NL
DE
While colonoscopy is the gold standard for detecting and removing colorectal polyps, up to one-fourth of polyps are still missed. Increased detection of polyps is associated with a decreased risk of developing colorectal cancer. AI polyp detection systems during colonoscopy have the potential to improve detection rates without increasing the procedural burden on patients.
Researcher Michiel Maas from the Department of Gastroenterology & Hepatology at Radboudumc evaluated the ‘Discovery’ AI system by PENTAX Medical across various colonoscopy indications. The research team, led by Peter Siersema, in collaboration with seven study sites across Europe and Canada, published their results in Endoscopy on May 15, 2024.
They conducted an international randomized controlled trial at seven sites. The primary aim of the study was to investigate whether the use of AI during colonoscopy improved the detection of adenomas, with a secondary focus on detecting sessile serrated lesions (SSLs), which are harder to spot and increasingly recognized for their role in the colorectal cancer pathway.
Text continues after image
Surprisingly, the study did not show a significant increase in adenoma detection with the use of AI. However, it did find that AI significantly improved the detection of SSLs. These results differ from earlier trials but align with more recent real-world studies investigating the efficacy of AI during colonoscopy. Given these mixed results, future research should explore the AI-human interaction and how AI can be tailored for different experience levels and colonoscopy indications. Future studies should also examine the impact of AI on long-term outcomes like colorectal cancer incidence and mortality.
-
Read the study here: A computer-aided detection system in the everyday setting of diagnostic, screening and surveillance colonoscopy: an international, randomized trial - PubMed (nih.gov)
Maas MHJ, Rath T, Spada C, Soons E, Forbes N, Kashin S, Cesaro P, Eickhoff A, Vanbiervliet G, Salvi D, Belletrutti PJ, Siersema PD. A computer-aided detection system in the everyday setting of diagnostic, screening and surveillance colonoscopy: an international, randomized trial. Endoscopy. 2024 May 15. doi: 10.1055/a-2328-2844. Epub ahead of print. PMID: 38749482.
