Computational frameworks for automated detection and quantification of paroxysmal sympathetic hyperactivity among traumatic brain injury patients
Xiangxiang Kong, Lujie Karen Chen, Sancharee Hom Chowdhurry, Ryan B. Felix, Shiming Yang, Peter Hu, Neeraj Badjatia, Jamie Erin Podell
Abstract
Paroxysmal sympathetic hyperactivity (PSH) is a syndrome that occurs in a large subset of critically ill traumatic brain injury (TBI) patients and is associated with complications and poor recovery. PSH is defined by recurrent episodic vital sign elevations in the appropriate clinical context.
Introduction
Paroxysmal Sympathetic Hyperactivity (PSH) is a clinically important manifestation of autonomic dysfunction that occurs in up to one third of critically ill patients after traumatic brain injury (TBI) [1–5]. Recurrent, sympathetically-mediated episodes of tachycardia, hypertension, tachypnea, hyperthermia, and motor posturing define PSH.
Materials and methods
In this study, we used a cohort of critically ill adult TBI patients (N = 221) admitted to R Adams Cowley Shock Trauma Center of University of Maryland Medical Center between January 2016 and July 2018. The inclusion criteria were head Abbreviated Injury Scale (AIS) > 0, ICU length of stay of at least three days and hospital length of stay of at least 14 days.
Results
Our cohort included 221 critically ill TBI patients described in Table 2.
Discussion
In this study we demonstrate three automatic continuous VS-derived methods for quantifying PSH in critically ill acute TBI patients. These methods demonstrate initial face validity by distinguishing clinically identified PSH cases from controls in a dynamic manner that mimics the manual standard PSH quantification tool, the PSH-AM [1,2].
Conclusion
This research presents methods for automatically quantifying PSH using patients’ high-resolution continuous VS data. Similar to prior work using manually derived daily CFS scores, our VS-based hrCFS differs across clinically defined PSH cases and controls during the time period when PSH is most often first diagnosed.
Citation: Kong X, Chen LK, Chowdhurry SH, Felix RB, Yang S, Hu P, et al. (2026) Computational frameworks for automated detection and quantification of paroxysmal sympathetic hyperactivity among traumatic brain injury patients. PLoS One 21(3): e0344088. https://doi.org/10.1371/journal.pone.0344088
Editor: Yashwanth Nanda Kumar, University of Washington, UNITED STATES OF AMERICA
Received: August 8, 2025; Accepted: February 15, 2026; Published: March 3, 2026
Copyright: © 2026 Kong et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: We provide de-identified data as supporting files, and we also provide author-generated code at the following url: https://github.com/seankong88/PSH_episode_analysis.
Funding: Research funding for this work was provided by the University of Maryland Baltimore, Institute for Clinical & Translational Research (ICTR), grant number 1UL1TR003098 to the institutions of Dr. Podell and Dr. Chen. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Competing interests: The authors have declated no competing interests.
