Underwater versus conventional EMR of large nonpedunculated colorectal lesions: a multicenter randomized controlled trial.

BACKGROUND AND AIMS: Underwater EMR (UEMR) is an alternative procedure to conventional EMR (CEMR) to treat large, nonpedunculated colorectal lesions (LNPCLs). In this multicenter, randomized controlled clinical trial, we aimed to compare the efficacy and safety of UEMR versus CEMR on LNPCLs. METHODS: We conducted a multicenter, randomized controlled clinical trial from February 2018 to February 2020 in 11 hospitals in Spain. A total of 298 patients (311 lesions) were randomized to the UEMR (n = 149) and CEMR (n = 162) groups. The main outcome was the lesion recurrence rate in at least 1 follow-up colonoscopy. Secondary outcomes included technical aspects, en bloc resection rate, R0 resection rates, and adverse events, among others. RESULTS: There were no differences in the overall recurrence rate (9.5% UEMR vs 11.7% CEMR; absolute risk difference, -2.2%; 95% CI, -9.4 to 4.9). However, considering polyp sizes between 20 and 30 mm, the recurrence rate was lower for UEMR (3.4% UEMR vs 13.1% CEMR; absolute risk difference, -9.7%; 95% CI, -19.4 to 0). The R0 resection showed the same tendency, with significant differences favoring UEMR only for polyps between 20 and 30 mm. Overall, UEMR was faster and easier to perform than CEMR. Importantly, the techniques were equally safe. CONCLUSIONS: UEMR is a valid alternative to CEMR for treating LNPCLs and could be considered the first option of treatment for lesions between 20 and 30 mm due to its higher en bloc and R0 resection rates. (Clinical trial registration number: NCT03567746.).

Artificial intelligence in gastrointestinal endoscopy — Evolution to a new era

Artificial intelligence (AI) systems based on machine learning have evolved in the last few years with increasing applicability in gastrointestinal endoscopy. Thanks to AI, animage (input) can be transformed into a clinical decision(output). Although AI systems have been studied mainly toimprove detection (CADe) and characterization of colorectalpolyps (CADx), other indications are being currently investigated, including detection of blind spots, scope guidance,and delineation/measurement of lesions.The objective of this review is to summarize the current evidence on the applicability of AI systems in gastrointestinalendoscopy, to highlight the strengths and limitations of thetechnology involved, and to review the relevant regulatoryand ethical aspects for general implementation in gastrointestinal endoscopy. (AU)

Artificial intelligence in gastrointestinal endoscopy - Evolution to a new era.

Artificial intelligence (AI) systems based on machine learning have evolved in the last few years with an increasing applicability in gastrointestinal endoscopy. Thanks to AI, an image (input) can be transformed into a clinical decision (output). Although AI systems have been initially studied to improve detection (CADe) and characterization of colorectal lesions (CADx), other indications are being currently investigated as detection of blind spots, scope guidance, or delineation/measurement of lesions. The objective of these review is to summarize the current evidence on applicability of AI systems in gastrointestinal endoscopy, highlight strengths and limitations of the technology and review regulatory and ethical aspects for its general implementation in gastrointestinal endoscopy.

Prevalence of adenomatous polyposis in a fecal immunochemical test-based colorectal cancer screening program and risk of advanced neoplasia during follow-up.

BACKGROUND : Current guidelines recommend genetic counseling and intensive colonoscopy surveillance for patients with ≥ 10 colorectal adenomas based on scarce data. We investigated the prevalence of this condition in a fecal immunochemical test (FIT)-based colorectal (CRC) screening program, and the incidence of metachronous lesions during follow-up. METHODS: We retrospectively included all FIT-positive participants with ≥ 10 adenomas at index colonoscopy between 2010 and 2018. Surveillance colonoscopies were collected until 2019. Patients with inherited syndromes, serrated polyposis syndrome, total colectomy, or lacking surveillance data were excluded. The cumulative incidence of CRC and advanced neoplasia were analyzed by Kaplan-Meier analysis. Risk factors for metachronous advanced neoplasia were investigated by multivariable logistic regression analysis. RESULTS: 215 of 9582 participants (2.2 %) had ≥ 10 adenomas. Germline genetic testing was performed in 92 % of patients with ≥ 20 adenomas, identifying two inherited syndromes (3.3 %). The 3-year cumulative incidence of CRC and advanced neoplasia were 1 % and 16 %, respectively. In 39 patients (24.2 %), no polyps were found on first surveillance colonoscopy. The presence of an advanced adenoma was independently associated with a higher risk of advanced neoplasia at first surveillance colonoscopy (odds ratio 3.91, 95 %CI 1.12-13.62; P = 0.03). Beyond the first surveillance colonoscopy, the risk of metachronous advanced neoplasia was lower. CONCLUSIONS: The prevalence of ≥ 10 adenomas in a FIT-based CRC screening program was 2.2 %; a small proportion of inherited syndromes were detected, even amongst those with ≥ 20 adenomas. A low rate of post-colonoscopy CRC was observed and the risk of advanced neoplasia beyond the first surveillance colonoscopy tended to progressively decrease throughout successive follow-ups.