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.
N1 - Publisher Copyright:
© 2015 IEEE.
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
T3 - Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015
SP - 82
EP - 89
BT - Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015
A2 - Fu, Wai-Tat
A2 - Balakrishnan, Prabhakaran
A2 - Harabagiu, Sanda
A2 - Wang, Fei
A2 - Srivatsava, Jaideep
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd IEEE International Conference on Healthcare Informatics, ICHI 2015
Y2 - 21 October 2015 through 23 October 2015
ER -