S0338 Is Artificial Intelligence for Colonoscopy Ready for Prime-Time: A Systematic Review and Meta-Analysis of Randomized Controlled Trials

Abstract

INTRODUCTION: Colonoscopy is the best tool for to screen for colorectal cancer. Adenoma detection rate (ADR) is the main quality control indicator for colonoscopy. An improvement in ADR translates into a reduction in the number of index and interval colorectal cancers. Computer-aided polyp detection (CADe) can improve ADR but the impact of real-time CADe on colonoscopy metrics has not been rigorously studied. We aim to conduct a systematic review with meta-analysis of randomized controlled trials (RCTs) to evaluate the efficacy of CADe to detect colorectal neoplasia. METHODS: Electronic databases (Pubmed Central, OVID Medline, Embase, EBM Reviews Cochrane Central Register of Controlled Trials) were interrogated from inception until May 2020 for RCTs that compared real-time CADe with standard colonoscopy (E). Data was reviewed separately by two authors. Adult patients undergoing diagnostic and screening colonoscopies were included. Primary outcomes were polyp detection rate (PDR) and ADR. Secondary outcomes were total number of polyps detected, pooled ADR and withdrawal time. A random effects model was used to estimate mean differences (MD), odds ratios (OR) and rate ratios (RR) with 95% confidence intervals (95% CI). Heterogeneity was assessed with I2 statistic, with >50% considered substantial. RESULTS: The search yielded 923 results. 6 studies met inclusion criteria. Controls included a sham system and colonoscopies without AI. The total number of subjects included in all studies were 5214. The mean age of patients was 49.49 years, and 47.55 % of the subjects were female. The mean BPPS in the CADe group was 6.7 (95% CI 6.61,6.8), similar to that in the E group. The pooled ADR for colonoscopy with CAD was 33%, and the pooled ADR for colonoscopy alone was 22.8%. Both, ADR and PDR were higher with CADe, OR 1.54 (95% CI 1.23–1.94) and OR 1.49 (95% CI 1.24–1.80), I2 = 0 for both. Number of polyps detected was also higher with CADe, OR 2.42 (95% CI 2.12–2.76), I2 = 0. Withdrawal time was significantly longer (by less than a minute) in the CADe group, MD of 0.74 (95% CI). CONCLUSION: Automatic polyp detection systems resulted in improved polyp and adenoma detection rates, but with increased withdrawal times, compared to standard colonoscopy. CADe use was associated with a significantly higher adenoma detection rate (ADR; 34% vs. 23%). CADe and standard colonoscopies had comparable detection rates of polyps 5–10 mm in size, but CADe had higher ADRs for diminutive polyps, and for polyps greater than 10 mm.Table 1.: Secondary Outcomes.Figure 1.: Adenoma Detection Rate: Higher in Computer-Aided Diagnosis group with an Odds Ratio of 1.54 (95% CI 1.23–1.94), I-squared = 0.00.Figure 2.: Polyp Detection Rate: Higher in Computer-Aided Diagnosis group with an Odds Ratio of 1.49 (95% CI 1.24–1.80), I-squared = 0.00.