Old Dogs Can Learn New Tricks: Artificial Intelligence Improves Adenoma Detection Rates in Screening Colonoscopies in Experienced Endoscopists

BACKGROUND: A high adenoma detection rate in screening colonoscopy is associated with decreased rates of post-colonoscopy colorectal cancer. The use of artificial intelligence has emerged to assist with the identification of adenomas. OBJECTIVE: Evaluating if adopting artificial intelligence-powered computer-aided detection systems in colonoscopy will increase the adenoma detection rate, with the greatest increase seen among low-volume and junior endoscopists. DESIGN: A retrospective review compared the adenoma detection rate before and after computer-aided detection in a single-center high-volume endoscopy practice, including both colorectal surgeons and gastroenterologists with a wide variety of experience. SETTING: Single tertiary referral institution between April 2023 and August 2023, and April 2024 and August 2024. PATIENTS: Endoscopists board-certified in colorectal surgery or gastroenterology. INTERVENTION: Incorporation of computer-aided detection software to colonoscopy equipment. MAIN OUTCOME MEASURE: Adenoma detection rate. RESULTS: Data from 9 colorectal surgeons and 15 gastroenterologists were included. A total of 2,327 colonoscopies were performed over the 10 months - 1,285 pre-computer-aided detection and 1,042 post-computer-aided detection. The overall mean adenoma detection rate significantly increased from 53.9% to 61.3% ( p = 0.02). Colorectal surgeons had a statistically significant increase in adenoma detection rate from 49% to 62% ( p = 0.02), but gastroenterologists did not (56.9% to 60.8%, p = 0.15). Of 12 senior and 12 junior endoscopists, the seniors had a statistically significant increase ( p = 0.02) from 51.7% to 59.6%, while juniors did not (56.2% to 62.9%, p = 0.12). From 12 high-volume and 12 low-volume endoscopists, the high-volume group had a statistically significant increase (51.3% to 59.4%, p = 0.01), but the low-volume group did not (56.5% to 63.1%, p = 0.13). LIMITATIONS: Single institution, limited time of study to show if increased adenoma detection rate will impact overall colorectal cancer incidence. CONCLUSIONS: Computer-aided detection in colonoscopy correlated with increased adenoma detection rate for experienced endoscopists. See Video Abstract .