Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU
This work addresses the need for more granular evaluation in clinical machine learning to improve outcomes for diverse patient populations, though it is incremental in applying existing multi-task methods to this domain.
The paper tackles the problem of poor predictive performance for specific patient groups in heterogeneous ICU populations by presenting a two-step framework that learns relevant subgroups and uses them in a multi-task framework, resulting in better in-hospital mortality prediction across groups and overall.
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.