Cost-effectiveness of chest radiography using artificial intelligence for lung cancer screening in South Korea

Abstract

Artificial intelligence (AI) shows promise in improving the accuracy and efficiency of lung cancer screening, but its economic value remains uncertain. We developed a decision-analytic model combining a decision tree and Markov model to evaluate five screening strategies in South Korea: no screening, chest X-ray (CXR), AI-assisted CXR, low-dose computed tomography (LDCT), and AI-assisted LDCT. We simulated hypothetical cohorts of 10,000 individuals, stratified by age group and smoking status to reflect the Korean population distribution, and projected their lifetime costs and quality-adjusted life years (QALYs). Analyses applied a 4.5% discount rate and a willingness-to-pay (WTP) threshold of $32,409.9 per QALY. AI-assisted CXR produced incremental cost-effectiveness ratio (ICER) of $8679-$10,030 per QALY, demonstrating cost-effectiveness across all age groups. CXR alone was less favorable, and LDCT-based strategies exceeded the willingness-to-pay (WTP) threshold. These findings suggest AI-assisted CXR offers a scalable, economically viable strategy for lung cancer screening, supporting its integration into national programs.