What happened
India's national TB program screens people with chest X-rays, and radiologists to read them are scarce. At the request of the Department of Health Research, researchers at the Indian Institute of Public Health Gandhinagar carried out a rapid health technology assessment. They used 2023 records of 93,486 people screened with DeepTek's Genki at six centers in Tamil Nadu and 6,281 screened with qXR in Maharashtra. They compared them with 2,731 people whose X-rays radiologists had read at the same facilities before the AI tools arrived. Accuracy came from published studies, and costs from the facilities and the makers' prices. A radiologist's reading cost INR 100 per case, against INR 30 with qXR and INR 22 with Genki. The incremental cost-effectiveness ratio was INR -9,865 per interpreted case for qXR, which saved money. It was INR 11,287 for Genki, which was cost-effective. Both values fell below India's GDP per head. The authors note that the analysis took the provider's view and lacked matched comparisons.
Sources
-
Peer-reviewed study, by authors with no tie to the system.
Raval D, Parmar D, Saha S, et al. Cost-effectiveness analysis of AI-assisted chest X-ray interpretation tools for TB screening: a rapid HTA. Frontiers in Digital Health 2025, 7:1629127. doi:10.3389/fdgth.2025.1629127. Conducted at the request of the HTAIn Secretariat, Department of Health Research, Ministry of Health and Family Welfare, which funded it. The authors declare no commercial or financial conflicts.
The incremental cost-effectiveness ratio (ICER) for qXR was Indian rupee (INR) -9,865 [-120 United States dollars (USD)] per interpreted case, which showed that the method was cost-saving, while for Genki, the corresponding value was INR 11,287 (137 USD), which showed that the method was cost-effective.
-
Assessment report, by authors with no tie to the system.
Health Technology Assessment in India (HTAIn), Department of Health Research, Ministry of Health and Family Welfare; assessment by its resource hub at the Indian Institute of Public Health Gandhinagar (2024). Health Technology Assessment of AI-Assisted CXR for Interpretation for Tuberculosis: A Rapid Health Technology Assessment (Policy Brief, study 77), Executive Summary; Results; Conclusion (pp. 1-2).
The findings of the study indicated that the Incremental Cost-Effectiveness Ratio (ICER) for qXR was found to be -9,864.77 INR per case screened/interpreted
Details
AI system
- Workflow
-
The tools read digital chest X-rays at public health facilities screening people aged 15 and older for TB. Genki ran offline and online on a lifetime license, and qXR ran online at a price per scan.
Follow-up
- Conditions for replication
-
The price per case stays low, since the authors found that qXR saved money only up to INR 410 and that Genki stayed cost-effective only up to INR 35. Accuracy in local use matches the pooled sensitivity of about 90% from published studies.
Entry details
- Sector
-
Healthcare (tuberculosis screening).
- Purpose
-
Qure.ai and DeepTek built qXR and Genki to read chest X-rays and flag people who may have tuberculosis.
30 more questions not yet checked
model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.
Cite this record
Peter H. Vartanian. (2026). qXR and Genki cut the cost of reading TB screening X-rays in India (AIBD-0932). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-0932.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)