DeepSigns: A predictive model based on Deep Learning for the early detection of patient health deterioration
作者：
Highlights：
• Computational model able to predict the deterioration of patients’ health status.
• Model based on Deep Learning (LSTM) to predict vital signs (accuracy ¿ 80%).
• Prediction of the patient’s vital signs to support Prognostic Index’ calculation.
• Identifies cases (60%) of future deterioration status that would not be identified.
• DeepSigns model can be attached to any early warning scoring system.
摘要
•Computational model able to predict the deterioration of patients’ health status.•Model based on Deep Learning (LSTM) to predict vital signs (accuracy ¿ 80%).•Prediction of the patient’s vital signs to support Prognostic Index’ calculation.•Identifies cases (60%) of future deterioration status that would not be identified.•DeepSigns model can be attached to any early warning scoring system.
论文关键词：Predictive scores,Machine learning,Deep learning,LSTM,Health informatics
论文评审过程：Received 20 March 2020, Revised 13 August 2020, Accepted 18 August 2020, Available online 27 August 2020, Version of Record 29 August 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113905
