Computer-aided quality assurance versus standard colonoscopy: A systematic review and meta-analysis of randomized-controlled trials

BACKGROUND AND STUDY AIM: Computer-aided quality assurance (CAQ) can provide feedback to improve mucosal inspection during standard colonoscopy(SC). This systematic review and meta-analysis of randomized controlled trials (RCTs) evaluated the efficacy of CAQ compared to SC in enhancing colonoscopy quality indicators.

PATIENTS AND METHODS: Adhering to PRISMA guidelines, we searched MEDLINE, Embase, and CENTRAL for RCTs comparing CAQ and SC. The primary outcome was adenoma detection rate (ADR). Secondary outcomes included advanced ADR (AADR), adenocarcinoma DR (ACDR), adenomas per colonoscopy (APC), and withdrawal time. Pooled risk ratios (RRs) and weighted mean differences (WMDs) were calculated using random-effects models.

RESULTS: Six RCTs involving 5,687 colonoscopies (CAQ: 2,895, SC: 2,792) were included. CAQ compared to SC increased ADR by 43 % (RR [CI 95%]: 1.43, [1.17-1.73], P<0.001, I 2 =73.5%), heterogeneity decreased substantially after omitting one study (1.52 [1.32-1.75], P<0.001, I 2 =11.9%), AADR by 54% (1.54 [1.26-1.87], P<0.001, I 2 =0.0%), ACDR by 30% (1.30 [1.00-1.68], P=0.047, I 2 =0.0%), APC by 0.14 adenomas (WMD [CI 95%]: 0.14 [0.08-0.20], P<0.001, I 2 =53.2%), adenomas ≥10mm by 0.03 adenomas (0.03 [0.02-0.05], P<0.001, I 2 =45.1%), and withdrawal time increased by 0.63 minutes (0.63 [0.04-1.24], P=0.037, I 2 =96.1%).

CONCLUSIONS: CAQ significantly improved ADR and the detection of clinically significant lesions.While findings for AADR and ACDR should be interpreted with caution due to low event rates, the improvements in adenomas ≥10mm and APC suggest that CAQ may lower the risk of postcolonoscopy colorectal cancer, a hypothesis that warrants evaluation in future long-term analyses of patient outcomes.