A multi-country head-to-head accuracy comparison of automated chest X-ray algorithms for tuberculosis

Authors

• William Worodria, World Alliance for Lung and Intensive Care Medicine in Uganda
• Robert Castro, University of California, San Francisco
• Sandra V. Kik, FIND
• Victoria Dalay, De La Salle Medical and Health Sciences Institute
• Brigitta Derendinger, Stellenbosch University, Faculty of Medicine and Health Sciences
• Charles Festo, Ifakara Health Institute
• Thanh Quoc Nguyen, National Lung Hospital
• Mihaja Raberahona, Centre Hospitalier Universitaire d'Antananarivo - Hôpital Joseph Ravoahangy Andrianavalona
• Swati Sudarsan, University of California, San Francisco
• Alfred Andama, World Alliance for Lung and Intensive Care Medicine in Uganda
• Balamugesh Thangakunam, Christian Medical College, Vellore
• Issa Lyimo, Ifakara Health Institute
• Viet Nhung Nguyen, National Lung Hospital
• Rivo Rakotoarivelo, Université d'Antananarivo
• Grant Theron, Stellenbosch University, Faculty of Medicine and Health Sciences
• Charles Yu, De La Salle Medical and Health Sciences Institute
• Claudia M. Denkinger, Universitätsklinikum Heidelberg
• Simon Grandjean Lapierre, Centre Hospitalier de L'Université de Montréal
• Adithya Cattamanchi, University of California, San Francisco
• Devasahayam J. Christopher, Centre Hospitalier Universitaire d'Antananarivo - Hôpital Joseph Ravoahangy Andrianavalona
• Devan Jaganath, University of California, San Francisco

Publication Date

5-1-2026

Document Type

Article

Publication Title

Annals of the American Thoracic Society

Abstract

Rationale: Computer-aided detection algorithms for automated chest X-ray reading have been endorsed by the World Health Organization for tuberculosis triage, but independent, multi-country assessment of current products is needed to guide implementation. Objectives: We included chest X-rays from adults who presented to outpatient facilities with at least 2 weeks of cough in India, Madagascar, the Philippines, South Africa, Tanzania, Uganda, and Vietnam. Methods: We calculated and compared the accuracy overall and by country and key groups for 7 computer-aided detection algorithms: CAD4TB, qXR, INSIGHT CXR, DrAid, Genki, InferRead, and Radify. We determined if any computer-aided detection product could achieve the minimum target accuracy for a tuberculosis triage test (≥ 90% sensitivity and ≥ 70% specificity). Results: Of 3901 individuals included, the median age was 41 years (IQR, 29-54 years), 12.9% were people living with HIV, 8.2% were living with diabetes, and 21.2% had a prior history of tuberculosis. Specificity ranged from 30.9% to 73.5% at 90% sensitivity. CAD4TB achieved the highest specificity at 90% sensitivity (73.5% specific [95% CI, 71.9%-75.1%]), although qXR and INSIGHT CXR also achieved the target 70% specificity. There was heterogeneity by country and subgroup that improved with population-specific thresholds, except for people living with HIV, 50 years and older, or with a history of tuberculosis. Conclusions: Multiple computer-aided detection algorithms achieved the minimum target accuracy for a tuberculosis triage test among symptomatic individuals with cough. Further efforts are needed to integrate computer-aided detection into routine tuberculosis case detection programs in high-burden communities.

First Page

728

Last Page

736

APA Citation

Worodria, W., Castro, R., Kik, S., Dalay, V., Derendinger, B., Festo, C., Nguyen, T., Raberahona, M., Sudarsan, S., Andama, A., Thangakunam, B., Lyimo, I., Nguyen, V., Rakotoarivelo, R., Theron, G., Yu, C., Denkinger, C., Lapierre, S., Cattamanchi, A., Christopher, D., & Jaganath, D. (5-1-2026). A multi-country head-to-head accuracy comparison of automated chest X-ray algorithms for tuberculosis. Faculty Research and Scholarly Works.
DOI:10.1093/annalsats/aaoag011