Singh, Dhruv

Abstract Background and study aims With the advent of deep neural networks (DNN) learning, the field of artificial intelligence (AI) is rapidly evolving. Recent randomized controlled trials (RCT) have investigated the influence of integrating AI in colonoscopy and its impact on adenoma detection rates (ADRs) and polyp detection rates (PDRs). We performed a systematic review and meta-analysis to reliably assess if the impact is statistically significant enough to warrant the adoption of AI -assisted colonoscopy (AIAC) in clinical practice. Methods We conducted a comprehensive search of multiple electronic databases and conference proceedings to identify RCTs that compared outcomes between AIAC and conventional colonoscopy (CC). The primary outcome was ADR. The secondary outcomes were PDR and total withdrawal time (WT). Results Six RCTs (comparing AIAC vs CC) with 5058 individuals undergoing average-risk screening colonoscopy were included in the meta-analysis. ADR was significantly higher with AIAC compared to CC (33.7 % versus 22.9 %; odds ratio (OR) 1.76, 95 % confidence interval (CI) 1.55–2.00; I2 = 28 %). Similarly, PDR was significantly higher with AIAC (45.6 % versus 30.6 %; OR 1.90, 95 %CI, 1.68–2.15, I2 = 0 %). The overall WT was higher for AIAC compared to CC (mean difference [MD] 0.46 (0.00–0.92) minutes, I2 = 94 %). Conclusions There is an increase in adenoma and polyp detection with the utilization of AIAC.

AbstractBackground Endoscopic retrograde cholangiopancreatography (ERCP) in patients with Roux-en-Y gastric bypass (RYGB) anatomy is challenging. Overtube-assisted enteroscopy (OAE) is usually needed to perform ERCP in these patients. There is significant variation in the reported rates of success and adverse events across published studies. We performed a systematic review and meta-analysis to reliably estimate the pooled rates of success and adverse events.Methods We performed a systematic search of multiple electronic databases through February 2020 to identify studies reporting outcomes of OAE-ERCP in post-RYGB patients. The pooled rates of enteroscopy success, technical success, and adverse events were estimated for OAE-ERCP. The pooled rates of success and adverse events were also estimated for ERCP using double-balloon enteroscopes (DBE) alone.Results 10 studies reporting a total of 398 procedures were included in the meta-analysis. The pooled rates of enteroscopy and technical success of OAE-ERCP were 75.3 % (95 % confidence interval [CI] 64.5 – 83.6) and 64.8 % (95 %CI 53.1 – 74.9) respectively. The pooled rate of adverse events was 8.0 % (95 %CI 5.2 – 12.2). The pooled rates of enteroscopy and technical success of DBE-ERCP (four studies) were 83.5 % (95 %CI 68.3 – 92.2) and 72.5 % (95 %CI 52.3 – 86.4), respectively. The pooled rate of adverse events with DBE-ERCP was 9.0 % (95 %CI 5.4 – 14.5). Substantial heterogeneity was noted.Conclusions OAE-ERCP appears to be effective and safe in post-RYGB patients. Among the currently available techniques, OAE-ERCP is the least invasive approach in this challenging group of patients. Future studies comparing the effectiveness and safety of alternative novel techniques, such as endosonography-directed transgastric ERCP, with OAE-ERCP are needed.