Accurate prediction of blood culture outcome in the intensive care unit using long short-term memory neural networks
作者：
Highlights：
• A computational model which can predict bloodstream infections in ICU patients is proposed.
• The model uses nine routinely available clinical parameters.
• The temporal nature of the model is key to success in early prediction.
• Implementation of the model in an electronic patient record may lead to earlier identification of patients at risk of bloodstream infection.
摘要
•A computational model which can predict bloodstream infections in ICU patients is proposed.•The model uses nine routinely available clinical parameters.•The temporal nature of the model is key to success in early prediction.•Implementation of the model in an electronic patient record may lead to earlier identification of patients at risk of bloodstream infection.
论文关键词：
论文评审过程：Received 25 April 2017, Revised 11 October 2018, Accepted 23 October 2018, Available online 9 November 2018, Version of Record 13 June 2019.
论文官网地址：https://doi.org/10.1016/j.artmed.2018.10.008
