Affordable Access

deepdyve-link
Publisher Website

Spectral clustering of risk score trajectories stratifies sepsis patients by clinical outcome and interventions received.

Authors
  • Liu, Ran1, 2
  • Greenstein, Joseph L1
  • Fackler, James C3, 4
  • Bembea, Melania M3, 4
  • Winslow, Raimond L1, 2
  • 1 Institute for Computational Medicine, The Johns Hopkins University, Baltimore, United States. , (United States)
  • 2 Department of Biomedical Engineering, The Johns Hopkins University School of Medicine & Whiting School of Engineering, Baltimore, United States. , (United States)
  • 3 Department of Anesthesiology and Critical Care Medicine, The Johns Hopkins University School of Medicine, Baltimore, United States. , (United States)
  • 4 Department of Pediatrics, The Johns Hopkins University School of Medicine, Baltimore, United States. , (United States)
Type
Published Article
Journal
eLife
Publisher
"eLife Sciences Organisation, Ltd."
Publication Date
Sep 22, 2020
Volume
9
Identifiers
DOI: 10.7554/eLife.58142
PMID: 32959779
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

Sepsis is not a monolithic disease, but a loose collection of symptoms with diverse outcomes. Thus, stratification and subtyping of sepsis patients is of great importance. We examine the temporal evolution of patient state using our previously-published method for computing risk of transition from sepsis into septic shock. Risk trajectories diverge into four clusters following early prediction of septic shock, stratifying by outcome: the highest-risk and lowest-risk groups have a 76.5% and 10.4% prevalence of septic shock, and 43% and 18% mortality, respectively. These clusters differ also in treatments received and median time to shock onset. Analyses reveal the existence of a rapid (30-60 min) transition in risk at the time of threshold crossing. We hypothesize that this transition occurs as a result of the failure of compensatory biological systems to cope with infection, resulting in a bifurcation of low to high risk. Such a collapse, we believe, represents the true onset of septic shock. Thus, this rapid elevation in risk represents a potential new data-driven definition of septic shock. © 2020, Liu et al.

Report this publication

Statistics

Seen <100 times