Open access
Jul 2026
Reducing overconfident errors in clinical prediction models.
Machine Learning (ML) models are increasingly being used in clinical workflows. Evaluation of these models tends to focus on global performance metrics, which can obscure error patterns and lead to bias in clinical decision making. Here, we propose Proximal Error-Based Confidence Adjustment (PECA), a framework designed...
Henry Bayly, Y. Tripodis, Steven Lenio et al.
· BMC Medical Informatics and... · 0 citations