The Effect of Novel AI-based Cecum Recognition System on Adenoma Detection Metrics at Screening Colonoscopy Setting

Wen-Feng Hsu; Wei-Yuan Chang; Chen-Ya Kuo; Li-Chun Chang; Hsuan-Ho Lin; Ming-Shiang Wu; Han-Mo Chiu

doi:10.1016/j.gie.2024.09.019

The Effect of Novel AI-based Cecum Recognition System on Adenoma Detection Metrics at Screening Colonoscopy Setting

Gastrointest Endosc. 2024 Sep 17:S0016-5107(24)03501-6. doi: 10.1016/j.gie.2024.09.019. Online ahead of print.

Authors

Wen-Feng Hsu¹, Wei-Yuan Chang¹, Chen-Ya Kuo², Li-Chun Chang¹, Hsuan-Ho Lin³, Ming-Shiang Wu¹, Han-Mo Chiu⁴

Affiliations

¹ Department of Internal Medicine, National Taiwan University Hospital, Taipei, Taiwan; Department of Internal Medicine, National Taiwan University College of Medicine, Taipei, Taiwan.
² Department of Internal Medicine, Fu Jen Catholic University Hospital, New Taipei City, Taiwan.
³ Department of Internal Medicine, National Taiwan University Hospital, Hsin-Chu Branch, Hsin-Chu, Taiwan.
⁴ Department of Internal Medicine, National Taiwan University Hospital, Taipei, Taiwan; Department of Internal Medicine, National Taiwan University College of Medicine, Taipei, Taiwan. Electronic address: hanmochiu@ntu.edu.tw.

PMID: 39299304
DOI: 10.1016/j.gie.2024.09.019

Abstract

Background and aims: Cecal intubation of colonoscopy relies on self-reporting. We developed an artificial intelligence-based cecum recognition system (AI-CRS) for post hoc verification of cecal intubation and explored its impact on adenoma metrics.

Methods: Quality metrics, including cecal intubation rate (CIR), adenoma detection rate (ADR), and other ADR-related metrics were compared both before (2015-2018) and after (2019-2022) the implementation of AI-CRS.

Results: While CIR did not change significantly after the implementation of AI-CRS, ADR and AADR significantly increased. While ADR significantly increased in all segments, the most significant increase in AADR was observed in the proximal colon. Implementation of AI-CRS was associated with a higher likelihood of detecting adenoma (aOR=1.35, 95%CI=1.26-1.45) and advanced adenoma (aOR=1.23, 95%CI=1.07-1.41), respectively.

Conclusions: Implementation of a post hoc verification of cecal intubation using an AI-CRS significantly improved various adenoma metrics in screening colonoscopy.