GRU-TV: Time- and velocity-aware GRU for patient representation on multivariate clinical time-series data

TL;DR

This paper introduces GRU-TV, a novel time- and velocity-aware recurrent neural network model that effectively captures continuous physiological changes in multivariate clinical time-series data for improved patient representation.

Contribution

The study proposes a time- and velocity-aware GRU model using neural ODEs and velocity perception for better patient representation learning from irregular clinical time-series data.

Findings

GRU-TV outperforms existing models on CAD tasks.

Effective on sequences with high-variance time intervals.

Demonstrates robustness across two real EHR datasets.

Abstract

Electronic health records (EHRs) are usually highly dimensional, heterogeneous, and multimodal. Besides, the random recording of clinical variables results in high missing rates and uneven time intervals between adjacent records in the multivariate clinical time-series data extracted from EHRs. Current works using clinical time-series data for patient representation regard the patients' physiological status as a discrete process described by sporadically collected records. However, changes in the patient's physiological condition are continuous and dynamic processes. The perception of time and velocity of change is crucial for patient representation learning. In this study, we propose a time- and velocity-aware gated recurrent unit model (GRU-TV) for patient representation learning of clinical multivariate time-series data in a time-continuous manner. The neural ordinary differential equations (ODEs) and velocity perception mechanism are applied to perceive the time interval between adjacent records and changing rate of the patient's physiological status, respectively. Our experiments on two real clinical EHR datasets (PhysioNet2012, MIMIC-III) establish that GRU-TV is a robust model on computer-aided diagnosis (CAD) tasks, especially on sequences with high-variance time intervals.