The Physiological Deep Learner: First application of multitask deep learning to predict hypotension in critically ill patients

作者：

Highlights：

• Expand the concept of learning from multiple physiological parameters by using a multitask learning approach

• Prediction of the mean arterial pressure and the heart rate simultaneously.

• Clinically meaningful predictions by providing actual values of MAP and HR

摘要

•Expand the concept of learning from multiple physiological parameters by using a multitask learning approach•Prediction of the mean arterial pressure and the heart rate simultaneously.•Clinically meaningful predictions by providing actual values of MAP and HR

论文关键词：Critical care,Shock hypotension,Multitask learning,RNN

论文评审过程：Received 20 February 2021, Revised 12 May 2021, Accepted 21 May 2021, Available online 29 May 2021, Version of Record 11 June 2021.

论文官网地址：https://doi.org/10.1016/j.artmed.2021.102118