Real-Life Clinical Validation of AI-Assisted Detection and Differentiation of Pleomorphic Lesions in Capsule Endoscopy

Capsule endoscopy (CE) is a minimally invasive procedure designed for small bowels' evaluation. However, prolonged reading times and a risk of missing clinically significant findings limit its potential. Prospective clinical validation studies of artificial intelligence (AI) for CE remain scarce. Furthermore, existing studies focus on lesion detection, without addressing lesion differentiation. A multicenter prospective validation study aimed to compare AI-assisted with conventional CE-reading. 330 CE videos from three devices across seven centers and four countries. After conventional reading reports, AI-assisted reading was performed by an independent expert using a deep learning model to detect and differentiate pleomorphic small bowel lesions. Both reports were reviewed by an expert from an independent center, which decided in discrepant cases. AI-assisted and standard reading were evaluated through their accuracy, sensitivity, specificity, positive and negative predictive value and small bowel lesion detect rate (SBLDR). AI-assisted reading detected 605 out of 635 lesions identified by expert-based consensus, while standard reading identified 354 lesions. AI-assisted reading outperformed standard reading, with SBLDR of 96.1% vs 76.3% and sensitivity of 97.5% vs 78.2%. AI-assisted reading had a mean exam reading time of 203 seconds per exam. This was the first multicentric study proving AI-assisted CE reading superiority compared to conventional reading. The inclusion of videos from multiple devices addresses the interoperability challenge, whereas including patients from 4 countries and two different continents assures a diverse demographic context. AI achieved gastroenterologist-level identification of small-bowel lesions, surpassing conventional reading methods in both lesion detection and characterization.