Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals.

Journal: BMC medical informatics and decision making
PMID: 33109167

Abstract

BACKGROUND: Severe sepsis and septic shock are among the leading causes of death in the United States and sepsis remains one of the most expensive conditions to diagnose and treat. Accurate early diagnosis and treatment can reduce the risk of adverse patient outcomes, but the efficacy of traditional rule-based screening methods is limited. The purpose of this study was to develop and validate a machine learning algorithm (MLA) for severe sepsis prediction up to 48 h before onset using a diverse patient dataset.

Authors

  • Hoyt Burdick
    Cabell Huntington Hospital, Huntington, WV, USA; Marshall University School of Medicine, Huntington, WV, USA.
  • Eduardo Pino
    Cabell Huntington Hospital, Huntington, WV, USA.
  • Denise Gabel-Comeau
    Cabell Huntington Hospital, Huntington, WV, USA.
  • Carol Gu
    Dascena, Inc., P.O. Box 156572, San Francisco, CA, 94115, USA.
  • Jonathan Roberts
    Dascena, Inc., P.O. Box 156572, San Francisco, CA, 94115, USA.
  • Sidney Le
    Dascena Inc., Oakland, CA, USA.
  • Joseph Slote
    Dascena, Inc., P.O. Box 156572, San Francisco, CA, 94115, USA.
  • Nicholas Saber
    Dascena, Inc., P.O. Box 156572, San Francisco, CA, 94115, USA.
  • Emily Pellegrini
  • Abigail Green-Saxena
    Dascena, Inc., USA.
  • Jana Hoffman
    Dascena Inc., San Francisco, CA, United States.
  • Ritankar Das
    Dascena, Inc, Hayward, California, USA.

Keywords

External Resources

Popular Topics
Recent Journals