Early prediction of the risk of ICU mortality with Deep Federated Learning

• Published in: Proceedings / IEEE International Symposium on Computer-Based Medical Systems pp. 706 - 711
• Main Authors: Randl, Korbinian, Llados Armengol, Nuria, Mondrejevski, Lena, Miliou, Ioanna
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2023
• Subjects: Data models; Data privacy; Early Mortality Prediction; Federated learning; Hospitals; Intensive Care Unit; Measurement; MIMICs; Multivariate Time Series; Recurrent Neural Networks; Regulation

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 subjec...