Analysis of factors related to poor outcome after e-learning training in endoscopic diagnosis of early gastric cancer using magnifying narrow-band imaging

Background and Aims: An e-learning system teaching endoscopic diagnostic process for early gastric cancer using magnifying endoscopy with narrow-band imaging (M-NBI) was established, and its efficacy in improving the diagnostic performance for early gastric cancer was proven in a multicenter randomized controlled trial. The aim of this study was to clarify the difference in learning effect in each lesion characteristic. Methods: Three hundred sixty-five participants diagnosed 40 gastric lesions based on M-NBI findings using the vessel-plus-surface classification system. The diagnosis data collected from each participant were assessed in this study. The accuracy of NBI cancer diagnosis was assessed using area under the receiver operating characteristics curve (AUC/ROC) analysis. AUC/ROCs were separately calculated in each lesion characteristic (shape and size), and the data were compared between tests 1 and 3. Results: Continuous net reclassification improvement (cNRI) analysis of all lesions revealed significant improvement in reclassification when participants underwent e-learning (cNRI, 1.17; P < .01). The integrated discrimination improvement analysis demonstrated that the e-learning system improved diagnostic ability (.19; P < .01). According to the analysis depending on the lesion's characteristics, high AUC/ROCs were demonstrated in depressed and small lesions (< 10 mm; .90 and .93, respectively). The cNRI analysis showed remarkable e-learning improvement in both depressed (cNRI, 1.33; P < .01) and small lesions (cNRI, 1.46; P < .01). However, no significant e-learning improvement was observed in elevated or flat lesions. Conclusions: In M-NBI education for endoscopists, a good learning outcome was obtained in depressed and small lesions, but a poor learning outcome was demonstrated in elevated and flat lesions.