Combining Biomarkers with EMR Data to Identify Patients in Different Phases of Sepsis

Ishan Taneja, Bobby Reddy, Gregory Damhorst, Sihai Dave Zhao, Umer Hassan, Zachary Price, Tor Jensen, Tanmay Ghonge, Manish Patel, Samuel Wachspress, Jake Winter, Michael Rappleye, Gillian Smith, Ryan Healey, Muhammad Ajmal, Muhammad Khan, Jay Patel, Harsh Rawal, Raiya Sarwar, Sumeet Soni & 6 others Syed Anwaruddin, Benjamin Davis, James Kumar, Karen White, Rashid Bashir, Ruoqing Zhu

Research output: Contribution to journalArticle

Abstract

Sepsis is a leading cause of death and is the most expensive condition to treat in U.S. hospitals. Despite targeted efforts to automate earlier detection of sepsis, current techniques rely exclusively on using either standard clinical data or novel biomarker measurements. In this study, we apply machine learning techniques to assess the predictive power of combining multiple biomarker measurements from a single blood sample with electronic medical record data (EMR) for the identification of patients in the early to peak phase of sepsis in a large community hospital setting. Combining biomarkers and EMR data achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.81, while EMR data alone achieved an AUC of 0.75. Furthermore, a single measurement of six biomarkers (IL-6, nCD64, IL-1ra, PCT, MCP1, and G-CSF) yielded the same predictive power as collecting an additional 16 hours of EMR data(AUC of 0.80), suggesting that the biomarkers may be useful for identifying these patients earlier. Ultimately, supervised learning using a subset of biomarker and EMR data as features may be capable of identifying patients in the early to peak phase of sepsis in a diverse population and may provide a tool for more timely identification and intervention.

Original languageEnglish (US)
Article number10800
JournalScientific Reports
Volume7
Issue number1
DOIs
StatePublished - Dec 1 2017

Fingerprint

Electronic Health Records
Sepsis
Biomarkers
Area Under Curve
Interleukin 1 Receptor Antagonist Protein
Community Hospital
Granulocyte Colony-Stimulating Factor
ROC Curve
Cause of Death
Interleukin-6
Learning
Population

ASJC Scopus subject areas

  • General

Cite this

Combining Biomarkers with EMR Data to Identify Patients in Different Phases of Sepsis. / Taneja, Ishan; Reddy, Bobby; Damhorst, Gregory; Zhao, Sihai Dave; Hassan, Umer; Price, Zachary; Jensen, Tor; Ghonge, Tanmay; Patel, Manish; Wachspress, Samuel; Winter, Jake; Rappleye, Michael; Smith, Gillian; Healey, Ryan; Ajmal, Muhammad; Khan, Muhammad; Patel, Jay; Rawal, Harsh; Sarwar, Raiya; Soni, Sumeet; Anwaruddin, Syed; Davis, Benjamin; Kumar, James; White, Karen; Bashir, Rashid; Zhu, Ruoqing.

In: Scientific Reports, Vol. 7, No. 1, 10800, 01.12.2017.

Research output: Contribution to journalArticle

Taneja, I, Reddy, B, Damhorst, G, Zhao, SD, Hassan, U, Price, Z, Jensen, T, Ghonge, T, Patel, M, Wachspress, S, Winter, J, Rappleye, M, Smith, G, Healey, R, Ajmal, M, Khan, M, Patel, J, Rawal, H, Sarwar, R, Soni, S, Anwaruddin, S, Davis, B, Kumar, J, White, K, Bashir, R & Zhu, R 2017, 'Combining Biomarkers with EMR Data to Identify Patients in Different Phases of Sepsis', Scientific Reports, vol. 7, no. 1, 10800. https://doi.org/10.1038/s41598-017-09766-1
Taneja, Ishan ; Reddy, Bobby ; Damhorst, Gregory ; Zhao, Sihai Dave ; Hassan, Umer ; Price, Zachary ; Jensen, Tor ; Ghonge, Tanmay ; Patel, Manish ; Wachspress, Samuel ; Winter, Jake ; Rappleye, Michael ; Smith, Gillian ; Healey, Ryan ; Ajmal, Muhammad ; Khan, Muhammad ; Patel, Jay ; Rawal, Harsh ; Sarwar, Raiya ; Soni, Sumeet ; Anwaruddin, Syed ; Davis, Benjamin ; Kumar, James ; White, Karen ; Bashir, Rashid ; Zhu, Ruoqing. / Combining Biomarkers with EMR Data to Identify Patients in Different Phases of Sepsis. In: Scientific Reports. 2017 ; Vol. 7, No. 1.
@article{762704619aed4fd29e79f99c83da6579,
title = "Combining Biomarkers with EMR Data to Identify Patients in Different Phases of Sepsis",
abstract = "Sepsis is a leading cause of death and is the most expensive condition to treat in U.S. hospitals. Despite targeted efforts to automate earlier detection of sepsis, current techniques rely exclusively on using either standard clinical data or novel biomarker measurements. In this study, we apply machine learning techniques to assess the predictive power of combining multiple biomarker measurements from a single blood sample with electronic medical record data (EMR) for the identification of patients in the early to peak phase of sepsis in a large community hospital setting. Combining biomarkers and EMR data achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.81, while EMR data alone achieved an AUC of 0.75. Furthermore, a single measurement of six biomarkers (IL-6, nCD64, IL-1ra, PCT, MCP1, and G-CSF) yielded the same predictive power as collecting an additional 16 hours of EMR data(AUC of 0.80), suggesting that the biomarkers may be useful for identifying these patients earlier. Ultimately, supervised learning using a subset of biomarker and EMR data as features may be capable of identifying patients in the early to peak phase of sepsis in a diverse population and may provide a tool for more timely identification and intervention.",
author = "Ishan Taneja and Bobby Reddy and Gregory Damhorst and Zhao, {Sihai Dave} and Umer Hassan and Zachary Price and Tor Jensen and Tanmay Ghonge and Manish Patel and Samuel Wachspress and Jake Winter and Michael Rappleye and Gillian Smith and Ryan Healey and Muhammad Ajmal and Muhammad Khan and Jay Patel and Harsh Rawal and Raiya Sarwar and Sumeet Soni and Syed Anwaruddin and Benjamin Davis and James Kumar and Karen White and Rashid Bashir and Ruoqing Zhu",
year = "2017",
month = "12",
day = "1",
doi = "10.1038/s41598-017-09766-1",
language = "English (US)",
volume = "7",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Combining Biomarkers with EMR Data to Identify Patients in Different Phases of Sepsis

