Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU

Abstract

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.

arXiv commentKDD 2018

References in corpus (9)

• Scikit-learn: Machine Learning in Python
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Teaching Machines to Read and Comprehend
• An Overview of Multi-Task Learning in Deep Neural Networks
• Attention-Based Models for Speech Recognition
• No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World
• Clinical Intervention Prediction and Understanding using Deep Networks
• The Use of Autoencoders for Discovering Patient Phenotypes
• Personalized Risk Scoring for Critical Care Patients using Mixtures of Gaussian Process Experts

Cited by in corpus (4)

• Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
• Deep learning for temporal data representation in electronic health records: A systematic review of challenges and methodologies
• A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
• FlexCare: Leveraging Cross-Task Synergy for Flexible Multimodal Healthcare Prediction