The abstract is read at the publisher; the summary is JClub's.
Geospatial AI targeting in Pune’s TB Units found 10 bacteriologically confirmed pulmonary TB cases after screening 66,095 people, versus 9 after 177,322 in standard ACF.
- Why it matters: Active case finding in India screens many people to detect few TB cases, so improving yield and efficiency while maintaining frontline acceptability is a key gap.
- What they did: In a prospective quasi-experimental evaluation across four TB Units, AI-NETRA guided two-week neighbourhood sweeps (April–May 2026) using routine notification data and field microplans, compared with the routine campaign (Dec 2024–Jan 2025).
- The result: AI-guided sweeps increased pulmonary confirmed yield (rate ratio 2.98, 95% CI 1.09 to 8.29), reduced NNS (6,610 vs 19,702) and lowered cost per case by 66%, while all-forms detection did not differ (15 vs 32; RR 1.26, 95% CI 0.63 to 2.39).
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.