Photo Credit: romaset

A novel AI detection system found more adenomas per colonoscopy compared with conventional methods, with no increase in withdrawal time.

A study published in The American Journal of Gastroenterology indicates that a novel AI detection system identified a meaningfully greater number of adenomas per colonoscopy than conventional high-definition colonoscopy without expanding colonoscopy withdrawal time.

Prateek Sharma, MD, and colleagues assessed a novel AI detection system that allows for real-time detection of colorectal polyps enabled with the colonoscope (CAD-EYE). The researchers recruited eligible patients who were at average risk, aged 45 years and older, and undergoing either screening or surveillance colonoscopy. The cohort was randomly assigned to undergo either CAD-EYE–assisted colonoscopy (CAC) or conventional colonoscopy (CC).

The researchers conducted a modified intention-to-treat investigation for patients who completed colonoscopy, focusing on the primary outcome of adenoma per colonoscopy (APC). Positive predictive value, or the total number of adenomas divided by total polyps removed, and adenoma detection rates were designated secondary outcomes.

Among the 1,031 participants in the modified intention-to-treat approach, 510 and 523 patients underwent CAC and CC, respectively, with no noteworthy differences in age, sex, ethnicity, or colonoscopy indication between the two groups.

More APC Detected With CAC System

The use of CAC resulted in meaningfully greater number of APC compared with CC, with no significant variance in the withdrawal time. The difference in the positive predictive value of a polyp detected as an adenoma among CAC and CC was less than the 10% threshold established.

Dr. Sharma and colleagues reported no significant differences in adenoma detection rate (46.9% vs 42.8%), the presence of advanced adenoma (6.5% vs 6.3%), sessile serrated lesion detection rate (12.9% vs 10.1%), and polyp detection rate (63.9% vs 59.3%) between the two groups. A larger number of polyps were detected per colonoscopy with CAC compared with CC: 1.68±2.1 vs 1.33±1.8 (incidence rate ratio, 1.27; P<0.01).

“Use of a novel AI detection system showed to a significantly higher number of adenomas per colonoscopy compared with conventional high-definition colonoscopy without any increase in colonoscopy withdrawal time, thus supporting the use of AI-assisted colonoscopy to improve colonoscopy quality,” the researchers wrote.