A prospective comparison of two computer aided detection systems with different false positive rates in colonoscopy (Nature)

A recent study comparing two AI-driven computer-aided detection (CADe) systems for colonoscopy found that a lower false positive (FP) rate led to significantly better clinical outcomes. The system with fewer FPs improved the adenoma detection rate and adenomas per colonoscopy, without increasing unnecessary removals of non-neoplastic lesions. In contrast, the higher-FP system did not enhance detection and caused more unnecessary resections. These findings highlight the importance of minimizing FPs for maximizing the effectiveness of AI-assisted colonoscopy.