AU - Taneja, Ishan

AU - Reddy, Bobby

AU - Damhorst, Gregory

AU - Zhao, Sihai Dave

AU - Hassan, Umer

AU - Price, Zachary

AU - Jensen, Tor

AU - Ghonge, Tanmay

AU - Patel, Manish

AU - Wachspress, Samuel

AU - Winter, Jake

AU - Rappleye, Michael

AU - Smith, Gillian

AU - Healey, Ryan

AU - Ajmal, Muhammad

AU - Khan, Muhammad

AU - Patel, Jay

AU - Rawal, Harsh

AU - Sarwar, Raiya

AU - Soni, Sumeet

AU - Anwaruddin, Syed

AU - Davis, Benjamin

AU - Kumar, James

AU - White, Karen

AU - Bashir, Rashid

AU - Zhu, Ruoqing

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Sepsis is a leading cause of death and is the most expensive condition to treat in U.S. hospitals. Despite targeted efforts to automate earlier detection of sepsis, current techniques rely exclusively on using either standard clinical data or novel biomarker measurements. In this study, we apply machine learning techniques to assess the predictive power of combining multiple biomarker measurements from a single blood sample with electronic medical record data (EMR) for the identification of patients in the early to peak phase of sepsis in a large community hospital setting. Combining biomarkers and EMR data achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.81, while EMR data alone achieved an AUC of 0.75. Furthermore, a single measurement of six biomarkers (IL-6, nCD64, IL-1ra, PCT, MCP1, and G-CSF) yielded the same predictive power as collecting an additional 16 hours of EMR data(AUC of 0.80), suggesting that the biomarkers may be useful for identifying these patients earlier. Ultimately, supervised learning using a subset of biomarker and EMR data as features may be capable of identifying patients in the early to peak phase of sepsis in a diverse population and may provide a tool for more timely identification and intervention.

AB - Sepsis is a leading cause of death and is the most expensive condition to treat in U.S. hospitals. Despite targeted efforts to automate earlier detection of sepsis, current techniques rely exclusively on using either standard clinical data or novel biomarker measurements. In this study, we apply machine learning techniques to assess the predictive power of combining multiple biomarker measurements from a single blood sample with electronic medical record data (EMR) for the identification of patients in the early to peak phase of sepsis in a large community hospital setting. Combining biomarkers and EMR data achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.81, while EMR data alone achieved an AUC of 0.75. Furthermore, a single measurement of six biomarkers (IL-6, nCD64, IL-1ra, PCT, MCP1, and G-CSF) yielded the same predictive power as collecting an additional 16 hours of EMR data(AUC of 0.80), suggesting that the biomarkers may be useful for identifying these patients earlier. Ultimately, supervised learning using a subset of biomarker and EMR data as features may be capable of identifying patients in the early to peak phase of sepsis in a diverse population and may provide a tool for more timely identification and intervention.

UR - http://www.scopus.com/inward/record.url?scp=85029125816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029125816&partnerID=8YFLogxK

U2 - 10.1038/s41598-017-09766-1

DO - 10.1038/s41598-017-09766-1

M3 - Article

VL - 7

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 10800

ER -