Predicting adverse reactions to blood transfusion

Dennis H. Murphree, Leanne Clifford, Yaxiong Lin, Nagesh Madde, Che Ngufor, Sudhindra Upadhyaya, Jyotishman Pathak, Daryl J Kor

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

2 Citations (Scopus)

Abstract

In 2011 approximately 21 million blood components were transfused in the United States, with roughly 1 in 414 causing an adverse reaction [1]. Two adverse reactions in particular, transfusion-related acute lung injury (TRALI) and transfusion-associated circulatory overload (TACO), accounted for 62% of reported transfusion-related fatalities in 2013 [2]. We describe newly developed models for predicting the likelihood of these adverse reactions, with a goal towards better informing the clinician prior to a transfusion decision. Our models include both traditional logistic regression as well as modern machine learning techniques, and incorporate over sampling methods to deal with severe class imbalance. We focus on a minimal set of predictors in order to maximize potential application. Results from 8 models demonstrate AUC's ranging from 0.72 to 0.84, with sensitivities tunable by threshold choice across ranges up to 0.93. Many of the models rank the same predictors amongst the most important, perhaps yielding insight into the mechanisms underlying TRALI and TACO. These models are currently being implemented in a Clinical Decision Support System [3] in perioperative environments at Mayo Clinic.

Original languageEnglish (US)
Title of host publicationProceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages82-89
Number of pages8
ISBN (Print)9781467395489
DOIs
StatePublished - Dec 8 2015
Event3rd IEEE International Conference on Healthcare Informatics, ICHI 2015 - Dallas, United States
Duration: Oct 21 2015Oct 23 2015

Other

Other3rd IEEE International Conference on Healthcare Informatics, ICHI 2015
CountryUnited States
CityDallas
Period10/21/1510/23/15

Fingerprint

Acute Lung Injury
Blood Transfusion
Clinical Decision Support Systems
Area Under Curve
Logistic Models
Machine Learning

Keywords

  • Adverse reaction
  • Logistic regression
  • Machine learning
  • Risk prediction
  • Transfusion
  • Transfusion-associated circulatory overload
  • Transfusion-related acute lung injury

ASJC Scopus subject areas

  • Health Informatics

Cite this

Murphree, D. H., Clifford, L., Lin, Y., Madde, N., Ngufor, C., Upadhyaya, S., ... Kor, D. J. (2015). Predicting adverse reactions to blood transfusion. In Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015 (pp. 82-89). [7349678] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI.2015.17

Predicting adverse reactions to blood transfusion. / Murphree, Dennis H.; Clifford, Leanne; Lin, Yaxiong; Madde, Nagesh; Ngufor, Che; Upadhyaya, Sudhindra; Pathak, Jyotishman; Kor, Daryl J.

Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 82-89 7349678.

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

Murphree, DH, Clifford, L, Lin, Y, Madde, N, Ngufor, C, Upadhyaya, S, Pathak, J & Kor, DJ 2015, Predicting adverse reactions to blood transfusion. in Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015., 7349678, Institute of Electrical and Electronics Engineers Inc., pp. 82-89, 3rd IEEE International Conference on Healthcare Informatics, ICHI 2015, Dallas, United States, 10/21/15. https://doi.org/10.1109/ICHI.2015.17
Murphree DH, Clifford L, Lin Y, Madde N, Ngufor C, Upadhyaya S et al. Predicting adverse reactions to blood transfusion. In Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 82-89. 7349678 https://doi.org/10.1109/ICHI.2015.17
Murphree, Dennis H. ; Clifford, Leanne ; Lin, Yaxiong ; Madde, Nagesh ; Ngufor, Che ; Upadhyaya, Sudhindra ; Pathak, Jyotishman ; Kor, Daryl J. / Predicting adverse reactions to blood transfusion. Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 82-89
@inproceedings{8c3a058fee084bfa81425a95ea2b0b81,
title = "Predicting adverse reactions to blood transfusion",
abstract = "In 2011 approximately 21 million blood components were transfused in the United States, with roughly 1 in 414 causing an adverse reaction [1]. Two adverse reactions in particular, transfusion-related acute lung injury (TRALI) and transfusion-associated circulatory overload (TACO), accounted for 62{\%} of reported transfusion-related fatalities in 2013 [2]. We describe newly developed models for predicting the likelihood of these adverse reactions, with a goal towards better informing the clinician prior to a transfusion decision. Our models include both traditional logistic regression as well as modern machine learning techniques, and incorporate over sampling methods to deal with severe class imbalance. We focus on a minimal set of predictors in order to maximize potential application. Results from 8 models demonstrate AUC's ranging from 0.72 to 0.84, with sensitivities tunable by threshold choice across ranges up to 0.93. Many of the models rank the same predictors amongst the most important, perhaps yielding insight into the mechanisms underlying TRALI and TACO. These models are currently being implemented in a Clinical Decision Support System [3] in perioperative environments at Mayo Clinic.",
keywords = "Adverse reaction, Logistic regression, Machine learning, Risk prediction, Transfusion, Transfusion-associated circulatory overload, Transfusion-related acute lung injury",
author = "Murphree, {Dennis H.} and Leanne Clifford and Yaxiong Lin and Nagesh Madde and Che Ngufor and Sudhindra Upadhyaya and Jyotishman Pathak and Kor, {Daryl J}",
year = "2015",
month = "12",
day = "8",
doi = "10.1109/ICHI.2015.17",
language = "English (US)",
isbn = "9781467395489",
pages = "82--89",
booktitle = "Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Predicting adverse reactions to blood transfusion

