Chest x-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: a prospective study of diagnostic accuracy for culture-confirmed disease
Open accessAbstract
BACKGROUND: Deep learning-based radiological image analysis could facilitate use of chest x-rays as triage tests for pulmonary tuberculosis in resource-limited settings. We sought to determine whether commercially available chest x-ray analysis software meet WHO recommendations for minimal sensitivity and specificity as pulmonary tuberculosis triage tests. METHODS: We recruited symptomatic adults at the Indus Hospital, Karachi, Pakistan. We compared two software, qXR version 2.0 (qXRv2) and CAD4TB version 6.0 (CAD4TBv6), with a reference of mycobacterial culture of two sputa. We assessed qXRv2 using its manufacturer prespecified threshold score for chest x-ray classification as tuberculosis present versus not present. For CAD4TBv6, we used a data-derived threshold, because it does not have a prespecified one. We tested for non-inferiority to preset WHO recommendations (0·90 for sensitivity, 0·70 for specificity) using a non-inferiority limit of 0·05. We identified factors associated with accuracy by stratification and logistic regression. FINDINGS: We included 2198 (92·7%) of 2370 enrolled participants. 2187 (99·5%) of 2198 were HIV-negative, and 272 (12·4%) had culture-confirmed pulmonary tuberculosis. For both software, accuracy was non-inferior to WHO-recommended minimum values (qXRv2 sensitivity 0·93 [95% CI 0·89-0·95], non-inferiority p=0·0002; CAD4TBv6 sensitivity 0·93 [0·90-0·96], p<0·0001; qXRv2 specificity 0·75 [0·73-0·77], p<0·0001; CAD4TBv6 specificity 0·69 [0·67-0·71], p=0·0003). Sensitivity was lower in smear-negative pulmonary tuberculosis for both software, and in women for CAD4TBv6. Specificity was lower in men and in those with previous tuberculosis, and reduced with increasing age and decreasing body mass index. Smoking and diabetes did not affect accuracy. INTERPRETATION: In an HIV-negative population, these software met WHO-recommended minimal accuracy for pulmonary tuberculosis triage tests. Sensitivity will be lower when smear-negative pulmonary tuberculosis is more prevalent. FUNDING: Canadian Institutes of Health Research.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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 majority of studies reporting on CAD threshold determination only included individuals who met criteria for microbiological testing.
“The majority of studies reporting on CAD threshold determination only included individuals who met some criteria for microbiological testing, such as having symptoms and/or abnormal chest radiographs [8, 16–27].”
From Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms. (2024) · cites this paper as [17]
Specificity was poorer in those with history of tuberculosis, as expected and corresponding to findings in other settings.
“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 [17]
Cites
pROC: an open-source package for R and S+ to analyze and compare ROC curves
Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.-C., & Müller, M. (2011) · BMC Bioinformatics · doi:10.1186/1471-2105-12-77 · Cited by 13,697 · see citing works
Lakhani, P., & Sundaram, B. (2017) · Radiology · doi:10.1148/radiol.2017162326 · Cited by 1,775 · see citing works
Engaging the private sector to increase tuberculosis case detection: an impact evaluation study
Khan, A. J., Khowaja, S., Khan, F. S., Qazi, F., Lotia, I., Habib, A., Mohammed, S., Khan, U., Amanullah, F., Hussain, H., et al. (2012) · The Lancet Infectious Diseases · doi:10.1016/s1473-3099(12)70116-0 · Cited by 136 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
How does artificial intelligence in radiology improve efficiency and health outcomes?
van Leeuwen, K. G., de Rooij, M., Schalekamp, S., van Ginneken, B., & Rutten, M. J. C. M. (2022) · Pediatric Radiology · doi:10.1007/s00247-021-05114-8 · Cited by 236 · see citing works
Geric, C., Qin, Z. Z., Denkinger, C. M., Kik, S. V., Marais, B., Anjos, A., David, P.-M., Ahmad Khan, F., & Trajman, A. (2023) · The International Journal of Tuberculosis and Lung Disease · doi:10.5588/ijtld.22.0687 · Cited by 61 · see citing works
Mungai, B., Ong‘angò, J., Ku, C. C., Henrion, M. Y. R., Morton, B., Joekes, E., Onyango, E., Kiplimo, R., Kirathe, D., Masini, E., et al. (2022) · PLOS Global Public Health · doi:10.1371/journal.pgph.0001272 · Cited by 24 · see citing works
“People with prior TB have lung changes that could lead to difficulty distinguishing old vs active disease, leading to low specificity [8,16].”
Vanobberghen, 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 · see citing works
- Authors
- Khan, F. A., Majidulla, A., Tavaziva, G., Nazish, A., Abidi, S. K., Benedetti, A., Menzies, D., Johnston, J. C., Khan, A. J., & Saeed, S.
- Affiliations
- Research Institute of the McGill University Health Centre (CA)
- Interactive Research and Development (PK)
- Indus Hospital (PK)
- McGill University Health Centre (CA)
- University of British Columbia (CA)
- Corresponding author
- Khan, Faiz Ahmad
- ORCID
- Venue
- The Lancet Digital Health
- Publisher
- Elsevier BV
- Published
- 2020-11
- Volume
- 2
- Issue
- 11
- Pages
- e573-e581
- ISSN
- 2589-7500 (ISSN-L)
- OpenAlex
- W3094350134
- Cited by
- 134
- References
- 3
- Citations by year
- 2026: 10 · 2025: 21 · 2024: 30 · 2023: 26 · 2022: 28 · 2021: 18 · 2020: 1
- FWCI
- 2.40
- Type
- journal article
- Language
- en
- Update notices
- erratum (2020-12-01)
- Open access
- gold
- doi.org
- Licence
- Locations
- The Lancet Digital Health (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Funders
- Canadian Institutes of Health Research
- 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 › Health Informatics › Artificial Intelligence in Healthcare and Education
- Keywords
- pulmonary tuberculosis, triage test, CAD4TB, diagnostic accuracy, non-inferiority, mycobacterial culture, smear-negative tuberculosis, resource-limited settings, WHO guidelines, sensitivity and specificity, HIV-negative individuals, body mass index, smoking, diabetes mellitus, history of tuberculosis, age, Karachi
- MeSH terms
- Deep Learning, Adult, Age Factors, Female, Humans, Image Processing, Computer-Assisted, Lung, Male, Middle Aged, Mycobacterium tuberculosis, Pakistan, Prospective Studies, Radiology, Sensitivity and Specificity, Sex Factors, Software, Sputum, Triage, Tuberculosis, Pulmonary, X-Rays, HIV Infections, Body Mass Index, Young Adult
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.
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
