Deep EHR Spotlight: a Framework and Mechanism to Highlight Events in Electronic Health Records for Explainable Predictions
This addresses the problem of explainability in EHR-based predictions for clinicians and researchers, though it appears incremental as it builds on existing deep learning and attention mechanisms.
The paper tackles the lack of transparency and cumbersome pre-processing in deep learning models for Electronic Health Records (EHRs) by proposing a framework that encodes patient pathways into images and highlights important events, enabling more complex predictions with intelligibility.
The wide adoption of Electronic Health Records (EHR) has resulted in large amounts of clinical data becoming available, which promises to support service delivery and advance clinical and informatics research. Deep learning techniques have demonstrated performance in predictive analytic tasks using EHRs yet they typically lack model result transparency or explainability functionalities and require cumbersome pre-processing tasks. Moreover, EHRs contain heterogeneous and multi-modal data points such as text, numbers and time series which further hinder visualisation and interpretability. This paper proposes a deep learning framework to: 1) encode patient pathways from EHRs into images, 2) highlight important events within pathway images, and 3) enable more complex predictions with additional intelligibility. The proposed method relies on a deep attention mechanism for visualisation of the predictions and allows predicting multiple sequential outcomes.