Early detection of sepsis utilizing deep learning on electronic health record event sequences

作者：

Highlights：

• Deep learning algorithm for early detection of sepsis on multi-center Danish data.

• Algorithm performance is superior to baseline machine learning models.

• Improved decision analysis that accounts for early model performance.

• Improves clinical utility by enabling earlier sepsis interventions.

摘要

•Deep learning algorithm for early detection of sepsis on multi-center Danish data.•Algorithm performance is superior to baseline machine learning models.•Improved decision analysis that accounts for early model performance.•Improves clinical utility by enabling earlier sepsis interventions.

论文关键词：Sepsis,Clinical decision support systems,Machine learning,Medical informatics,Early diagnosis,Electronic health records

论文评审过程：Received 2 May 2019, Revised 9 January 2020, Accepted 17 February 2020, Available online 19 February 2020, Version of Record 11 April 2020.

论文官网地址：https://doi.org/10.1016/j.artmed.2020.101820