Learning Tasks for Multitask Learning
Author(s)
Suresh, Harini; Gong, Jen J.; Guttag, John V.
DownloadSubmitted version (779.2Kb)
Open Access Policy
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Alternative title
Heterogenous Patient Populations in the ICU
Terms of use
Metadata
Show full item recordAbstract
© 2018 Copyright held by the owner/author(s). Machine learning approaches have been effective in predicting adverse outcomes in different clinical settings. These models are often developed and evaluated on datasets with heterogeneous patient populations. However, good predictive performance on the aggregate population does not imply good performance for specific groups. In this work, we present a two-step framework to 1) learn relevant patient subgroups, and 2) predict an outcome for separate patient populations in a multi-task framework, where each population is a separate task. We demonstrate how to discover relevant groups in an unsupervised way with a sequence-to-sequence autoencoder. We show that using these groups in a multi-task framework leads to better predictive performance of in-hospital mortality both across groups and overall. We also highlight the need for more granular evaluation of performance when dealing with heterogeneous populations.
Date issued
2018-07-19Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryPublisher
ACM
Citation
Suresh, Harini, Gong, Jen J. and Guttag, John V. 2018. "Learning Tasks for Multitask Learning."
Version: Original manuscript