large effect on CAD specificity, with older age, previous TB history, and possibly HIV infection increasing false-positive screens [68, 69].”
BackgroundSelf-citationAI for Detection of Tuberculosis: Implications for Global Health
Hwang, E. J., Jeong, W. G., David, P., Arentz, M., Rühwald, M., & Yoon, S. H. (2024) · Radiology Artificial Intelligence · doi:10.1148/ryai.230327 · Cited by 49
Kyambade, M., & Namatovu, A. (2025) · Leadership in health services · doi:10.1108/lhs-02-2025-0025 · Cited by 37
AI Applications for Thoracic Imaging: Considerations for Best Practice
Hwang, E. J., Goo, J. M., & Park, C. M. (2025) · Radiology · doi:10.1148/radiol.240650 · Cited by 37
Scott, A. J., Perumal, T., Hohlfeld, A., Oelofse, S., Kühn, L., Swanepoel, J., Geric, C., Khan, F. A., Esmail, A., Ochodo, E., et al. (2024) · Open Forum Infectious Diseases · doi:10.1093/ofid/ofae020 · Cited by 28
“The CAD threshold was only predefined in 2 studies [31, 33], with the 3 remaining studies reporting threshold scores postanalysis [30, 32, 34], and therefore determined to have high risk of bias.”
BackgroundMethodInfluentialVanobberghen, F., Keter, A. K., Jacobs, B. K. M., Glass, T. R., Lynen, L., Law, I., Murphy, K., van Ginneken, B., Ayakaka, I., van Heerden, A., et al. (2024) · ERJ Open Research · doi:10.1183/23120541.00508-2023 · Cited by 13
“Lastly, specificity was poorer in those with history of tuberculosis, as expected and corresponding to findings in other settings [11, 17, 23, 43].”
MethodResultBiewer, A., Tzelios, C., Tintaya, K., Roman, B., Hurwitz, S., Yuen, C. M., Mitnick, C. D., Nardell, E. A., Lecca, L. W., Tierney, D. B., et al. (2024) · PLOS Global Public Health · doi:10.1371/journal.pgph.0002031 · Cited by 18
Bosman, S., Ayakaka, I., Muhairwe, J. A., Kamele, M., van Heerden, A. C., Madonsela, T., Labhardt, N. D., Sommer, G., Bremerich, J., Zöller, T., et al. (2024) · Clinical Infectious Diseases · doi:10.1093/cid/ciae378 · Cited by 19
“Consistent with previous CAD studies [11, 27, 28], the AUROC of CAD4TBv7 was significantly lower in individuals with previous tuberculosis, most likely due to post-tuberculous residual lung abnormalities resulting in lower specificity.”
Schwalb, A., Horton, K. C., Emery, J. C., Harker, M. J., Goscé, L., Veeken, L. D., Garden, F. L., Nguyen, H. V., Nguyen, T. A., Luu, K. B., et al. (2025) · PLOS Global Public Health · doi:10.1371/journal.pgph.0005050 · Cited by 10
Abuzerr, S. S., & Zinszer, K. (2023) · Frontiers in Public Health · doi:10.3389/fpubh.2023.1254658 · Cited by 11
Keter, A., Vanobberghen, F. M., Lynen, L., van Heerden, A. C., Fehr, J., Olivier, S., Wong, E. B., Glass, T. R., Reither, K., Goetghebeur, E. J. T., et al. (2024) · PLoS ONE · doi:10.1371/journal.pone.0305126 · Cited by 5
Giridharan, P., Inbaraj, L. R., Frederick, A., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-94346-x · Cited by 3
“9 .”
