Event-Based Contrastive Learning for Medical Time Series

TL;DR

This paper introduces Event-Based Contrastive Learning (EBCL), a novel method for learning temporal embeddings from heterogeneous medical time series data, improving downstream predictive tasks and patient subgroup identification.

Contribution

The paper proposes EBCL, a contrastive learning framework that preserves temporal information around key medical events for better patient data representation.

Findings

EBCL improves performance on mortality, readmission, and length of stay predictions.

Unsupervised embeddings reveal distinct patient subgroups with different outcomes.

Method is adaptable to various time-series datasets for personalized healthcare.

Abstract

In clinical practice, one often needs to identify whether a patient is at high risk of adverse outcomes after some key medical event. For example, quantifying the risk of adverse outcomes after an acute cardiovascular event helps healthcare providers identify those patients at the highest risk of poor outcomes; i.e., patients who benefit from invasive therapies that can lower their risk. Assessing the risk of adverse outcomes, however, is challenging due to the complexity, variability, and heterogeneity of longitudinal medical data, especially for individuals suffering from chronic diseases like heart failure. In this paper, we introduce Event-Based Contrastive Learning (EBCL) - a method for learning embeddings of heterogeneous patient data that preserves temporal information before and after key index events. We demonstrate that EBCL can be used to construct models that yield improved performance on important downstream tasks relative to other pretraining methods. We develop and test the method using a cohort of heart failure patients obtained from a large hospital network and the publicly available MIMIC-IV dataset consisting of patients in an intensive care unit at a large tertiary care center. On both cohorts, EBCL pretraining yields models that are performant with respect to a number of downstream tasks, including mortality, hospital readmission, and length of stay. In addition, unsupervised EBCL embeddings effectively cluster heart failure patients into subgroups with distinct outcomes, thereby providing information that helps identify new heart failure phenotypes. The contrastive framework around the index event can be adapted to a wide array of time-series datasets and provides information that can be used to guide personalized care.