Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series

Abstract

Deep learning-based support systems have demonstrated encouraging results in numerous clinical applications involving the processing of time series data. While such systems often are very accurate, they have no inherent mechanism for explaining what influenced the predictions, which is critical for clinical tasks. However, existing explainability techniques lack an important component for trustworthy and reliable decision support, namely a notion of uncertainty. In this paper, we address this lack of uncertainty by proposing a deep ensemble approach where a collection of DNNs are trained independently. A measure of uncertainty in the relevance scores is computed by taking the standard deviation across the relevance scores produced by each model in the ensemble, which in turn is used to make the explanations more reliable. The class activation mapping method is used to assign a relevance score for each time step in the time series. Results demonstrate that the proposed ensemble is more accurate in locating relevant time steps and is more consistent across random initializations, thus making the model more trustworthy. The proposed methodology paves the way for constructing trustworthy and dependable support systems for processing clinical time series for healthcare related tasks.

arXiv comment11 pages, 9 figures, code at https://github.com/Wickstrom/TimeSeriesXAI

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Neural Machine Translation by Jointly Learning to Align and Translate
• Popular Ensemble Methods: An Empirical Study
• Striving for Simplicity: The All Convolutional Net
• InceptionTime: Finding AlexNet for Time Series Classification
• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
• Uncertainty and Interpretability in Convolutional Neural Networks for Semantic Segmentation of Colorectal Polyps
• Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record

Cited by in corpus (2)

• Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine
• Deep sub-ensembles meets quantile regression: uncertainty-aware imputation for time series