Abstract
It would be desirable before a surgical procedure to have a prediction rule that could accurately estimate the probability of a patient bleeding, need for blood transfusion, and other important outcomes. Such a prediction rule would allow optimal planning, more efficient use of blood bank resources, and identification of high-risk patient cohort for specific perioperative interventions. The goal of this study is to develop an efficient and accurate algorithm that could estimate the risk of multiple outcomes simultaneously. Specifically, a heterogeneous multi-task learning method is proposed for learning outcomes such as perioperative bleeding, intraoperative RBC transfusion, ICU care, and ICU length of stay. Additional outcomes not normally predicted are incorporated in the model for transfer learning and help improve the performance of relevant outcomes. Results for predicting perioperative bleeding and need for blood transfusion for patients undergoing non-cardiac operations from an institutional transfusion datamart show that the proposed method significantly increases AUC and G-Mean by more than 6% and 5% respectively over standard single-task learning methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Vivacqua, A., Koch, C.G., Yousuf, A.M., Nowicki, E.R., Houghtaling, P.L., Blackstone, E.H., Sabik III, J.F.: Morbidity of bleeding after cardiac surgery: is it blood transfusion, reoperation for bleeding, or both? The Annals of Thoracic Surgery 91(6), 1780–1790 (2011)
Zheng, F., Cammisa Jr., F.P., Sandhu, H.S., Girardi, F.P., Khan, S.N.: Factors predicting hospital stay, operative time, blood loss, and transfusion in patients undergoing revision posterior lumbar spine decompression, fusion, and segmental instrumentation. Spine 27(8), 818–824 (2002)
Kor, D.J., Stubbs, J.R., Gajic, O.: Perioperative coagulation management–fresh frozen plasma. Best Practice & Research Clinical Anaesthesiology 24(1), 51–64 (2010)
US Department of Health and Human Services and others: The 2009 national blood collection and utilization survey report. US Department of Health and Human Services, Office of the Assistant Secretary for Health, Washington, DC (2011)
Despotis, G., Avidan, M., Eby, C.: Prediction and management of bleeding in cardiac surgery. Journal of Thrombosis and Haemostasis 7(s1), 111–117 (2009)
Thomas, I.C., Sorrentino, M.J.: Bleeding risk prediction models in atrial fibrillation. Current Cardiology Reports 16(1), 1–8 (2014)
Caruana, R.: Multitask learning. Springer (1998)
Bakker, B., Heskes, T.: Task clustering and gating for bayesian multitask learning. The Journal of Machine Learning Research 4, 83–99 (2003)
Evgeniou, T., Pontil, M.: Regularized multi–task learning. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 109–117. ACM (2004)
Gong, P., Ye, J., Zhang, C.: Robust multi-task feature learning. In: Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 895–903. ACM (2012)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Transactions Knowledge and Data Engineering 22(10), 1345–1359 (2010)
Ngufor, C., Wojtusiak, J.: Extreme logistic regression. Advances in Data Analysis and Classification, 1–26 (2014)
Huang, G.B., Zhou, H., Ding, X., Zhang, R.: Extreme learning machine for regression and multiclass classification. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 42(2), 513–529 (2012)
Ngufor, C., Wojtusiak, J.: Learning from large-scale distributed health data: an approximate logistic regression approach. In: Proc. ICML 2013: Role of Machine Learning in Transforming Healthcare (2013)
Ngufor, C., Wojtusiak, J., Hooker, A., Oz, T., Hadley, J.: Extreme logistic regression: A large scale learning algorithm with application to prostate cancer mortality prediction. In: The Twenty-Seventh International Flairs Conference (2014)
Herasevich, V., Kor, D., Li, M., Pickering, B.: Icu data mart: a non-it approach. a team of clinicians, researchers and informatics personnel at the mayo clinic have taken a homegrown approach to building an icu data mart. Healthcare Informatics: the Business Magazine for Information and Communication Systems 28(11), 42–44 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Ngufor, C., Upadhyaya, S., Murphree, D., Madde, N., Kor, D., Pathak, J. (2015). A Heterogeneous Multi-Task Learning for Predicting RBC Transfusion and Perioperative Outcomes. In: Holmes, J., Bellazzi, R., Sacchi, L., Peek, N. (eds) Artificial Intelligence in Medicine. AIME 2015. Lecture Notes in Computer Science(), vol 9105. Springer, Cham. https://doi.org/10.1007/978-3-319-19551-3_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-19551-3_37
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19550-6
Online ISBN: 978-3-319-19551-3
eBook Packages: Computer ScienceComputer Science (R0)