THE PIONEERING COLO-DETECT trial has demonstrated the potential of AI to significantly enhance the detection of colorectal polyps during colonoscopies.
Conducted across 12 NHS hospitals in England, the multicentre, open-label, parallel-arm, pragmatic randomised controlled trial investigated the effectiveness of the GI Genius intelligent endoscopy module by comparing computer-aided detection (CADe)-assisted colonoscopies with standard colonoscopies in routine practice.
The study involved 2,032 adult participants with an average age of 62.4 years, of whom 55.7% were male and 44.3% female. Patients underwent colonoscopies either for colorectal cancer screening (60.6%) or due to gastrointestinal symptoms (39.4%). Participants were randomly assigned in equal numbers to either CADe-assisted or standard colonoscopy using a web-based algorithm. The primary outcome was the mean number of adenomas detected per procedure, and the secondary outcome measured the proportion of procedures that identified at least one adenoma. Adenomas, which are precancerous polyps, are critical to detect and remove to prevent progression to colorectal cancer.
Results revealed that CADe-assisted colonoscopies significantly outperformed standard colonoscopies in detecting adenomas. In the CADe-assisted group, the average number of adenomas per procedure was 1.56 compared to 1.21 in the standard group, representing a 30% increase in detection (adjusted mean difference: 0·36, P<0.0001). Additionally, adenomas were detected in 56.6% of procedures in the CADe-assisted group compared to 48.4% in the standard group, reflecting an 8.3% higher detection rate (adjusted odds ratio: 1.47, P<0.0001).
Importantly, the increased detection did not result in higher rates of adverse events. The CADe-assisted group reported 25 adverse events, compared to 19 in the standard group, but none in the CADe-assisted group were linked to the use of the GI Genius module. These findings suggest that the integration of AI into colonoscopy procedures can significantly enhance the identification of premalignant polyps without compromising patient safety.
AI technologies, such as GI Genius, can improve routine medical practices by increasing the quality and effectiveness of preventive healthcare. By facilitating earlier detection of colorectal polyps, these tools can play a pivotal role in reducing the incidence and mortality of colorectal cancer, which remains one of the leading causes of cancer-related deaths globally.
Ada Enesco, EMJ
Reference
Seager A et al. Polyp detection with colonoscopy assisted by the GI Genius artificial intelligence endoscopy module compared with standard colonoscopy in routine colonoscopy practice (COLO-DETECT): a multicentre, open-label, parallel-arm, pragmatic randomised controlled trial. Lancet Gastroenterol Hepatol. 2024;9(10):911-923.
