Ada-WHIPS: Explaining AdaBoost Classification with Applications in the Health Sciences

Abstract

Background Computer Aided Diagnostics (CAD) can support medical practitioners to make critical decisions about their patients' disease conditions. Practitioners require access to the chain of reasoning behind CAD to build trust in the CAD advice and to supplement their own expertise. Yet, CAD systems might be based on black box machine learning (ML) models and high dimensional data sources (electronic health records, MRI scans, cardiotocograms, etc). These foundations make interpretation and explanation of the CAD advice very challenging. This challenge is recognised throughout the machine learning research community. eXplainable Artificial Intelligence (XAI) is emerging as one of the most important research areas of recent years, because it addresses the interpretability and trust concerns of medical practitioners and other critical decision makers. Method In this work, we focus on AdaBoost, a black box model that has been widely adopted in the CAD literature. We address the challenge -- to explain AdaBoost classification -- with a novel algorithm that extracts simple, logical rules from AdaBoost models. Our algorithm, \textit{Adaptive-Weighted High Importance Path Snippets} (Ada-WHIPS), makes use of AdaBoost's adaptive classifier weights; using a novel formulation, Ada-WHIPS uniquely redistributes the weights among individual decision nodes at the internals of the AdaBoost model. Then, a simple heuristic search of the weighted nodes finds a single rule that dominated the model's decision. We compare the explanations generated by our novel approach with the state of the art in an experimental study. We evaluate the derived explanations with simple statistical tests of well-known quality measures, precision and coverage, and a novel measure \textit{stability} that is better suited to the XAI setting. Results In this paper, our experimental results demonstrate the benefits of using our novel algorithm for explaining AdaBoost classification. The simple rule-based explanations have better generalisation (mean coverage 15\%-68\%) while remaining competitive for specificity (mean precision 80\%-99\%). A very small trade-off in specificity is shown to guard against over-fitting. Conclusions This research demonstrates that interpretable, classification rule-based explanations can be generated for computer aided diagnostic tools based on AdaBoost, and that a tightly coupled, AdaBoost-specific approach can outperform model-agnostic methods.