TY - JOUR T1 - Highlights from the literature JF - Frontline Gastroenterology JO - Frontline Gastroenterol SP - 356 LP - 356 DO - 10.1136/flgastro-2021-101819 VL - 12 IS - 4 AU - Julia Louisa Gauci AU - Ian D Penman Y1 - 2021/07/01 UR - http://fg.bmj.com/content/12/4/356.abstract N2 - Deep learning systems allow real-time computer-aided polyp detection (CADe). Early reports suggested CADe improves polyp detection, thus potentially reducing interval cancers. Hassan et al 1 published a systematic review and meta-analysis of five randomised controlled trials comparing adenoma detection rate (ADR) and the features of detected lesions when using CADe versus white light endoscopy (WLE) alone. A total of 4354 participants were included in the analysis (2163 for CADe and 219 for WLE). The overall ADR was significantly higher for the CADe group versus controls (791/2163 (36.6%) vs 558/2191 (25.2%), RR 1.44), with similar findings for the number of adenomas per colonoscopy (1249/2163 (0.58%) vs 779/2191 (0.36%), RR 1.70), irrespective of size, location or morphology. No statistically significant difference between withdrawal times in the two groups was observed. Incorporating CADe into diagnostic colonoscopy significantly increases the detection of colorectal neoplasia, regardless of adenoma characteristics, with no negative impact on efficiency. We may expect … ER -