GRU-TV: Time- and velocity-aware GRU for patient representation on multivariate clinical time-series data
This work addresses the challenge of handling irregularly sampled EHR data for patient representation learning, which is incremental as it builds on existing GRU models by adding time and velocity perception mechanisms.
The authors tackled the problem of learning patient representations from multivariate clinical time-series data with irregular time intervals and high missing rates by proposing GRU-TV, a model that incorporates time and velocity awareness, achieving robust performance on computer-aided diagnosis tasks, particularly on sequences with high-variance time intervals.
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.