The abstract is read at the publisher; the summary is JClub's.
AI-guided geographical targeting with MATCH-AI increased camp positivity yield for bacteriologically confirmed tuberculosis in Pakistan in a validated per-protocol analysis (32% higher; 1·32, 1·12–1·54; p<0·0001).
- Why it matters: Conventional site selection for community active case-finding can yield low screening returns, limiting detection efficiency in programmatic tuberculosis elimination efforts in Pakistan.
- What they did: In a pragmatic stepped wedge cluster-randomised trial across all four provinces, 30 mobile x-ray van teams in 68 districts transitioned from conventional selection to MATCH-AI targeting; 3936 camps were analyzed by intention-to-treat and per-protocol.
- The result: From Aug 1, 2023 to Sept 28, 2024, intention-to-treat showed a non-significant 7% increase (adjusted risk ratio 1·07, 95% CI 0·94–1·22; p=0·27), while per-protocol showed 32% higher yield, suggesting improved efficiency.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.