Meta-analysis demonstrates improved adenoma detection rate and colorectal cancer detection rate with AI-colonoscopy, highlighting its diagnostic accuracy over traditional methods.
Aim Early diagnosis of colorectal adenoma and colorectal cancer is imperative to reduce associated significant mortality and morbidity. Use of computer aided artificial intelligence (AI) tools to improve diagnostic accuracy is gaining popularity worldwide. The objective of this study is to evaluate the role of AI aided colonoscopy in improving the adenoma detection rate and colorectal cancer detection rate compared to conventional colonoscopy. Methods Randomized, controlled trials (RCTs) reporting utilization of AI-colonoscopy versus colonoscopy were retrieved from the medical databases and summated outcomes were achieved by analysis using Revman 5.4 statistical tool. Results Forty-three RCTs on procedures of AI-colonoscopy versus colonoscopy contributed into the calculation of adenoma detection rate. In the random effects model analysis, AI-colonoscopy reported higher adenoma detection rates [odds ratio 0.69 (CI 0.63-0.75), z= 8.30, p= 0.00001] compared to colonoscopy. Twenty-two RCTs on 19644 procedures reported the colorectal cancer detection rate and in the random effects model analysis, AI-colonoscopy reported higher colorectal cancer detection rates [odds ratio 0.88 (CI 0.80-0.97), z= 2.71, p= 0.0007] compared to colonoscopy. However, there was significant statistical heterogeneity among included studies [Tau2= 0.05, Chi2= 135.01, df=42, I2=69 %]. Conclusion AI-colonoscopy has shown diagnostic superiority over conventional colonoscopy in adenoma detection rate and colorectal cancer detection rate.
No takes yet. Share an insight, caveat, or question.
Shafique et al. (2025) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: