Elucidating Discrepancy in Explanations of Predictive Models Developed using EMR
This addresses the lack of transparency hindering clinical adoption of ML algorithms, focusing on agreement between XAI methods and expert knowledge, but it is incremental as it applies existing methods to analyze discrepancies without introducing new techniques.
The study applied state-of-the-art explainability methods to clinical decision support algorithms using EMR data to analyze concordance with expert clinical knowledge, identifying discrepancies and discussing causes from clinical and technical perspectives.
The lack of transparency and explainability hinders the clinical adoption of Machine learning (ML) algorithms. While explainable artificial intelligence (XAI) methods have been proposed, little research has focused on the agreement between these methods and expert clinical knowledge. This study applies current state-of-the-art explainability methods to clinical decision support algorithms developed for Electronic Medical Records (EMR) data to analyse the concordance between these factors and discusses causes for identified discrepancies from a clinical and technical perspective. Important factors for achieving trustworthy XAI solutions for clinical decision support are also discussed.