Litcius/Paper detail

Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice

Idan Levy, Liora Bruckmayer, Eyal Klang, Shomron Ben‐Horin, Uri Kopylov

2022The American Journal of Gastroenterology107 citationsDOI

Abstract

The performance of artificial intelligence-aided colonoscopy (AIAC) in a real-world setting has not been described. We compared adenoma and polyp detection rates (ADR/PDR) in a 6-month period before (pre-AIAC) and after introduction of AIAC (GI Genius, Medtronic) in all endoscopy suites in our large-volume center. The ADR and PDR in the AIAC group was lower compared with those in the pre-AIAC group (30.3% vs 35.2%, P < 0.001; 36.5% vs 40.9%, P = 0.004, respectively); procedure time was significantly shorter in the AIAC group. In summary, introduction of AIAC did not result in performance improvement in our large-center cohort, raising important questions on AI-human interactions in medicine.

Topics & Concepts

MedicineColonoscopyAdenomaClinical PracticeGeneral surgeryMedical physicsInternal medicineFamily medicineColorectal cancerCancerColorectal Cancer Screening and DetectionRadiomics and Machine Learning in Medical ImagingGastric Cancer Management and Outcomes