Clinically Relevant Unsupervised Online Representation Learning of ICU Waveforms

Faris Faried Gulamali, Ashwin Shreekant Sawant, Ira Hofer, Matt Levin, Karandeep Singh, Benjamin S Glicksberg, Girish N Nadkarni

Keywords: ICU, High frequency time series, Representation Learning, Online Learning

TL;DR: Online unsupervised learning can generate clinically relevant representation of patient states in the Intensive Care Unit (ICU).

Abstract: Univariate high-frequency time series are dominant data sources for many medical, economic and environmental applications. In many of these domains, the time series are tied to real-time changes in state. In the intensive care unit, for example, changes and intracranial pressure waveforms can indicate whether a patient is developing decreased blood perfusion to the brain during a stroke, for example. However, most representation learning to resolve states is conducted in an offline, batch-dependent manner. In high frequency time-series, high intra-state and inter-sample variability makes offline, batch-dependent learning a relatively difficult task. Hence, we propose Spatial Resolved Temporal Networks (SpaRTeN), a novel composite deep learning model for online, unsupervised representation learning through a spatially constrained latent space. SpaRTeN maps waveforms to states, and learns time-dependent representations of each state. Our key contribution is that we generate clinically relevant representations of each state for intracranial pressure waveforms.

Anonymity: We agree to keep the submission (including any supplements and/or code) anonymous.

Formatting: We confirm that we read and complied with the author's instructions.