Hong Xu1, Raymond S Y Tang2, Thomas Y T Lam3, Guijun Zhao4, James Y W Lau5, Yunpeng Liu6, Qi Wu7, Long Rong8, Weiran Xu1, Xue Li4, Sunny H Wong9, Shuntian Cai6, Jing Wang7, Guanyi Liu8, Tantan Ma1, Xiong Liang4, Joyce W Y Mak2, Hongzhi Xu6, Peng Yuan7, Tingting Cao1, Fudong Li1, Zhenshi Ye6, Zhang Shutian10, Joseph J Y Sung11. 1. Department of Gastroenterology and Endoscopy Center, First Hospital of Jilin University, Jilin, China. 2. Department of Medicine and Therapeutics, Chinese University of Hong Kong, Hong Kong SAR, China; Institute of Digestive Disease, Chinese University of Hong Kong, Hong Kong SAR, China. 3. Institute of Digestive Disease, Chinese University of Hong Kong, Hong Kong SAR, China; JC School of Public Health and Primary Care, Chinese University of Hong Kong, Hong Kong SAR, China; Stanley Ho Big Data Decision Analytics Research Centre, Chinese University of Hong Kong, Hong Kong SAR, China. 4. Department of Endoscopy Center, Inner Mongolia Key Laboratory of Endoscopic Digestive Diseases, Inner Mongolia People's Hospital, Hohhot, China. 5. Institute of Digestive Disease, Chinese University of Hong Kong, Hong Kong SAR, China; Department of Surgery, Chinese University of Hong Kong, Hong Kong SAR, China. 6. Department of Gastroenterology, Zhongshan Hospital Affiliated to Xiamen University, Xiamen, China. 7. Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Endoscopy Center, Peking University Cancer Hospital and Institute, Beijing, China. 8. Endoscopy Center, Peking University First Hospital, Beijing, China. 9. Department of Medicine and Therapeutics, Chinese University of Hong Kong, Hong Kong SAR, China; Institute of Digestive Disease, Chinese University of Hong Kong, Hong Kong SAR, China; Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore. 10. Department of Gastroenterology and Hepatology, Beijing Friendship Hospital, Capital Medical University, National Clinical Research Center for Digestive Diseases, Beijing, China. 11. Department of Medicine and Therapeutics, Chinese University of Hong Kong, Hong Kong SAR, China; Institute of Digestive Disease, Chinese University of Hong Kong, Hong Kong SAR, China; Stanley Ho Big Data Decision Analytics Research Centre, Chinese University of Hong Kong, Hong Kong SAR, China; Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore. Electronic address: josephsung@ntu.edu.sg.
Abstract
BACKGROUND AND AIMS: Artificial intelligence (AI)-assisted colonoscopy improves polyp detection and characterization in colonoscopy. However, data from large-scale multicenter randomized controlled trials (RCT) in an asymptomatic population are lacking. METHODS: This multicenter RCT aimed to compare AI-assisted colonoscopy with conventional colonoscopy for adenoma detection in an asymptomatic population. Asymptomatic subjects 45-75 years of age undergoing colorectal cancer screening by direct colonoscopy or fecal immunochemical test were recruited in 6 referral centers in Hong Kong, Jilin, Inner Mongolia, Xiamen, and Beijing. In the AI-assisted colonoscopy, an AI polyp detection system (Eagle-Eye) with real-time notification on the same monitor of the endoscopy system was used. The primary outcome was overall adenoma detection rate (ADR). Secondary outcomes were mean number of adenomas per colonoscopy, ADR according to endoscopist's experience, and colonoscopy withdrawal time. This study received Institutional Review Board approval (CRE-2019.393). RESULTS: From November 2019 to August 2021, 3059 subjects were randomized to AI-assisted colonoscopy (n = 1519) and conventional colonoscopy (n = 1540). Baseline characteristics and bowel preparation quality between the 2 groups were similar. The overall ADR (39.9% vs 32.4%; P < .001), advanced ADR (6.6% vs 4.9%; P = .041), ADR of expert (42.3% vs 32.8%; P < .001) and nonexpert endoscopists (37.5% vs 32.1%; P = .023), and adenomas per colonoscopy (0.59 ± 0.97 vs 0.45 ± 0.81; P < .001) were all significantly higher in the AI-assisted colonoscopy. The median withdrawal time (8.3 minutes vs 7.8 minutes; P = .004) was slightly longer in the AI-assisted colonoscopy group. CONCLUSIONS: In this multicenter RCT in asymptomatic patients, AI-assisted colonoscopy improved overall ADR, advanced ADR, and ADR of both expert and nonexpert attending endoscopists. (ClinicalTrials.gov, Number: NCT04422548).
BACKGROUND AND AIMS: Artificial intelligence (AI)-assisted colonoscopy improves polyp detection and characterization in colonoscopy. However, data from large-scale multicenter randomized controlled trials (RCT) in an asymptomatic population are lacking. METHODS: This multicenter RCT aimed to compare AI-assisted colonoscopy with conventional colonoscopy for adenoma detection in an asymptomatic population. Asymptomatic subjects 45-75 years of age undergoing colorectal cancer screening by direct colonoscopy or fecal immunochemical test were recruited in 6 referral centers in Hong Kong, Jilin, Inner Mongolia, Xiamen, and Beijing. In the AI-assisted colonoscopy, an AI polyp detection system (Eagle-Eye) with real-time notification on the same monitor of the endoscopy system was used. The primary outcome was overall adenoma detection rate (ADR). Secondary outcomes were mean number of adenomas per colonoscopy, ADR according to endoscopist's experience, and colonoscopy withdrawal time. This study received Institutional Review Board approval (CRE-2019.393). RESULTS: From November 2019 to August 2021, 3059 subjects were randomized to AI-assisted colonoscopy (n = 1519) and conventional colonoscopy (n = 1540). Baseline characteristics and bowel preparation quality between the 2 groups were similar. The overall ADR (39.9% vs 32.4%; P < .001), advanced ADR (6.6% vs 4.9%; P = .041), ADR of expert (42.3% vs 32.8%; P < .001) and nonexpert endoscopists (37.5% vs 32.1%; P = .023), and adenomas per colonoscopy (0.59 ± 0.97 vs 0.45 ± 0.81; P < .001) were all significantly higher in the AI-assisted colonoscopy. The median withdrawal time (8.3 minutes vs 7.8 minutes; P = .004) was slightly longer in the AI-assisted colonoscopy group. CONCLUSIONS: In this multicenter RCT in asymptomatic patients, AI-assisted colonoscopy improved overall ADR, advanced ADR, and ADR of both expert and nonexpert attending endoscopists. (ClinicalTrials.gov, Number: NCT04422548).