Effects of Plasma Transfusion on Perioperative Bleeding Complications: A Machine Learning Approach

Che Ngufor, Dennis Murphree, Sudhindra Upadhyaya, Nageswar Madde, Daryl J Kor, Jyotishman Pathak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Perioperative bleeding (PB) is associated with increased patient morbidity and mortality, and results in substantial health care resource utilization. To assess bleeding risk, a routine practice in most centers is to use indicators such as elevated values of the International Normalized Ratio (INR). For patients with elevated INR, the routine therapy option is plasma transfusion. However, the predictive accuracy of INR and the value of plasma transfusion still remains unclear. Accurate methods are therefore needed to identify early the patients with increased risk of bleeding. The goal of this work is to apply advanced machine learning methods to study the relationship between preoperative plasma transfusion (PPT) and PB in patients with elevated INR undergoing noncardiac surgery. The problem is cast under the framework of causal inference where robust meaningful measures to quantify the effect of PPT on PB are estimated. Results show that both machine learning and standard statistical methods generally agree that PPT negatively impacts PB and other important patient outcomes. However, machine learning methods show significant results, and machine learning boosting methods are found to make less errors in predicting PB.

Original languageEnglish (US)
Title of host publicationStudies in Health Technology and Informatics
PublisherIOS Press
Pages721-725
Number of pages5
Volume216
ISBN (Print)9781614995630
DOIs
StatePublished - 2015
Event15th World Congress on Health and Biomedical Informatics, MEDINFO 2015 - Sao Paulo, Brazil
Duration: Aug 19 2015Aug 23 2015

Publication series

NameStudies in Health Technology and Informatics
Volume216
ISSN (Print)09269630
ISSN (Electronic)18798365

Other

Other15th World Congress on Health and Biomedical Informatics, MEDINFO 2015
CountryBrazil
CitySao Paulo
Period8/19/158/23/15

Fingerprint

Learning systems
Hemorrhage
International Normalized Ratio
Plasmas
Patient Acceptance of Health Care
Health care
Surgery
Statistical methods
Health Resources
Machine Learning
Morbidity
Mortality

Keywords

  • Bleeding
  • Blood Transfusion
  • Classification
  • Electronic Health Records
  • Machine Learning
  • Treatment Effect

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Ngufor, C., Murphree, D., Upadhyaya, S., Madde, N., Kor, D. J., & Pathak, J. (2015). Effects of Plasma Transfusion on Perioperative Bleeding Complications: A Machine Learning Approach. In Studies in Health Technology and Informatics (Vol. 216, pp. 721-725). (Studies in Health Technology and Informatics; Vol. 216). IOS Press. https://doi.org/10.3233/978-1-61499-564-7-721

Effects of Plasma Transfusion on Perioperative Bleeding Complications : A Machine Learning Approach. / Ngufor, Che; Murphree, Dennis; Upadhyaya, Sudhindra; Madde, Nageswar; Kor, Daryl J; Pathak, Jyotishman.

