Identification of physiological shock in intensive care units via Bayesian regime switching models

arXiv stat.ML / 2026/3/24

💬 オピニオンSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

要点

The paper proposes a Bayesian regime switching model to detect occult hemorrhage in ICU patients by inferring a patient’s underlying physiological state from trends in vitals and labs.
It uses longitudinal ICU data (33,924 encounters curated from Mayo Clinic) and models measurements with a vector autoregressive process conditioned on latent states that evolve via a Markov process.
The method includes a novel Bayesian sampling routine to learn posterior probabilities over physiological states over time, enabling probabilistic assessment rather than deterministic detection.
The approach also accounts for physiological changes that occurred before ICU admission, addressing baseline shifts that could otherwise confound detection.
Simulation experiments and a real case study are presented to demonstrate the effectiveness of the regime-switching approach for earlier intervention potential.

Abstract

Detection of occult hemorrhage (i.e., internal bleeding) in patients in intensive care units (ICUs) can pose significant challenges for critical care workers. Because blood loss may not always be clinically apparent, clinicians rely on monitoring vital signs for specific trends indicative of a hemorrhage event. The inherent difficulties of diagnosing such an event can lead to late intervention by clinicians which has catastrophic consequences. Therefore, a methodology for early detection of hemorrhage has wide utility. We develop a Bayesian regime switching model (RSM) that analyzes trends in patients' vitals and labs to provide a probabilistic assessment of the underlying physiological state that a patient is in at any given time. This article is motivated by a comprehensive dataset we curated from Mayo Clinic of 33,924 real ICU patient encounters. Longitudinal response measurements are modeled as a vector autoregressive process conditional on all latent states up to the current time point, and the latent states follow a Markov process. We present a novel Bayesian sampling routine to learn the posterior probability distribution of the latent physiological states, as well as develop an approach to account for pre-ICU-admission physiological changes. A simulation and real case study illustrate the effectiveness of our approach.