Martin C. S. Wong1,2,3,4,5, Junjie Huang1,5, Claire Chenwen Zhong1,5, Thomas Y. T. Lam6, Louis H. S. Lau7, Philip W. Y. Chiu8
1JC School of Public Health and Primary Care, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China;
2The Chinese Academy of Medical Sciences and Peking Union Medical Colleges, Beijing, China;
3School of Public Health, Peking University, Beijing, China;
4School of Public Health, Fudan University, Shanghai, China;
5Centre for Health Education and Health Promotion, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China;
6School of Nursing, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China;
7Department of Medicine and Therapeutics, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China;
8Department of Surgery, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China
Background: The study provided the cost-effectiveness of using artificial intelligence (AI) colonoscopy in different population-based colorectal cancer (CRC) screening strategies. The study aimed to provide insights into the potential benefits and economic implications of incorporating AI colonoscopy into CRC screening programs.
Methods: To evaluate the cost-effectiveness of different population-based CRC screening strategies, including the use of AI-aided colonoscopy, by comparing incremental cost-effectiveness ratios (ICERs) and various outcome measures such as loss of cancer-related life-years, prevention of CRC cases, life-years saved, and total cost per life-year saved. Data from international literature and the government gazette were accessed to calculate relevant cost and performance estimates.
Results: The ICER of fecal immunochemical test (FIT) + colonoscopy, FIT + AI colonoscopy, colonoscopy, and AI colonoscopy was US$138,539, US$122,539, US$203,929, and US$180,444, respectively. When compared with FIT + colonoscopy, use of FIT + AI colonoscopy could lead to significantly smaller total loss of cancer-related life-years (5,355 vs. 5,327), a higher number and proportion of CRC cases prevented (120 vs. 132, 3.7% vs. 4.1%), more life-years saved (280 vs. 308), and lower total cost per life-year saved (US$944,008 vs. US$854,367). FIT + AI colonoscopy had the lowest ICER (US$122,539) and dominated across all other strategies (−US$36,462 vs. FIT + colonoscopy). When colonoscopy is adopted as a primary screening test, AI colonoscopy dominated conventional colonoscopy (ICER −39,040).
Conclusions: These findings show that FIT followed by AI colonoscopy is the most cost-effective strategy in population-based CRC screening programmes.
Keywords: Colorectal cancer (CRC); screening; artificial intelligence (AI); cost-effectiveness; life-years save
