English

Predicting Severe Sepsis Using Text from the Electronic Health Record

Computers and Society 2017-12-01 v1 Machine Learning

Abstract

Employing a machine learning approach we predict, up to 24 hours prior, a diagnosis of severe sepsis. Strongly predictive models are possible that use only text reports from the Electronic Health Record (EHR), and omit structured numerical data. Unstructured text alone gives slightly better performance than structured data alone, and the combination further improves performance. We also discuss advantages of using unstructured EHR text for modeling, as compared to structured EHR data.

Keywords

Cite

@article{arxiv.1711.11536,
  title  = {Predicting Severe Sepsis Using Text from the Electronic Health Record},
  author = {Phil Culliton and Michael Levinson and Alice Ehresman and Joshua Wherry and Jay S. Steingrub and Stephen I. Gallant},
  journal= {arXiv preprint arXiv:1711.11536},
  year   = {2017}
}

Comments

Accepted at workshop on Machine Learning For Health at the conference on Neural Information Processing Systems, 2017. Near-final draft version

R2 v1 2026-06-22T23:02:44.063Z