AU - Murphree, Dennis H.

AU - Clifford, Leanne

AU - Lin, Yaxiong

AU - Madde, Nagesh

AU - Ngufor, Che

AU - Upadhyaya, Sudhindra

AU - Pathak, Jyotishman

AU - Kor, Daryl J

PY - 2015/12/8

Y1 - 2015/12/8

N2 - In 2011 approximately 21 million blood components were transfused in the United States, with roughly 1 in 414 causing an adverse reaction [1]. Two adverse reactions in particular, transfusion-related acute lung injury (TRALI) and transfusion-associated circulatory overload (TACO), accounted for 62% of reported transfusion-related fatalities in 2013 [2]. We describe newly developed models for predicting the likelihood of these adverse reactions, with a goal towards better informing the clinician prior to a transfusion decision. Our models include both traditional logistic regression as well as modern machine learning techniques, and incorporate over sampling methods to deal with severe class imbalance. We focus on a minimal set of predictors in order to maximize potential application. Results from 8 models demonstrate AUC's ranging from 0.72 to 0.84, with sensitivities tunable by threshold choice across ranges up to 0.93. Many of the models rank the same predictors amongst the most important, perhaps yielding insight into the mechanisms underlying TRALI and TACO. These models are currently being implemented in a Clinical Decision Support System [3] in perioperative environments at Mayo Clinic.

AB - In 2011 approximately 21 million blood components were transfused in the United States, with roughly 1 in 414 causing an adverse reaction [1]. Two adverse reactions in particular, transfusion-related acute lung injury (TRALI) and transfusion-associated circulatory overload (TACO), accounted for 62% of reported transfusion-related fatalities in 2013 [2]. We describe newly developed models for predicting the likelihood of these adverse reactions, with a goal towards better informing the clinician prior to a transfusion decision. Our models include both traditional logistic regression as well as modern machine learning techniques, and incorporate over sampling methods to deal with severe class imbalance. We focus on a minimal set of predictors in order to maximize potential application. Results from 8 models demonstrate AUC's ranging from 0.72 to 0.84, with sensitivities tunable by threshold choice across ranges up to 0.93. Many of the models rank the same predictors amongst the most important, perhaps yielding insight into the mechanisms underlying TRALI and TACO. These models are currently being implemented in a Clinical Decision Support System [3] in perioperative environments at Mayo Clinic.

KW - Adverse reaction

KW - Logistic regression

KW - Machine learning

KW - Risk prediction

KW - Transfusion

KW - Transfusion-associated circulatory overload

KW - Transfusion-related acute lung injury

UR - http://www.scopus.com/inward/record.url?scp=84966318579&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966318579&partnerID=8YFLogxK

U2 - 10.1109/ICHI.2015.17

DO - 10.1109/ICHI.2015.17

M3 - Conference contribution

AN - SCOPUS:84966318579

SN - 9781467395489

SP - 82

EP - 89

BT - Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -