Beyond the algorithm: what makes artificial intelligence-assisted colonoscopy effective in routine practice?

Effectiveness of a novel artificial intelligence-assisted colonoscopy system for adenoma detection: a prospective, propensity score-matched, non-randomized controlled study in Korea ENAD-assisted colonoscopy significantly improved the ADR, APC, and SSLDR in real-world clinical practice, particularly for smaller and nonpolypoid adenomas.Prospective, propensity score-matched, non-randomized controlled study Standard Colonoscopy VS ENAD-Assisted Colonoscopy Compared with the SC group, the ENAD group had a significantly higher adenoma detection rate (ADR), sessile serrated lesion detection rate (SSLDR), and mean number of adenomas per colonoscopy (APC) 2,105 Patients who underwent colonoscopies between May 2022 and October 2022 at Seoul National University Hospital, Healthcare System Gangnam 254 Patients excluded due to disease or colorectal cancer Previous colon resection Failed insertion Refused to participate in the study SC group: 972 patients, ENAD group: 879 patients Age and sex propensity score matching 1,851 Enrolled SC group: 879 patients ENAD group: 879 patients 50 45 40 35 30 25 20 15 10 5 0 % Adenoma Advanced adenoma 38.8 45.