ECONOMIC EVALUATION OF AN ELECTRONIC HEALTH RECORD-BASED LUNG CANCER SCREENING PROGRAM AT GRASS-ROOT LEVEL...
Author(s)
Xiaolong Hu1, Donglan Zhang, PhD2, Jiayan Huang, PhD1.
1School of Public Health, Fudan University, Shanghai, China, 2New York University, New York, NY, USA.
1School of Public Health, Fudan University, Shanghai, China, 2New York University, New York, NY, USA.
OBJECTIVES: This study evaluates the economic and health outcomes of a digital intelligence-based organized lung cancer screening strategy compared with conventional opportunistic screening in China.
METHODS: A Markov state-transition model was developed to simulate lung cancer progression in a hypothetical cohort of 100,000 residents in Yuhuan City, China, over a 40-year time horizon. The primary outcomes were quality-adjusted life years (QALYs) and the number of early-stage lung cancer cases detected. Costs and outcomes were estimated for three strategies: opportunistic screening (reference), community-based organized screening, and digital intelligence-based organized screening.
RESULTS: Digital intelligence-based organized screening was the dominant strategy. Compared with opportunistic screening, it detected an additional 1,268 early-stage cases and gained 259 QALYs, while reducing screening and diagnostic costs by 0.76 million USD. In contrast, community-based organized screening was associated with lower effectiveness than the reference strategy. Sensitivity analyses showed that the results were robust, with most iterations falling below the willingness-to-pay threshold.
CONCLUSIONS: Integrating digital intelligence into population-based screening programs may improve risk stratification and health outcomes while reducing costs. These findings provide evidence to support the use of AI-enabled EHR systems in lung cancer screening policy.
METHODS: A Markov state-transition model was developed to simulate lung cancer progression in a hypothetical cohort of 100,000 residents in Yuhuan City, China, over a 40-year time horizon. The primary outcomes were quality-adjusted life years (QALYs) and the number of early-stage lung cancer cases detected. Costs and outcomes were estimated for three strategies: opportunistic screening (reference), community-based organized screening, and digital intelligence-based organized screening.
RESULTS: Digital intelligence-based organized screening was the dominant strategy. Compared with opportunistic screening, it detected an additional 1,268 early-stage cases and gained 259 QALYs, while reducing screening and diagnostic costs by 0.76 million USD. In contrast, community-based organized screening was associated with lower effectiveness than the reference strategy. Sensitivity analyses showed that the results were robust, with most iterations falling below the willingness-to-pay threshold.
CONCLUSIONS: Integrating digital intelligence into population-based screening programs may improve risk stratification and health outcomes while reducing costs. These findings provide evidence to support the use of AI-enabled EHR systems in lung cancer screening policy.
Conference/Value in Health Info
2026-09, ISPOR Asia Pacific 2026, Bangkok, Thailand
Value in Health, Volume 55, Issue S1
Code
EE91
Topic
Economic Evaluation
Disease
SDC: Oncology, SDC: Respiratory-Related Disorders (Allergy, Asthma, Smoking, Other Respiratory)