Corpus ID: 28940368

Predicting Severe Sepsis Using Text from the Electronic Health Record

@article{Culliton2017PredictingSS,
  title={Predicting Severe Sepsis Using Text from the Electronic Health Record},
  author={Phil Culliton and M. Levinson and Alice Ehresman and Joshua Wherry and J. Steingrub and S. I. Gallant},
  journal={ArXiv},
  year={2017},
  volume={abs/1711.11536}
}

Phil Culliton, M. Levinson, +3 authors S. I. Gallant

Published 2017

Computer Science

ArXiv

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed

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.