Towards Polynomial Adaptive Local Explanations for Healthcare Classifiers

Jamie Andrew Duell, Xiuyi Fan, Monika Seisenberger

Abstract: Local explanations aim to provide transparency for individual instances and their associated predictions. The need for local explanations is prominent for high-risk domains such as finance, law and health care. We propose a new model-agnostic framework for local explanations “Polynomial Adaptive Local Explanations (PALE)”, to combat the lack of transparency of predictions through adaptive local models. We aim to explore explanations of predictions by assessing the impact of instantaneous rate of change in each feature and the association with the resulting prediction of the local model. PALE optimises a complex black-box model and the local explanation models for each instance, providing two forms of explanations, one provided by a localised derivative of an adapting polynomial, thus emphasising instance specificity, and the latter a core interpretable logistic regression model.