Accuracy of Artificial Intelligence in Detecting Tuberculosis from Chest X-ray: A Systematic Review and Meta-Analysis of Diagnostic Performance
Downloads
Tuberculosis (TB) remains a major global public health challenge, particularly in low-resource countries where access to trained radiologists is limited, making Chest X-ray (CXR) screening difficult to scale. The advancement of Artificial Intelligence (AI) and Computer-Aided Detection (CAD) technology offers a potential solution by providing automated TB detection and supporting diagnostic workflows. To assess their clinical readiness, this systematic review and meta-analysis was conducted using the PRISMA 2020 protocol and included studies from PubMed, Scopus, and Semantic Scholar that evaluated AI-CAD systems (Index Test) against microbiological or extended reference standards (Reference Standard). The Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2 and QUADAS-C) tools were applied to measure risk of bias, and a random-effects model was used to estimate pooled Diagnostic Odds Ratio (DOR). Six studies with approximately 38,940 participants were eligible for analysis. Results showed a pooled DOR of 0.133 (95% CI: 0.047–0.377), indicating a significantly lower diagnostic error rate (P=0.000). Although sensitivity was consistently high (83.3%–100%), specificity varied widely (26.8%–98.9%), resulting in notable heterogeneity and a wide prediction interval (0.003–6.411). These findings conclude that AI-CAD tools demonstrate strong potential for TB screening but should undergo local validation, threshold calibration, and operational evaluation before broad clinical implementation, especially where specificity remains below the WHO Target Product Profile.
Copyright (c) 2026 Singgih Priyambodo, Iwan Danardono
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International (CC-BY-SA). that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
