Artificial Intelligence and Machine Learning-based prediction of tuberculosis treatment failure: A systematic review and meta-analysis

Rogers Kamulegeya, Rose Nabatanzi, Derrick Semugenze, Faridah Mugala, Mercy Takuwa, Emmanuel Nasinghe, Denis Musinguzi, Sharon Namiiro · 2026

Read Artificial Intelligence and Machine Learning-based prediction of tuberculosis treatment failure: A systematic review and meta-analysis by Rogers Kamulegeya, Rose Nabatanzi, Derrick Semugenze, Faridah Mugala, Mercy Takuwa, Emmanuel Nasinghe, Denis Musinguzi, Sharon Namiiro (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0355124.txt.

Description

Rogers Kamulegeya and seven colleagues systematically review artificial intelligence models that predict whether tuberculosis treatment will fail, in this 2026 meta-analysis. Failure fuels transmission and drug resistance, so early warning matters. Searching two major databases for a quarter-century of work, they gathered thirty-four studies, most published since 2019, and pooled the accuracy of nineteen of them covering over one hundred thousand patients.

The pooled discrimination looked promising, but the ground beneath it was shaky. Results varied enormously between studies, models performed notably worse in groups including people with HIV, and only a quarter of studies had validated their model on outside data. Just one study earned a low overall risk-of-bias rating, and the analysis detected signs of publication bias. The authors conclude these tools are not ready for routine care and prioritize rigorous external validation in high-burden settings.

Catalog record

CREATORRogers Kamulegeya, Rose Nabatanzi, Derrick Semugenze, Faridah Mugala, Mercy Takuwa, Emmanuel Nasinghe, Denis Musinguzi, Sharon Namiiro
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE47615
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0355124

Browse the full library · About the Tower of Babel