JMIR Publications

ABSTRACT

Background:

Computer-aided detection (CADe) of colorectal polyps has been shown to increase adenoma detection rates, which would potentially shorten subsequent surveillance intervals.

Objective:

We simulated the potential changes in subsequent colonoscopy surveillance intervals after application of CADe in a large cohort of patients

Methods:

We simulated the projected increase in polyp and adenoma detection by universal CADe application in our patients who had undergone colonoscopy with complete endoscopic and histological findings between 2016 and 2020. Simulation was based on bootstrapping of the published performance of CADe. The corresponding changes in surveillance intervals of each patient, as recommended by the United States Multi-Society Task Force on Colorectal Cancer (USMSTF) or the European Society of Gastrointestinal Endoscopy (ESGE), after CADe was determined.

Results:

A total of 5,514 patients who had undergone colonoscopy were included. Based on the simulated CADe effect, the application of CADe would result in 11.2% and 2.5% of patients to have a shorter surveillance interval according to the USMSTF and ESGE guidelines, respectively. In particular, all (or 3.3% total) patients who were originally scheduled to have 3-5 years surveillance would have surveillance interval shortened to 3 years, following the USMSTF guidelines. Of this group of patients, the changes were largely attributed to increase in number of adenomas (70.8%) rather than serrated lesions detected.

Conclusions:

Widespread adoption of CADe would inevitably increase the demand for surveillance colonoscopy with shortening of original surveillance intervals, particularly following the current USMSTF guideline.