Data-driven discovery of a novel sepsis pre-shock state predicts impending septic shock in the ICU

Ran Liu, Joseph L. Greenstein, Stephen J. Granite, James C Fackler, Melania Bembea, Sridevi V. Sarma, Raimond Winslow

Research output: Contribution to journalArticle

Abstract

Septic shock is a life-threatening condition in which timely treatment substantially reduces mortality. Reliable identification of patients with sepsis who are at elevated risk of developing septic shock therefore has the potential to save lives by opening an early window of intervention. We hypothesize the existence of a novel clinical state of sepsis referred to as the “pre-shock” state, and that patients with sepsis who enter this state are highly likely to develop septic shock at some future time. We apply three different machine learning techniques to the electronic health record data of 15,930 patients in the MIMIC-III database to test this hypothesis. This novel paradigm yields improved performance in identifying patients with sepsis who will progress to septic shock, as defined by Sepsis- 3 criteria, with the best method achieving a 0.93 area under the receiver operating curve, 88% sensitivity, 84% specificity, and median early warning time of 7 hours. Additionally, we introduce the notion of patient-specific positive predictive value, assigning confidence to individual predictions, and achieving values as high as 91%. This study demonstrates that early prediction of impending septic shock, and thus early intervention, is possible many hours in advance.

Original languageEnglish (US)
Article number6145
JournalScientific reports
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2019

Fingerprint

Septic Shock
Shock
Sepsis
Electronic Health Records
Databases
Sensitivity and Specificity
Mortality
Therapeutics

ASJC Scopus subject areas

  • General

Cite this

Data-driven discovery of a novel sepsis pre-shock state predicts impending septic shock in the ICU. / Liu, Ran; Greenstein, Joseph L.; Granite, Stephen J.; Fackler, James C; Bembea, Melania; Sarma, Sridevi V.; Winslow, Raimond.

In: Scientific reports, Vol. 9, No. 1, 6145, 01.12.2019.

Research output: Contribution to journalArticle

@article{307a5e9705004e158d81ab420693f190,
title = "Data-driven discovery of a novel sepsis pre-shock state predicts impending septic shock in the ICU",
abstract = "Septic shock is a life-threatening condition in which timely treatment substantially reduces mortality. Reliable identification of patients with sepsis who are at elevated risk of developing septic shock therefore has the potential to save lives by opening an early window of intervention. We hypothesize the existence of a novel clinical state of sepsis referred to as the “pre-shock” state, and that patients with sepsis who enter this state are highly likely to develop septic shock at some future time. We apply three different machine learning techniques to the electronic health record data of 15,930 patients in the MIMIC-III database to test this hypothesis. This novel paradigm yields improved performance in identifying patients with sepsis who will progress to septic shock, as defined by Sepsis- 3 criteria, with the best method achieving a 0.93 area under the receiver operating curve, 88{\%} sensitivity, 84{\%} specificity, and median early warning time of 7 hours. Additionally, we introduce the notion of patient-specific positive predictive value, assigning confidence to individual predictions, and achieving values as high as 91{\%}. This study demonstrates that early prediction of impending septic shock, and thus early intervention, is possible many hours in advance.",
author = "Ran Liu and Greenstein, {Joseph L.} and Granite, {Stephen J.} and Fackler, {James C} and Melania Bembea and Sarma, {Sridevi V.} and Raimond Winslow",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-42637-5",
language = "English (US)",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Data-driven discovery of a novel sepsis pre-shock state predicts impending septic shock in the ICU

AU - Liu, Ran

AU - Greenstein, Joseph L.

AU - Granite, Stephen J.

AU - Fackler, James C

AU - Bembea, Melania

AU - Sarma, Sridevi V.

AU - Winslow, Raimond

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Septic shock is a life-threatening condition in which timely treatment substantially reduces mortality. Reliable identification of patients with sepsis who are at elevated risk of developing septic shock therefore has the potential to save lives by opening an early window of intervention. We hypothesize the existence of a novel clinical state of sepsis referred to as the “pre-shock” state, and that patients with sepsis who enter this state are highly likely to develop septic shock at some future time. We apply three different machine learning techniques to the electronic health record data of 15,930 patients in the MIMIC-III database to test this hypothesis. This novel paradigm yields improved performance in identifying patients with sepsis who will progress to septic shock, as defined by Sepsis- 3 criteria, with the best method achieving a 0.93 area under the receiver operating curve, 88% sensitivity, 84% specificity, and median early warning time of 7 hours. Additionally, we introduce the notion of patient-specific positive predictive value, assigning confidence to individual predictions, and achieving values as high as 91%. This study demonstrates that early prediction of impending septic shock, and thus early intervention, is possible many hours in advance.

AB - Septic shock is a life-threatening condition in which timely treatment substantially reduces mortality. Reliable identification of patients with sepsis who are at elevated risk of developing septic shock therefore has the potential to save lives by opening an early window of intervention. We hypothesize the existence of a novel clinical state of sepsis referred to as the “pre-shock” state, and that patients with sepsis who enter this state are highly likely to develop septic shock at some future time. We apply three different machine learning techniques to the electronic health record data of 15,930 patients in the MIMIC-III database to test this hypothesis. This novel paradigm yields improved performance in identifying patients with sepsis who will progress to septic shock, as defined by Sepsis- 3 criteria, with the best method achieving a 0.93 area under the receiver operating curve, 88% sensitivity, 84% specificity, and median early warning time of 7 hours. Additionally, we introduce the notion of patient-specific positive predictive value, assigning confidence to individual predictions, and achieving values as high as 91%. This study demonstrates that early prediction of impending septic shock, and thus early intervention, is possible many hours in advance.

UR - http://www.scopus.com/inward/record.url?scp=85064569612&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064569612&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-42637-5

DO - 10.1038/s41598-019-42637-5

M3 - Article

C2 - 30992534

AN - SCOPUS:85064569612

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 6145

ER -