Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU.

Journal: BMJ open
Published Date: Jan 26, 2018

Abstract

OBJECTIVES: We validate a machine learning-based sepsis-prediction algorithm () for the detection and prediction of three sepsis-related gold standards, using only six vital signs. We evaluate robustness to missing data, customisation to site-specific data using transfer learning and generalisability to new settings.

Authors

  • Qingqing Mao
    Dascena Inc., Hayward, California, USA.
  • Melissa Jay
    Dascena Inc., Hayward, California, USA.
  • Jana L Hoffman
    Dascena Inc., Hayward, California, USA.
  • Jacob Calvert
    Dascena Inc., Hayward, California, USA.
  • Christopher Barton
    Department of Emergency Medicine, University of California San Francisco, San Francisco, California, USA.
  • David Shimabukuro
    Department of Anesthesia and Perioperative Care, University of California San Francisco, San Francisco, California, USA.
  • Lisa Shieh
    Department of Medicine, Stanford University School of Medicine, Stanford, California, USA.
  • Uli Chettipally
    Department of Emergency Medicine, University of California San Francisco, San Francisco, California, USA.
  • Grant Fletcher
    Division of Internal Medicine, University of Washington School of Medicine, Seattle, Washington, USA.
  • Yaniv Kerem
    Department of Clinical Informatics, Stanford University School of Medicine, Stanford, California, USA.
  • Yifan Zhou
    Department of Pharmacology, University of Oxford, Oxford, United Kingdom.
  • Ritankar Das
    Dascena, Inc, Hayward, California, USA.

Keywords

External Resources

Popular Topics
Recent Journals