Global and local interpretability techniques of supervised machine learning black box models for numerical medical data

Abstract

The most effective machine learning classification techniques, such as artificial neural networks, are not easily interpretable, which limits their usefulness in critical areas, such as medicine, where errors can have severe consequences. Researchers have been working to balance the trade-off between the model performance and interpretability. In this study, seven interpretability techniques (global surrogate, accumulated local effects, local interpretable model-agnostic explanations (LIME), Shapley additive explanations (SHAP), model agnostic post hoc local explanations (MAPLE), local rule-based explanation (LORE), and Contextual Importance and Utility (CIU)) were evaluated to interpret five medical classifiers (multilayer perceptron, support vector machines, random forests, extreme gradient boosting, and naïve bayes) using six model performance metrics and three interpretability technique metrics across six medical numerical datasets. The results confirmed the effectiveness of integrating global and local interpretability techniques, and highlighted the superior performance of global SHAP explainer and local CIU explanations. The quantitative evaluations of explanations emphasised the importance of assessing these interpretability techniques before employing them to interpret black box models.