Interpretable Machine Learning Classifiers for Brain Tumour Survival Prediction

TL;DR

This study compares interpretable rule-based models with black box machine learning methods for brain tumour survival prediction, emphasizing the importance of interpretability for clinical integration and demonstrating that simple rule lists can be nearly as effective as complex models.

Contribution

The paper introduces a novel dataset and evaluates the effectiveness and interpretability of rule list models versus popular machine learning approaches for brain tumour survival prediction.

Findings

Rule lists slightly outperform black box models in interpretability and clinical utility.

Black box models' explanations via LIME and SHAP may be unreliable.

Rule list algorithms produce decision lists aligned with clinical expertise.

Abstract

Prediction of survival in patients diagnosed with a brain tumour is challenging because of heterogeneous tumour behaviours and responses to treatment. Better estimations of prognosis would support treatment planning and patient support. Advances in machine learning have informed development of clinical predictive models, but their integration into clinical practice is almost non-existent. One reasons for this is the lack of interpretability of models. In this paper, we use a novel brain tumour dataset to compare two interpretable rule list models against popular machine learning approaches for brain tumour survival prediction. All models are quantitatively evaluated using standard performance metrics. The rule lists are also qualitatively assessed for their interpretability and clinical utility. The interpretability of the black box machine learning models is evaluated using two post-hoc explanation techniques, LIME and SHAP. Our results show that the rule lists were only slightly outperformed by the black box models. We demonstrate that rule list algorithms produced simple decision lists that align with clinical expertise. By comparison, post-hoc interpretability methods applied to black box models may produce unreliable explanations of local model predictions. Model interpretability is essential for understanding differences in predictive performance and for integration into clinical practice.