skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A minimal set of physiomarkers in continuous high frequency data streams predict adult sepsis onset earlier

Abstract

Purpose: We report that sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. To improve short- and long-term outcomes, it is critical to detect at-risk sepsis patients at an early stage.Methods: A data-set consisting of high-frequency physiological data from 1161 critically ill patients was analyzed. 377 patients had developed sepsis, and had data at least 3 h prior to the onset of sepsis. A random forest classifier was trained to discriminate between sepsis and non-sepsis patients in real-time using a total of 132 features extracted from a moving time-window. The model was trained on 80% of the patients and was tested on the remaining 20% of the patients, for two observational periods of lengths 3 and 6 h prior to onset.Results: The model that used continuous physiological data alone resulted in sensitivity and F1 score of up to 80% and 67% one hour before sepsis onset. On average, these models were able to predict sepsis 294.19 ± 6.50 min (5 h) before the onset.Conclusions: Lastly, the use of machine learning algorithms on continuous streams of physiological data can allow for early identification of at-risk patients in real-time with high accuracy.

Authors:
 [1]; ORCiD logo [1];  [2];  [3];  [2]; ORCiD logo [2]
  1. Univ. of Tennessee, Knoxville, TN (United States)
  2. University of Tennessee Health, Memphis, TN (United States)
  3. Univ. of Tennessee, Knoxville, TN (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1502531
Grant/Contract Number:  
AC05-00OR22725
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
International Journal of Medical Informatics
Additional Journal Information:
Journal Volume: 122; Journal Issue: C; Journal ID: ISSN 1386-5056
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; 97 MATHEMATICS AND COMPUTING; 59 BASIC BIOLOGICAL SCIENCES

Citation Formats

van Wyk, Franco, Khojandi, Anahita, Mohammed, Akram, Begoli, Edmon, Davis, Robert L., and Kamaleswaran, Rishikesan. A minimal set of physiomarkers in continuous high frequency data streams predict adult sepsis onset earlier. United States: N. p., 2018. Web. doi:10.1016/j.ijmedinf.2018.12.002.
van Wyk, Franco, Khojandi, Anahita, Mohammed, Akram, Begoli, Edmon, Davis, Robert L., & Kamaleswaran, Rishikesan. A minimal set of physiomarkers in continuous high frequency data streams predict adult sepsis onset earlier. United States. doi:10.1016/j.ijmedinf.2018.12.002.
van Wyk, Franco, Khojandi, Anahita, Mohammed, Akram, Begoli, Edmon, Davis, Robert L., and Kamaleswaran, Rishikesan. Mon . "A minimal set of physiomarkers in continuous high frequency data streams predict adult sepsis onset earlier". United States. doi:10.1016/j.ijmedinf.2018.12.002.
@article{osti_1502531,
title = {A minimal set of physiomarkers in continuous high frequency data streams predict adult sepsis onset earlier},
author = {van Wyk, Franco and Khojandi, Anahita and Mohammed, Akram and Begoli, Edmon and Davis, Robert L. and Kamaleswaran, Rishikesan},
abstractNote = {Purpose: We report that sepsis is a life-threatening condition with high mortality rates and expensive treatment costs. To improve short- and long-term outcomes, it is critical to detect at-risk sepsis patients at an early stage.Methods: A data-set consisting of high-frequency physiological data from 1161 critically ill patients was analyzed. 377 patients had developed sepsis, and had data at least 3 h prior to the onset of sepsis. A random forest classifier was trained to discriminate between sepsis and non-sepsis patients in real-time using a total of 132 features extracted from a moving time-window. The model was trained on 80% of the patients and was tested on the remaining 20% of the patients, for two observational periods of lengths 3 and 6 h prior to onset.Results: The model that used continuous physiological data alone resulted in sensitivity and F1 score of up to 80% and 67% one hour before sepsis onset. On average, these models were able to predict sepsis 294.19 ± 6.50 min (5 h) before the onset.Conclusions: Lastly, the use of machine learning algorithms on continuous streams of physiological data can allow for early identification of at-risk patients in real-time with high accuracy.},
doi = {10.1016/j.ijmedinf.2018.12.002},
journal = {International Journal of Medical Informatics},
issn = {1386-5056},
number = C,
volume = 122,
place = {United States},
year = {2018},
month = {12}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on December 10, 2019
Publisher's Version of Record

Save / Share: