Novel Artificial Intelligence Systems in Detecting Adenomas in Colonoscopy: A Systemic Review and Network Meta-Analysis
Authors:
- Sunny KumarSKSunny Kumar
- Mahveer MaheshwariMMMahveer Maheshwari
- Shahnoor AleemSAShahnoor Aleem
- Zoha BatoolZBZoha Batool
- Nawal AlsubaieNANawal Alsubaie
- Saifullah SyedSSSaifullah Syed
- Nida Fatima DaterdiwalaNDNida Fatima Daterdiwala
- Hina Fatima MemonHMHina Fatima Memon
- Jaweria AzeemJAJaweria Azeem
- Sajida Moiz Hussain QamariSQSajida Moiz Hussain Qamari
- Mohammad JawwadMJMohammad Jawwad
Open Access
- 20 August 2025
- journal article
- endoscopy
- Published by Wolters Kluwer Health in Clinical and Translational Gastroenterology
- Vol. 16 (10) , e00904
Abstract
INTRODUCTION: Artificial intelligence (AI) has the potential to improve adenoma detection rates (ADRs) during colonoscopy, but the efficacy of various AI-assisted systems remains unclear. To evaluate and compare the effectiveness of different AI-assisted systems for detecting colorectal neoplasia during colonoscopy. METHODS: A systematic literature search of PubMed, Scopus, and Google Scholar databases was conducted up to March 4, 2025, to identify randomized controlled trials comparing AI-assisted colonoscopy with conventional colonoscopy. The analysis included AI systems such as GI Genius (Medtronic, Dublin, Ireland), CAD EYE (Fujifilm, Tokyo, Japan), ENDOANGEL, EndoScreener, and EndoAID. The primary outcome was ADR, analyzed using random-effects models to calculate pooled odds ratios (OR) and 95% confidence intervals (CI). Surface under the cumulative ranking curve (SUCRA) rankings and subgroup analyses were also performed. RESULTS: Seventeen randomized controlled trials with 10,539 participants were included. ENDOANGEL showed the highest efficacy (OR 1.84, 95% CI 1.50–2.30; SUCRA 0.9), followed by EndoAID (OR 1.64, 95% CI 1.20–2.26; SUCRA 0.7). CAD EYE and GI Genius were similarly ranked (OR 1.46 and 1.45, respectively). EndoScreener was ranked just above the control group (OR 1.37, 95% CI 1.20–1.56; SUCRA 0.4). DISCUSSION: AI-assisted colonoscopy systems showed improved ADR detection rates compared with traditional colonoscopy. These results suggest that artificial intelligence may help enhance detection during colonoscopy procedures; however, additional large-scale studies are needed to confirm these findings.Keywords
This publication has 29 references indexed in Scilit:
- Colorectal cancer: A health and economic problemBest Practice & Research Clinical Gastroenterology, 2023
- Usefulness of a novel computer-aided detection system for colorectal neoplasia: a randomized controlled trialGastrointestinal Endoscopy, 2022
- Computer-aided detection, mucosal exposure device, their combination, and standard colonoscopy for adenoma detection: a randomized controlled trialGastrointestinal Endoscopy, 2022
- Deep Learning Computer-aided Polyp Detection Reduces Adenoma Miss Rate: A United States Multi-center Randomized Tandem Colonoscopy Study (CADeT-CS Trial)Clinical Gastroenterology and Hepatology, 2022
- AGA White Paper: Challenges and Gaps in Innovation for the Performance of Colonoscopy for Screening and Surveillance of Colorectal CancerClinical Gastroenterology and Hepatology, 2022
- Effect of a deep-learning computer-aided detection system on adenoma detection during colonoscopy (CADe-DB trial): a double-blind randomised studyThe Lancet Gastroenterology & Hepatology, 2020
- Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): a randomised controlled studyThe Lancet Gastroenterology & Hepatology, 2020
- Magnitude, Risk Factors, and Factors Associated With Adenoma Miss Rate of Tandem Colonoscopy: A Systematic Review and Meta-analysisGastroenterology, 2019
- Accuracy of Capsule Colonoscopy in Detecting Colorectal Polyps in a Screening PopulationGastroenterology, 2015
- Guidelines for Colonoscopy Surveillance After Polypectomy: A Consensus Update by the US Multi-Society Task Force on Colorectal Cancer and the American Cancer SocietyGastroenterology, 2006