Causally-informed Deep Learning towards Explainable and Generalizable Outcomes Prediction in Critical Care
This addresses the need for explainable and generalizable early warning systems in critical care, representing an incremental improvement by integrating causal discovery into existing deep learning frameworks.
The paper tackled the problem of deep learning models lacking interpretability and limited generalizability in predicting clinical deteriorations in critical care, and the result was a causally-informed model that achieved superior accuracy for 6 different outcomes and better generalizability across patient groups compared to baselines.
Recent advances in deep learning (DL) have prompted the development of high-performing early warning score (EWS) systems, predicting clinical deteriorations such as acute kidney injury, acute myocardial infarction, or circulatory failure. DL models have proven to be powerful tools for various tasks but come with the cost of lacking interpretability and limited generalizability, hindering their clinical applications. To develop a practical EWS system applicable to various outcomes, we propose causally-informed explainable early prediction model, which leverages causal discovery to identify the underlying causal relationships of prediction and thus owns two unique advantages: demonstrating the explicit interpretation of the prediction while exhibiting decent performance when applied to unfamiliar environments. Benefiting from these features, our approach achieves superior accuracy for 6 different critical deteriorations and achieves better generalizability across different patient groups, compared to various baseline algorithms. Besides, we provide explicit causal pathways to serve as references for assistant clinical diagnosis and potential interventions. The proposed approach enhances the practical application of deep learning in various medical scenarios.