Enhancing accuracy and interpretability in EEG-based medical decision making using an explainable ensemble learning framework application for stroke prediction

Medical decision making increasingly relies on machine learning algorithms to analyze complex patient data and provide recommendations. However, the lack of interpretability in "black box" models has limited their adoption in clinical practice, which demands transparency and justification. Echo State Networks (ESNs), a recurrent neural network architecture, have shown promise for medical Decision Support Systems (DSS) applications due to their accuracy in modeling time series data, such as physiological signals. However, conventional ESNs suffer from a lack of interpretability, which limits their usefulness for clinical decisions. This study proposes a multilevel framework to optimize both accuracy and interpretability for improved medical decision support. The framework is specifically designed for EEG data, which represents a non-invasive and continuous recording of brain activity. EEG data is ideal for recording information about the internal state of the brain, which is not always translated by perceptible external manifestations. The framework consists of four components: (1) data preprocessing and optimized feature selection utilizing a filter-based feature importance algorithm, (2) ensemble learning via Ensemble ESNs (E-ESNs) that combines the predictions of multiple ESNs to reduce variance and improve accuracy, (3) Global and Local model explanation techniques to allow users to understand the decisionmaking process and identify the most influential features for each prediction, and (4) decision-making for presenting diagnoses and recommendations. The framework was evaluated on an EEG dataset for stroke prediction, a valuable use case for informed clinical decisions and resource allocation. The results showed that the framework significantly outperformed baseline related works with an accuracy of 96.5% and provides insights into the E-ESN model's predictions. This transparency enhances trust and comprehension among healthcare practitioners. These findings suggest that the proposed framework can be a valuable tool for medical DSS applications.