Cesare Hassan, in collaboration with several established researchers in the European gastroenterology community, among them Yuichi Mori at The University of Oslo, published the paper “Real-Time Computer-Aided Detection of Colorectal Neoplasia During Colonoscopy: A Systematic Review and Meta-analysis” this week in the renowned medical journal Annals of Internal Medicine.
Increased performance
The study investigates the effect of real-time computer-aided detection of colorectal polyps during colonoscopy (CADe, an AI tool). The researchers found that doctors performed better, by detecting more polyps, when aided by the AI tool. The effect was negatively correlated with the experience of the endosopists, which is good news: the best effects are achieved when increasing the skills in those with a lower performance level, hence low ADR (ADR: Adenoma Detection Rate).
The paper was also commented in the editorial “From Tool to Team Member: A Second Set of Eyes for Polyp Detection” in the same issue of Annals of Internal Medicine.