Enhancing the Interpretability of Rule-based Explanations through Information Retrieval
This work addresses the need for more transparent AI in healthcare decision-making, particularly for clinicians assessing lymphedema risk, but it is incremental as it builds on existing explainable AI methods.
The authors tackled the problem of low interpretability in AI predictions for healthcare by developing an attribution-based method that uses information retrieval metrics to analyze rule-based models, specifically for assessing lymphedema risk after breast cancer radiotherapy, and found in a user study that it improved interpretability and usefulness compared to raw model outputs.
The lack of transparency of data-driven Artificial Intelligence techniques limits their interpretability and acceptance into healthcare decision-making processes. We propose an attribution-based approach to improve the interpretability of Explainable AI-based predictions in the specific context of arm lymphedema's risk assessment after lymph nodal radiotherapy in breast cancer. The proposed method performs a statistical analysis of the attributes in the rule-based prediction model using standard metrics from Information Retrieval techniques. This analysis computes the relevance of each attribute to the prediction and provides users with interpretable information about the impact of risk factors. The results of a user study that compared the output generated by the proposed approach with the raw output of the Explainable AI model suggested higher levels of interpretability and usefulness in the context of predicting lymphedema risk.