IndiaHealthcare and life sciences2025–2026Delhi State TB Elimination Programme
AI-read chest X-ray screening in urban slum clusters (Qure.ai)
Delhi screened 168,568 slum residents with AI-read X-rays in nine months and confirmed TB in 877
Problem
Over 40% of bacteriologically confirmed TB cases in India's national prevalence survey had no common symptoms, so symptom-based checks miss them. Delhi wanted to find these cases in crowded slum clusters.
Approach
From July 2025 to March 2026, health teams ran 3,566 community camps in 349 slum clusters across six districts, in anganwadi centres, schools, community halls and private facilities. Qure.ai software read digital chest X-rays and flagged suspicious images but did not diagnose. Flagged people gave sputum samples for molecular testing, and community health workers helped them complete it.
Results
Takeaway
About 192 people were screened for each confirmed case. The reported figures come from a study by the programme's own health authorities, and no cost figure was given.
Categories
- Size
- Large enterprise
- Industry
- Healthcare and life sciences
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer vision
- Adoption
- Vendor solution
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
The paper reports a study in the Indian Journal of Tuberculosis, dated 23 August 2026, by Delhi health authorities and the Union (India). It gives 3,566 camps, 168,568 people screened, 18,377 flagged, 16,866 followed up and 877 confirmed. It also gives 520 confirmed cases per 100,000 screened and 192 screened per case, and says the AI did not make the final diagnosis.
A partner organisation said the Delhi project used 21 handheld X-ray devices across six districts and, since mid-2025, screened over 160,000 people and found more than 800 with TB. It put Delhi's TB prevalence at 747 per 100,000.
Full details are in the original sources.