Sung, J., Kitonsa, P. J., Nalutaaya, A., et al. (2025) · medRxiv · doi:10.1101/2025.04.09.25325458 · Cited by 2
Biewer, A., Tzelios, C., Tintaya, K., Roman, B., Hurwitz, S., Yuen, C. M., Mitnick, C. D., Nardell, E. A., Lecca, L. W., Tierney, D. B., et al. (2023) · medRxiv · doi:10.1101/2023.05.17.23290110 · Cited by 2
Somwe, P., Maimbolwa, M. M., Chiyenu, K., Lumpa, M., Kagujje, M., & Muyoyeta, M. (2025) · PLOS Global Public Health · doi:10.1371/journal.pgph.0003955 · Cited by 4
da Silva, M. C. B., de Camargo, T. F. O., de Paiva, J. P. Q., Horvath, J. D. C., & Ribeiro, G. (2025) · doi:10.5753/sbcas_estendido.2025.7025 · Cited by 1
Schwalb, A., Horton, K. C., Emery, J. C., et al. (2024) · medRxiv · doi:10.1101/2024.12.30.24319770 · Cited by 1
Carnimeo, V., Phillips, E. L. Y., Galvan, D. K., Camélique, O., Roxas, M. R., Duka, M., Pardilla, G. F., Recidoro, M. J. C., Castro, R. H., Hossain, F., et al. (2026) · PLOS Global Public Health · doi:10.1371/journal.pgph.0006908 · Cited by 1
“This insight is also supported by Fehr and colleagues [18] who emphasize the risks of using the same threshold across different software versions without accounting for performance variations and highlight the critical need for transparency and clear guidance when transitioning between versions of…”
Bakker, M. I., Krugu, J. K., Mergenthaler, C., Adusi-Poku, Y., Amenyo, R. P. F., Wadie, B., Afutu, F. K., Mensah, M., Alebachew, Z., Asambobillah, R., et al. (2026) · PLOS Global Public Health · doi:10.1371/journal.pgph.0006874
“This approach is more cost-effective and feasible when primarily offered to individuals with symptoms or those at higher risk for TB [41]; however, this strategy forfeits the advantage of identifying asymptomatic patients [42].”
Horton, K. C., Richards, A. S., Schwalb, A., & Houben, R. M. G. J. (2026) · PLoS Medicine · doi:10.1371/journal.pmed.1005040
“Probabilities of a positive test were broadly based on sensitivity for sTB and specificity for non-TB states [3,19–21], complemented by data from national TB prevalence surveys [22,23], with assumptions where no data were available (Tables C and D in S1 Appendix).”
Odhiambo, O. C., & Orowe, I. (2026) · American Journal of Theoretical and Applied Statistics · doi:10.11648/j.ajtas.20261689.12
Sung, J., Kitonsa, P. J., Nalutaaya, A., Isooba, D., Birabwa, S., Ndyabayunga, K., Okura, R., Magezi, J., Nantale, D., Mugabi, I., et al. (2025) · The Lancet Digital Health · doi:10.1016/j.landig.2025.100934 · Cited by 6
“…screening-eligible individuals in accuracy estimates increases the number of true negatives (ie, no tuberculosis, with low x-ray scores) and results in higher specificities of CAD, as reported by studies 28,29 including ours, that included individuals with normal x-rays in CAD accuracy estimation.”
Horton, K. C., Richards, A. S., Schwalb, A., & Houben, R. M. G. J. (2025) · medRxiv · doi:10.1101/2025.08.22.25334237
Zayed, O., Ibrahim, L., & Mansour, A. (2024) · Journal of Medical Sciences and Interdisciplinary Research · doi:10.51847/zrwoaky1h7
Metadata
- Authors
- Mungai, B., Ong‘angò, J., Ku, C. C., Henrion, M. Y. R., Morton, B., Joekes, E., Onyango, E., Kiplimo, R., Kirathe, D., Masini, E., Sitienei, J., Manduku, V., Mugi, B., Squire, S. B., MacPherson, P., & The IMPALA Consortium
- Affiliations
- Liverpool School of Tropical Medicine (GB)
- Imperial College London (GB)
- Global Fund to Fight AIDS, Tuberculosis and Malaria (CH)
- Kenya Medical Research Institute (KE)
- Kenyatta National Hospital (KE)
- Corresponding author
- Mungai, Brenda
- ORCID
- Venue
- PLOS Global Public Health
- Publisher
- Public Library of Science (PLoS)
- Published
- 2022-11-23
- Volume
- 2
- Issue
- 11
- Pages
- e0001272
- ISSN
- 2767-3375 (ISSN-L)
- PMC
- PMC10022380
- OpenAlex
- W4309796546
- Cited by
- 24
- References
- 26
- Citations by year
- 2026: 5 · 2025: 8 · 2024: 7 · 2023: 3 · 2022: 1
- FWCI
- 2.32
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLOS Global Public Health (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- LSTM Online Archive (Liverpool School of Tropical Medicine) (acceptedVersion)
- ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam) (acceptedVersion, cc-by-sa)
- LSHTM Research Online (London School of Hygiene and Tropical Medicine) (acceptedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Institute for Health Research (16/136/35)
- Wellcome (200901/Z/16/Z)
- Malawi Liverpool Wellcome Trust Programme (206545/Z/17/Z)
- Topics
- Health Sciences › Medicine › Infectious Diseases › Tuberculosis Research and Epidemiology
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Lung Cancer Diagnosis and Treatment
- Keywords
- tuberculosis screening, computer-aided detection, pulmonary tuberculosis, target product profile, screening accuracy, sensitivity and specificity, Bayesian latent class model, community-based screening
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.