Studies in Health Technology and Informatics. Vol. 216 IOS Press, 2015. p. 721-725 (Studies in Health Technology and Informatics; Vol. 216).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ngufor, C, Murphree, D, Upadhyaya, S, Madde, N, Kor, DJ & Pathak, J 2015, Effects of Plasma Transfusion on Perioperative Bleeding Complications: A Machine Learning Approach. in Studies in Health Technology and Informatics. vol. 216, Studies in Health Technology and Informatics, vol. 216, IOS Press, pp. 721-725, 15th World Congress on Health and Biomedical Informatics, MEDINFO 2015, Sao Paulo, Brazil, 8/19/15. https://doi.org/10.3233/978-1-61499-564-7-721
Ngufor C, Murphree D, Upadhyaya S, Madde N, Kor DJ, Pathak J. Effects of Plasma Transfusion on Perioperative Bleeding Complications: A Machine Learning Approach. In Studies in Health Technology and Informatics. Vol. 216. IOS Press. 2015. p. 721-725. (Studies in Health Technology and Informatics). https://doi.org/10.3233/978-1-61499-564-7-721
Ngufor, Che ; Murphree, Dennis ; Upadhyaya, Sudhindra ; Madde, Nageswar ; Kor, Daryl J ; Pathak, Jyotishman. / Effects of Plasma Transfusion on Perioperative Bleeding Complications : A Machine Learning Approach. Studies in Health Technology and Informatics. Vol. 216 IOS Press, 2015. pp. 721-725 (Studies in Health Technology and Informatics).
@inproceedings{65fe16440f384450983f5247faec95d5,
title = "Effects of Plasma Transfusion on Perioperative Bleeding Complications: A Machine Learning Approach",
abstract = "Perioperative bleeding (PB) is associated with increased patient morbidity and mortality, and results in substantial health care resource utilization. To assess bleeding risk, a routine practice in most centers is to use indicators such as elevated values of the International Normalized Ratio (INR). For patients with elevated INR, the routine therapy option is plasma transfusion. However, the predictive accuracy of INR and the value of plasma transfusion still remains unclear. Accurate methods are therefore needed to identify early the patients with increased risk of bleeding. The goal of this work is to apply advanced machine learning methods to study the relationship between preoperative plasma transfusion (PPT) and PB in patients with elevated INR undergoing noncardiac surgery. The problem is cast under the framework of causal inference where robust meaningful measures to quantify the effect of PPT on PB are estimated. Results show that both machine learning and standard statistical methods generally agree that PPT negatively impacts PB and other important patient outcomes. However, machine learning methods show significant results, and machine learning boosting methods are found to make less errors in predicting PB.",
keywords = "Bleeding, Blood Transfusion, Classification, Electronic Health Records, Machine Learning, Treatment Effect",
author = "Che Ngufor and Dennis Murphree and Sudhindra Upadhyaya and Nageswar Madde and Kor, {Daryl J} and Jyotishman Pathak",
year = "2015",
doi = "10.3233/978-1-61499-564-7-721",
language = "English (US)",
isbn = "9781614995630",
volume = "216",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press",
pages = "721--725",
booktitle = "Studies in Health Technology and Informatics",

}

TY - GEN

T1 - Effects of Plasma Transfusion on Perioperative Bleeding Complications

T2 - A Machine Learning Approach

AU - Ngufor, Che

AU - Murphree, Dennis

AU - Upadhyaya, Sudhindra

AU - Madde, Nageswar

AU - Kor, Daryl J

AU - Pathak, Jyotishman

PY - 2015

Y1 - 2015

N2 - Perioperative bleeding (PB) is associated with increased patient morbidity and mortality, and results in substantial health care resource utilization. To assess bleeding risk, a routine practice in most centers is to use indicators such as elevated values of the International Normalized Ratio (INR). For patients with elevated INR, the routine therapy option is plasma transfusion. However, the predictive accuracy of INR and the value of plasma transfusion still remains unclear. Accurate methods are therefore needed to identify early the patients with increased risk of bleeding. The goal of this work is to apply advanced machine learning methods to study the relationship between preoperative plasma transfusion (PPT) and PB in patients with elevated INR undergoing noncardiac surgery. The problem is cast under the framework of causal inference where robust meaningful measures to quantify the effect of PPT on PB are estimated. Results show that both machine learning and standard statistical methods generally agree that PPT negatively impacts PB and other important patient outcomes. However, machine learning methods show significant results, and machine learning boosting methods are found to make less errors in predicting PB.

AB - Perioperative bleeding (PB) is associated with increased patient morbidity and mortality, and results in substantial health care resource utilization. To assess bleeding risk, a routine practice in most centers is to use indicators such as elevated values of the International Normalized Ratio (INR). For patients with elevated INR, the routine therapy option is plasma transfusion. However, the predictive accuracy of INR and the value of plasma transfusion still remains unclear. Accurate methods are therefore needed to identify early the patients with increased risk of bleeding. The goal of this work is to apply advanced machine learning methods to study the relationship between preoperative plasma transfusion (PPT) and PB in patients with elevated INR undergoing noncardiac surgery. The problem is cast under the framework of causal inference where robust meaningful measures to quantify the effect of PPT on PB are estimated. Results show that both machine learning and standard statistical methods generally agree that PPT negatively impacts PB and other important patient outcomes. However, machine learning methods show significant results, and machine learning boosting methods are found to make less errors in predicting PB.

KW - Bleeding

KW - Blood Transfusion

KW - Classification

KW - Electronic Health Records

KW - Machine Learning

KW - Treatment Effect

UR - http://www.scopus.com/inward/record.url?scp=84951986793&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951986793&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-564-7-721

DO - 10.3233/978-1-61499-564-7-721

M3 - Conference contribution

C2 - 26262146

AN - SCOPUS:84951986793

SN - 9781614995630

VL - 216

T3 - Studies in Health Technology and Informatics

SP - 721

EP - 725

BT - Studies in Health Technology and Informatics

PB - IOS Press

ER -