Detecting Patterns of Physiological Response to Hemodynamic Stress via Unsupervised Deep Learning

TL;DR

This study employs unsupervised deep learning to transform vital sign data into a lower-dimensional space, revealing physiological response patterns to hemodynamic stress that align with clinical intuition.

Contribution

It introduces an unsupervised deep learning approach to identify and characterize physiological response patterns from raw vital sign data.

Findings

Clusters in latent space correspond to physiological response patterns.

The method visualizes and interprets complex vital sign data.

Potential for improved understanding of hemorrhage responses.

Abstract

Monitoring physiological responses to hemodynamic stress can help in determining appropriate treatment and ensuring good patient outcomes. Physicians' intuition suggests that the human body has a number of physiological response patterns to hemorrhage which escalate as blood loss continues, however the exact etiology and phenotypes of such responses are not well known or understood only at a coarse level. Although previous research has shown that machine learning models can perform well in hemorrhage detection and survival prediction, it is unclear whether machine learning could help to identify and characterize the underlying physiological responses in raw vital sign data. We approach this problem by first transforming the high-dimensional vital sign time series into a tractable, lower-dimensional latent space using a dilated, causal convolutional encoder model trained purely unsupervised. Second, we identify informative clusters in the embeddings. By analyzing the clusters of latent embeddings and visualizing them over time, we hypothesize that the clusters correspond to the physiological response patterns that match physicians' intuition. Furthermore, we attempt to evaluate the latent embeddings using a variety of methods, such as predicting the cluster labels using explainable features.