Factors driving provider adoption of the TREWS machine learning-based early warning system and its effects on sepsis treatment timing.

Journal: Nature medicine
Published Date: Jul 21, 2022

Abstract

Machine learning-based clinical decision support tools for sepsis create opportunities to identify at-risk patients and initiate treatments at early time points, which is critical for improving sepsis outcomes. In view of the increasing use of such systems, better understanding of how they are adopted and used by healthcare providers is needed. Here, we analyzed provider interactions with a sepsis early detection tool (Targeted Real-time Early Warning System), which was deployed at five hospitals over a 2-year period. Among 9,805 retrospectively identified sepsis cases, the early detection tool achieved high sensitivity (82% of sepsis cases were identified) and a high rate of adoption: 89% of all alerts by the system were evaluated by a physician or advanced practice provider and 38% of evaluated alerts were confirmed by a provider. Adjusting for patient presentation and severity, patients with sepsis whose alert was confirmed by a provider within 3 h had a 1.85-h (95% CI 1.66-2.00) reduction in median time to first antibiotic order compared to patients with sepsis whose alert was either dismissed, confirmed more than 3 h after the alert or never addressed in the system. Finally, we found that emergency department providers and providers who had previous interactions with an alert were more likely to interact with alerts, as well as to confirm alerts on retrospectively identified patients with sepsis. Beyond efforts to improve the performance of early warning systems, efforts to improve adoption are essential to their clinical impact and should focus on understanding providers' knowledge of, experience with and attitudes toward such systems.

Authors

  • Katharine E Henry
    Department of Computer Science, Johns Hopkins University, Baltimore, MD.
  • Roy Adams
    College of Information and Computer Sciences, University of Massaachusttes Amherst, Amherst, MA, United States.
  • Cassandra Parent
    Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA.
  • Hossein Soleimani
    Health Informatics, University of California, San Francisco, San Francisco, CA, USA.
  • Anirudh Sridharan
    Howard County General Hospital, Columbia, MD, USA.
  • Lauren Johnson
    Department of Quality Improvement, The Johns Hopkins Hospital, Baltimore, MD, USA.
  • David N Hager
    Division of Pulmonary and Critical Care, Department of Medicine, Johns Hopkins University, Baltimore, MD.
  • Sara E Cosgrove
    Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA.
  • Andrew Markowski
    Suburban Hospital, Bethesda, MD, USA.
  • Eili Y Klein
    Center for Disease Dynamics, Economics & Policy, Silver Spring, Maryland, United States.
  • Edward S Chen
    Department of Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA.
  • Mustapha O Saheed
    Department of Emergency Medicine, Johns Hopkins School of Medicine, Baltimore, MD, USA.
  • Maureen Henley
    Department of Quality Improvement, The Johns Hopkins Hospital, Baltimore, MD, USA.
  • Sheila Miranda
    Department of Medicine, The Johns Hopkins Hospital, Baltimore, MD, USA.
  • Katrina Houston
    Department of Quality Improvement, The Johns Hopkins Hospital, Baltimore, MD, USA.
  • Robert C Linton
    Howard County General Hospital, Columbia, MD, USA.
  • Anushree R Ahluwalia
    Department of Quality Improvement, The Johns Hopkins Hospital, Baltimore, MD, USA.
  • Albert W Wu
    Department of Health Policy and Management, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD.
  • Suchi Saria
    Department of Computer Science, Johns Hopkins University, Baltimore, MD.

Keywords

External Resources

Popular Topics
Recent Journals