Cost-effectiveness analysis of AI-assisted chest X-ray Interpretation tools for TB screening: a rapid HTA in India.

Devang Raval¹Dhaval Parmar^1*Somen Saha¹Raju Sarkar¹Medha Wadhwa¹Apurvakumar Pandya¹HARSH SHAH¹Kavitha Rajsekar²

• ¹Indian Institute of Public Health Gandhinagar (IIPHG), Gandhinagar, India
• ²Department of Health Research, New Delhi, India

Background: Early diagnosis remains one of the major barriers to treating and managing tuberculosis. Artificial Intelligence (AI) has gained significant importance and has been employed in the context of tuberculosis screening as well. This study assessed whether newer AI-assisted technologies provide cost-effective benefits for pulmonary tuberculosis (PTB) diagnosis in resource-constrained settings. Methods: This retrospective study analyzed secondary data from patients who underwent tuberculosis screening using chest X-rays interpreted by AI-assisted software (qXR and Genki) in 2023. The pooled diagnostic accuracy was calculated using the secondary literature and cost-effectiveness was assessed by comparing the newer technology with conventional mode, i.e., manual interpretation by radiologists using digital X-ray. The Cost-effectiveness analysis was undertaken using the HTAIn guidelines. Incremental cost per additional case interpreted was considered as an outcome. Findings: An incremental cost-effectiveness ratio (ICER) for qXR was Indian Rupee (INR) -9,865 (-120 United States Dollar (USD)) per case interpreted which showed that intervention is cost saving, while for Genki, the corresponding value was INR 11,287 (137 USD) which showed that intervention is cost-effective. Both ICER values were below India's per capita GDP for 2022. The threshold analysis showed that healthcare systems could invest a maximum amount of INR 35 (USD 0.43) for Genki and INR 410 (USD 5) for qXR to interpret one presumptive TB case. Interpretation: AI-assisted tools qXR and Genki improve TB diagnosis with high sensitivity, specificity, and cost-effectiveness, offering a valuable alternative to traditional radiologist interpretation. Particularly beneficial in resource-limited settings like India, these technologies can enhance TB detection and patient outcomes in high-volume public healthcare institutions. Funding: The Department of Health and Research, Ministry of Health and Family Welfare, Government of India.