Machine learning methods for septic shock prediction

Aiman Darwiche; Sumitra Mukherjee

doi:10.1145/3293663.3293673

Machine learning methods for septic shock prediction

Aiman Darwiche
, Sumitra Mukherjee

Nova Southeastern University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Scopus citations

Abstract

Sepsis is an organ dysfunction life-threatening disease that is caused by a dysregulated body response to infection. Sepsis is difficult to detect at an early stage, and when not detected early, is difficult to treat and results in high mortality rates. Developing improved methods for identifying patients in high risk of suffering septic shock has been the focus of much research in recent years. This paper develops an improved method for septic shock prediction. Using the data from the MMIC-III database, an ensemble classifier is trained to identify high-risk patients. A robust prediction model is built by obtaining a risk score from fitting the Cox Hazard model on multiple input features. The score is added to the list of features and the Random Forest ensemble classifier is trained to produce the model. The Cox Enhanced Random Forest (CERF) proposed method is evaluated by comparing its predictive accuracy to those of extant methods.

Original language	English
Title of host publication	AIVR 2018 - 2018 International Conference on Artificial Intelligence and Virtual Reality
Publisher	Association for Computing Machinery (ACM)
Pages	104-110
Number of pages	7
ISBN (Electronic)	9781450366410
DOIs	https://doi.org/10.1145/3293663.3293673
State	Published - Nov 23 2018
Event	2018 International Conference on Artificial Intelligence and Virtual Reality, AIVR 2018 - Nagoya, Japan Duration: Nov 23 2018 → Nov 25 2018

Publication series

Name	Proceedings of the 2018 International Conference on Artificial Intelligence and Virtual Reality

Conference

Conference	2018 International Conference on Artificial Intelligence and Virtual Reality, AIVR 2018
Country/Territory	Japan
City	Nagoya
Period	11/23/18 → 11/25/18

Bibliographical note

Publisher Copyright:
© 2018 Association for Computing Machinery.

ASJC Scopus Subject Areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Keywords

Classification
Cox hazards model
Ensemble classifier
Machine learning
Prediction
Random forests
Sepsis
Septic shock

Access to Document

10.1145/3293663.3293673

Cite this

Darwiche, A., & Mukherjee, S. (2018). Machine learning methods for septic shock prediction. In AIVR 2018 - 2018 International Conference on Artificial Intelligence and Virtual Reality (pp. 104-110). (Proceedings of the 2018 International Conference on Artificial Intelligence and Virtual Reality). Association for Computing Machinery (ACM). https://doi.org/10.1145/3293663.3293673

Machine learning methods for septic shock prediction. / Darwiche, Aiman; Mukherjee, Sumitra.
AIVR 2018 - 2018 International Conference on Artificial Intelligence and Virtual Reality. Association for Computing Machinery (ACM), 2018. p. 104-110 (Proceedings of the 2018 International Conference on Artificial Intelligence and Virtual Reality).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Darwiche, A & Mukherjee, S 2018, Machine learning methods for septic shock prediction. in AIVR 2018 - 2018 International Conference on Artificial Intelligence and Virtual Reality. Proceedings of the 2018 International Conference on Artificial Intelligence and Virtual Reality, Association for Computing Machinery (ACM), pp. 104-110, 2018 International Conference on Artificial Intelligence and Virtual Reality, AIVR 2018, Nagoya, Japan, 11/23/18. https://doi.org/10.1145/3293663.3293673

@inproceedings{93fba9b93b134f9ea8b9ed23b34fc988,

title = "Machine learning methods for septic shock prediction",

abstract = "Sepsis is an organ dysfunction life-threatening disease that is caused by a dysregulated body response to infection. Sepsis is difficult to detect at an early stage, and when not detected early, is difficult to treat and results in high mortality rates. Developing improved methods for identifying patients in high risk of suffering septic shock has been the focus of much research in recent years. This paper develops an improved method for septic shock prediction. Using the data from the MMIC-III database, an ensemble classifier is trained to identify high-risk patients. A robust prediction model is built by obtaining a risk score from fitting the Cox Hazard model on multiple input features. The score is added to the list of features and the Random Forest ensemble classifier is trained to produce the model. The Cox Enhanced Random Forest (CERF) proposed method is evaluated by comparing its predictive accuracy to those of extant methods. ",

keywords = "Classification, Cox hazards model, Ensemble classifier, Machine learning, Prediction, Random forests, Sepsis, Septic shock",

author = "Aiman Darwiche and Sumitra Mukherjee",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 2018 International Conference on Artificial Intelligence and Virtual Reality, AIVR 2018 ; Conference date: 23-11-2018 Through 25-11-2018",

year = "2018",

month = nov,

day = "23",

doi = "10.1145/3293663.3293673",

language = "English",

series = "Proceedings of the 2018 International Conference on Artificial Intelligence and Virtual Reality",

publisher = "Association for Computing Machinery (ACM)",

pages = "104--110",

booktitle = "AIVR 2018 - 2018 International Conference on Artificial Intelligence and Virtual Reality",

}

TY - GEN

T1 - Machine learning methods for septic shock prediction

AU - Darwiche, Aiman

AU - Mukherjee, Sumitra

PY - 2018/11/23

Y1 - 2018/11/23

N2 - Sepsis is an organ dysfunction life-threatening disease that is caused by a dysregulated body response to infection. Sepsis is difficult to detect at an early stage, and when not detected early, is difficult to treat and results in high mortality rates. Developing improved methods for identifying patients in high risk of suffering septic shock has been the focus of much research in recent years. This paper develops an improved method for septic shock prediction. Using the data from the MMIC-III database, an ensemble classifier is trained to identify high-risk patients. A robust prediction model is built by obtaining a risk score from fitting the Cox Hazard model on multiple input features. The score is added to the list of features and the Random Forest ensemble classifier is trained to produce the model. The Cox Enhanced Random Forest (CERF) proposed method is evaluated by comparing its predictive accuracy to those of extant methods.

AB - Sepsis is an organ dysfunction life-threatening disease that is caused by a dysregulated body response to infection. Sepsis is difficult to detect at an early stage, and when not detected early, is difficult to treat and results in high mortality rates. Developing improved methods for identifying patients in high risk of suffering septic shock has been the focus of much research in recent years. This paper develops an improved method for septic shock prediction. Using the data from the MMIC-III database, an ensemble classifier is trained to identify high-risk patients. A robust prediction model is built by obtaining a risk score from fitting the Cox Hazard model on multiple input features. The score is added to the list of features and the Random Forest ensemble classifier is trained to produce the model. The Cox Enhanced Random Forest (CERF) proposed method is evaluated by comparing its predictive accuracy to those of extant methods.

KW - Classification

KW - Cox hazards model

KW - Ensemble classifier

KW - Machine learning

KW - Prediction

KW - Random forests

KW - Sepsis

KW - Septic shock

UR - https://www.scopus.com/pages/publications/85062796485

UR - https://www.scopus.com/pages/publications/85062796485#tab=citedBy

U2 - 10.1145/3293663.3293673

DO - 10.1145/3293663.3293673

M3 - Conference contribution

AN - SCOPUS:85062796485

T3 - Proceedings of the 2018 International Conference on Artificial Intelligence and Virtual Reality

SP - 104

EP - 110

BT - AIVR 2018 - 2018 International Conference on Artificial Intelligence and Virtual Reality

PB - Association for Computing Machinery (ACM)

T2 - 2018 International Conference on Artificial Intelligence and Virtual Reality, AIVR 2018

Y2 - 23 November 2018 through 25 November 2018

ER -

Machine learning methods for septic shock prediction

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this