Automated Interpretable Machine Learning for the Medical Domain

Abstract

Machine learning (ML) algorithms are increasingly used in high-stake domains like healthcare. While ML systems frequently outperform humans in specific tasks, ensuring safety and transparency is critical in these domains. Interpretability, therefore, plays a crucial role in understanding the decision-making process, auditing and correction of ML models and establishing trust. Furthermore, there is a growing demand for automated machine learning (AutoML) to facilitate model development without expert intervention. However, the combination of interpretability and AutoML has received limited attention thus far. In this study, we propose two objective model-agnostic measures of interpretability to quantify model compactness and explanation stability, embedded within an automated interpretable ML pipeline. We experiment with a set of interpretable models on medical classification tasks reporting the proposed measures along with the predictive performances. We further conduct a user study with domain experts to evaluate the correlation between these measures and the subjective concept of interpretability. Our findings demonstrate the effectiveness of the proposed measures, affirming their success and validating their utility in creating an interpretable automated pipeline.