Fact checked byHeather Biele

Read more

August 26, 2024
2 min read
Save

AI-based GI Genius boosts adenoma, sessile serrated lesion detection vs. colonoscopy alone

Fact checked byHeather Biele
You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

Key takeaways:

  • Mean number of adenomas per procedure was higher with GI Genius vs. standard colonoscopy (1.56 vs. 1.21), as was ADR (56.6% vs. 48.4%).
  • Sessile serrated lesion detection rate also was higher with GI Genius.

An AI-assisted endoscopy module increased adenoma detection, including sessile serrated lesions, during colonoscopy and is recommended in routine practice to reduce incidence of post-procedure colorectal cancer, according to researchers.

“The GI Genius intelligent endoscopy module (Medtronic) is an AI-based computer-aided detection (CADe) system that integrates with most endoscopy systems,” Alexander Seager, MSc, of the department of research and innovation at South Tyneside and Sunderland NHS Foundation Trust, and colleagues wrote in The Lancet Gastroenterology & Hepatology. “Several studies and meta-analyses of CADe systems have been reported in the past few years; they have consistently shown increases in adenoma detection rate and mean adenomas per procedure with CADe.

Results from the COLO-DETECT trial demonstrated adenoma detection rates of: GI Genius-assisted colonoscopy; 56.5% VS Standard colonoscopy; 48.4%
Data derived from: Seager A, et al. Lancet Gastroenterol Hepatol. 2024;doi:10.1016/S2468-1253(24)00161-4.

“Well-powered randomized, controlled trials delivered in a pragmatic way with robust methodology, including screening and non-screening populations, are required.”

In the COLO-DETECT trial, Seager and colleagues enrolled 2,032 participants (mean age, 62.4 years; 55.7% men) undergoing colonoscopy for gastrointestinal symptoms, surveillance or CRC screening at 12 NHS hospitals in England. Individuals were randomly assigned to CADe-assisted colonoscopy, with the GI Genius module active throughout the inspection phase of colonoscope withdrawal (n = 1,015), or standard colonoscopy (n = 1,017).

The primary outcome was mean adenomas per procedure, while the key secondary outcome was ADR. Other secondary outcomes included sessile serrated lesion and polyp detection rates. The researchers conducted subgroup analyses of secondary outcomes by screening (60.6%) or symptomatic (39.4%) indication.

According to results, the mean number of adenomas per procedure was higher in the CADe-assisted group vs. the standard colonoscopy group (1.56 vs. 1.21), with an adjusted mean difference of 0.36 (95% CI, 0.14-0.57) and an adjusted incidence rate ratio of 1.3 (95% CI, 1.15-1.47).

In addition, CADe-assisted colonoscopy yielded a higher ADR (56.5% vs. 48.4%), with a proportional difference (PD) of 8.3% (95% CI, 3.9-12.7) and adjusted OR of 1.47 (95% CI, 1.21-1.78), as well as a higher sessile serrated lesion detection rate (PD = 3%; 95% CI, 0.4-5.5; aOR = 1.46; 95% CI, 1.07-1.99). The polyp detection rate also was higher in the CADe-assisted group (PD = 9%; 95% CI, 4.9-13.2; aOR = 1.56; 95% CI, 1.29-1.9) and type 0 to IIa polyps were more commonly detected (34% vs. 27%).

The researchers reported similar results in both the screening and symptomatic subpopulations.

“The GI Genius intelligent endoscopy module improved polyp detection overall and in both screening and symptomatic subpopulations, compared with standard colonoscopy,” Seager and colleagues wrote. “The benefit was particularly evident for the detection of small, flat (type 0–IIa) polyps, aligning with increased detection of adenomas and sessile serrated lesions, which is likely to be of clinical significance.”

They continued: “We recommend the adoption of GI Genius to improve polyp detection and, in turn, reduce the incidence of post-colonoscopy colorectal cancer.”