IOS Press, Studies in Health Technology and Informatics, 2023
DOI: 10.3233/shti230346
Full text: Unavailable
Feature importance is often used to explain clinical prediction models. In this work, we examine three challenges using experiments with electronic health record data: computational feasibility, choosing between methods, and interpretation of the resulting explanation. This work aims to create awareness of the disagreement between feature importance methods and underscores the need for guidance to practitioners how to deal with these discrepancies.