Multitask LS-Svm for Predicting Bleeding and Re-operation Due to Bleeding

Che Ngufor, Dennis H. Murphree, Sudhindra Upadhyaya, Jyotishman Pathak, Daryl J Kor

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

Abstract

Individualized blood transfusion management would benefit from the ability to prospectively identify patients at risk of complications of blood transfusion, and target them for closer monitoring or intervention. This study presents a simple and efficient multi-task learning method for predicting multiple surgical outcomes based on the weighted least squares support vector machine. To accelerate the training process, the input data is mapped onto a low dimensional randomized feature space leading to a simple linear system that can be solved with any existing fast linear or gradient based methods. Results for predicting early re-operation due to bleeding for patients undergoing non-cardiac operations from an institutional transfusion datamart illustrates that the method can reduce misclassification errors by as much as 13 compared to learning independent models. To further demonstrate the general applicability of the proposed method, a series of experiments are performed on synthetic data sets for scalability and on a real public data set for accuracy and robustness.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages56-65
Number of pages10
ISBN (Electronic)9781509048816
DOIs
StatePublished - Sep 8 2017
Event5th IEEE International Conference on Healthcare Informatics, ICHI 2017 - Park City, United States
Duration: Aug 23 2017Aug 26 2017

Other

Other5th IEEE International Conference on Healthcare Informatics, ICHI 2017
CountryUnited States
CityPark City
Period8/23/178/26/17

Fingerprint

Hemorrhage
Blood Transfusion
Learning
Aptitude
Least-Squares Analysis
Datasets
Support Vector Machine

Keywords

  • Multi-task learning
  • Robust estimation
  • Support Vector Machine
  • Transfusion

ASJC Scopus subject areas

  • Health Informatics

Cite this

Ngufor, C., Murphree, D. H., Upadhyaya, S., Pathak, J., & Kor, D. J. (2017). Multitask LS-Svm for Predicting Bleeding and Re-operation Due to Bleeding. In Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017 (pp. 56-65). [8031132] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI.2017.101

Multitask LS-Svm for Predicting Bleeding and Re-operation Due to Bleeding. / Ngufor, Che; Murphree, Dennis H.; Upadhyaya, Sudhindra; Pathak, Jyotishman; Kor, Daryl J.

Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 56-65 8031132.

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

Ngufor, C, Murphree, DH, Upadhyaya, S, Pathak, J & Kor, DJ 2017, Multitask LS-Svm for Predicting Bleeding and Re-operation Due to Bleeding. in Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017., 8031132, Institute of Electrical and Electronics Engineers Inc., pp. 56-65, 5th IEEE International Conference on Healthcare Informatics, ICHI 2017, Park City, United States, 8/23/17. https://doi.org/10.1109/ICHI.2017.101
Ngufor C, Murphree DH, Upadhyaya S, Pathak J, Kor DJ. Multitask LS-Svm for Predicting Bleeding and Re-operation Due to Bleeding. In Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 56-65. 8031132 https://doi.org/10.1109/ICHI.2017.101
Ngufor, Che ; Murphree, Dennis H. ; Upadhyaya, Sudhindra ; Pathak, Jyotishman ; Kor, Daryl J. / Multitask LS-Svm for Predicting Bleeding and Re-operation Due to Bleeding. Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 56-65
@inproceedings{1bec54e6d4144ac08b02449b3628b9fb,
title = "Multitask LS-Svm for Predicting Bleeding and Re-operation Due to Bleeding",
abstract = "Individualized blood transfusion management would benefit from the ability to prospectively identify patients at risk of complications of blood transfusion, and target them for closer monitoring or intervention. This study presents a simple and efficient multi-task learning method for predicting multiple surgical outcomes based on the weighted least squares support vector machine. To accelerate the training process, the input data is mapped onto a low dimensional randomized feature space leading to a simple linear system that can be solved with any existing fast linear or gradient based methods. Results for predicting early re-operation due to bleeding for patients undergoing non-cardiac operations from an institutional transfusion datamart illustrates that the method can reduce misclassification errors by as much as 13 compared to learning independent models. To further demonstrate the general applicability of the proposed method, a series of experiments are performed on synthetic data sets for scalability and on a real public data set for accuracy and robustness.",
keywords = "Multi-task learning, Robust estimation, Support Vector Machine, Transfusion",
author = "Che Ngufor and Murphree, {Dennis H.} and Sudhindra Upadhyaya and Jyotishman Pathak and Kor, {Daryl J}",
year = "2017",
month = "9",
day = "8",
doi = "10.1109/ICHI.2017.101",
language = "English (US)",
pages = "56--65",
booktitle = "Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Multitask LS-Svm for Predicting Bleeding and Re-operation Due to Bleeding

AU - Ngufor, Che

AU - Murphree, Dennis H.

AU - Upadhyaya, Sudhindra

AU - Pathak, Jyotishman

AU - Kor, Daryl J

PY - 2017/9/8

Y1 - 2017/9/8

N2 - Individualized blood transfusion management would benefit from the ability to prospectively identify patients at risk of complications of blood transfusion, and target them for closer monitoring or intervention. This study presents a simple and efficient multi-task learning method for predicting multiple surgical outcomes based on the weighted least squares support vector machine. To accelerate the training process, the input data is mapped onto a low dimensional randomized feature space leading to a simple linear system that can be solved with any existing fast linear or gradient based methods. Results for predicting early re-operation due to bleeding for patients undergoing non-cardiac operations from an institutional transfusion datamart illustrates that the method can reduce misclassification errors by as much as 13 compared to learning independent models. To further demonstrate the general applicability of the proposed method, a series of experiments are performed on synthetic data sets for scalability and on a real public data set for accuracy and robustness.

AB - Individualized blood transfusion management would benefit from the ability to prospectively identify patients at risk of complications of blood transfusion, and target them for closer monitoring or intervention. This study presents a simple and efficient multi-task learning method for predicting multiple surgical outcomes based on the weighted least squares support vector machine. To accelerate the training process, the input data is mapped onto a low dimensional randomized feature space leading to a simple linear system that can be solved with any existing fast linear or gradient based methods. Results for predicting early re-operation due to bleeding for patients undergoing non-cardiac operations from an institutional transfusion datamart illustrates that the method can reduce misclassification errors by as much as 13 compared to learning independent models. To further demonstrate the general applicability of the proposed method, a series of experiments are performed on synthetic data sets for scalability and on a real public data set for accuracy and robustness.

KW - Multi-task learning

KW - Robust estimation

KW - Support Vector Machine

KW - Transfusion

UR - http://www.scopus.com/inward/record.url?scp=85032382124&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032382124&partnerID=8YFLogxK

U2 - 10.1109/ICHI.2017.101

DO - 10.1109/ICHI.2017.101

M3 - Conference contribution

AN - SCOPUS:85032382124

SP - 56

EP - 65

BT - Proceedings - 2017 IEEE International Conference on Healthcare Informatics, ICHI 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -