Detecting Patterns of Physiological Response to Hemodynamic Stress via Unsupervised Deep Learning
This work addresses the challenge of characterizing unknown physiological responses to hemorrhage for medical monitoring and treatment, representing an incremental advancement by applying existing unsupervised techniques to a new domain-specific problem.
The paper tackled the problem of identifying physiological response patterns to hemodynamic stress from raw vital sign data using unsupervised deep learning, resulting in a method that transforms high-dimensional time series into a lower-dimensional latent space and identifies clusters hypothesized to match physicians' intuition about response patterns.
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.