Early prediction of the risk of ICU mortality with Deep Federated Learning
This provides a privacy-preserving solution for hospitals to predict ICU mortality risk without sharing sensitive patient data, though it is incremental as it applies an existing federated learning framework to a specific healthcare task.
The study tackled early prediction of ICU mortality risk using deep federated learning to address data privacy constraints, showing that federated learning performs equally well as centralized approaches and substantially better than local methods, with performance metrics like AUPRC, F1-score, and AUROC.
Intensive Care Units usually carry patients with a serious risk of mortality. Recent research has shown the ability of Machine Learning to indicate the patients' mortality risk and point physicians toward individuals with a heightened need for care. Nevertheless, healthcare data is often subject to privacy regulations and can therefore not be easily shared in order to build Centralized Machine Learning models that use the combined data of multiple hospitals. Federated Learning is a Machine Learning framework designed for data privacy that can be used to circumvent this problem. In this study, we evaluate the ability of deep Federated Learning to predict the risk of Intensive Care Unit mortality at an early stage. We compare the predictive performance of Federated, Centralized, and Local Machine Learning in terms of AUPRC, F1-score, and AUROC. Our results show that Federated Learning performs equally well as the centralized approach and is substantially better than the local approach, thus providing a viable solution for early Intensive Care Unit mortality prediction. In addition, we show that the prediction performance is higher when the patient history window is closer to discharge or death. Finally, we show that using the F1-score as an early stopping metric can stabilize and increase the performance of our approach for the task at hand.