P0530 - Comparison of Effectiveness of Artificial Intelligence (AI)-Aided Colonoscopy With Conventional Colonoscopy in Enhanced Detection of Colorectal Adenomas and Polyps - A Systematic Review and Meta-Analysis

Rishikesh R. Magaji, ¹, Trisha Chandra Mohan, ¹, Vinay Chandramouli Bellur, ², Omar Oudit, DO³, Ananya Prasad, ⁴, Vardhini Ganesh Iyer, ¹, Vibhav MS, ⁵, Druvadeep Srinivas, ⁶, Prakriti Ramamurthy, MBBS, MD⁷, Sravani Bhavanam, ⁸, Allama Prabhu N S, ⁹, Adithya Sathya narayana, MBBS¹⁰
1BGS Global Institute of Medical Sciences, Bangalore, Karnataka, India; 2Ramaiah medical college, Bangalore, Karnataka, India; 3Brookdale University Hospital Medical Center, Brooklyn, NY; 4ramaiah medical college, Bangalore, Karnataka, India; 5bangalore medical college and research institute, Bangalore, Karnataka, India; 6rajarajeshwari medical college & hospital, Bangalore, Karnataka, India; 7University of Massachusetts Chan Medical School - Baystate Health, Springfield, MA; 8Brookdale University Hospital Medical Center, Bangalore, Karnataka, India; 9Bangalore Medical College and Research Institute, Bangalore, Karnataka, India; 10M S Ramaiah Medical College, Bangalore, Karnataka, India

Introduction: Artificial intelligence(AI)-aided colonscopy has shown significant improvement in detection of precancerous lesions. This systematic review and meta-analysis evaluates its performance in comparison to regular conventional colonoscopy by assessing the adenoma and polyp detection rates, as well as adenomas and polyps detected per procedure, thus highlighting the potential of AI to enhance prevention of colorectal cancer.

Methods: The review conducted follows the PRISMA guidelines and major medical databases, which include PUBMED, Google Scholar and Science-Direct, were extensively searched using a comprehensive search term to identify and retrieve available articles. The articles that included the assessment of the detection of adenoma and polyp by AI-assisted colonoscopy and traditional colonoscopy were included in the final analysis.



The data was analysed using the Meta, Metadata and the Metafor packages of R Studio. The Odds Ratio (OR) of detection of Adenoma and Polyp through different colonoscopy techniques was assessed as the primary outcome. The Mantel-Haenszel method and the Inverse variance method were utilised to analyse the odds ratio. The I^2 test was used to assess the heterogeneity of the studies.

Results: The study included a total of 16 studies with 5466 patients undergoing AI-assisted colonoscopy and 5430 subjects undergoing Traditional colonoscopy. The AI-assisted endoscopy performed better in comparison to traditional colonoscopy in detecting adenomas (OR=1.45 (1.27;1.67) ,95% CI,p=0.003 ,I^2=63.66%). The detection rates of detecting polyps in AI-assisted colonoscopy were significantly higher than traditional colonoscopy. (OR=2.01(1.14;3.52) 95% CI ,p< 0.0001 ,I^2=94.6%)

Discussion: Our study shows that AI assisted endoscopy is superior to Traditional Colonoscopy in the detection of Adenomas. The detection rate of Polyps through AI assisted colonoscopy was significantly higher. This highlights the importance of integration of AI in routine endoscopy to enhance detection of Adenomas and Polyps which go undetected through traditional endoscopy.


Figure: Odds Ratio of Detection of Adenomas in AI Assisted Colonoscopy in comparision to Traditional Endoscopy


Figure: Odds Ratio of Detection of Polyps in AI Assisted Colonoscopy in comparision to Traditional Endoscopy

Disclosures:
Rishikesh R. Magaji indicated no relevant financial relationships.
Trisha Chandra Mohan indicated no relevant financial relationships.
Vinay Chandramouli Bellur indicated no relevant financial relationships.
Omar Oudit indicated no relevant financial relationships.
Ananya Prasad indicated no relevant financial relationships.
Vardhini Ganesh Iyer indicated no relevant financial relationships.
Vibhav MS indicated no relevant financial relationships.
Druvadeep Srinivas indicated no relevant financial relationships.
Prakriti Ramamurthy indicated no relevant financial relationships.
Sravani Bhavanam indicated no relevant financial relationships.
Allama Prabhu N S indicated no relevant financial relationships.
Adithya Sathya narayana indicated no relevant financial relationships.

Rishikesh R. Magaji, ¹, Trisha Chandra Mohan, ¹, Vinay Chandramouli Bellur, ², Omar Oudit, DO³, Ananya Prasad, ⁴, Vardhini Ganesh Iyer, ¹, Vibhav MS, ⁵, Druvadeep Srinivas, ⁶, Prakriti Ramamurthy, MBBS, MD⁷, Sravani Bhavanam, ⁸, Allama Prabhu N S, ⁹, Adithya Sathya narayana, MBBS¹⁰. P0530 - Comparison of Effectiveness of Artificial Intelligence (AI)-Aided Colonoscopy With Conventional Colonoscopy in Enhanced Detection of Colorectal Adenomas and Polyps - A Systematic Review and Meta-Analysis, ACG 2025 Annual Scientific Meeting Abstracts. Phoenix, AZ: American College of Gastroenterology.