Open your black box classifier

A priority for machine learning in healthcare and other high stakes applications is to enable end-users to easily interpret individual predictions. This opinion piece outlines recent developments in interpretable classifiers and methods to open black box models. This opinion piece outlines recent developments in the interpretation of machine learning models, with particular relevance for computer-based decision support in medicine. For tabular data, black box models can be opened, becoming as transparent as a nomogram, while retaining classification performance.image