Exploring Real-Time Variability and Latent Markers of Blood Volume Decompensation Status in Wearable Signals Measured During Hemorrhage

Abstract

Project SummaryThis project aims to develop novel technologies for bridging wearable sensing and machine learning for estimating blood volume decompensation status for the Warfighter in austere environments. Reduced blood volume, or hypovolemia, is experienced bythe modern Warfighter in a variety of circumstances ranging from exsanguinating hemorrhage to hypoxia, and can lead to shock or collapse. The Inan Research Lab has created a novel wearable sensing system that captures multiple modalities of cardiac and vascular sensing data. This device captures electrocardiogram, photoplethysmogram, and seismocardiogram signals, and is thus a unique data collection tool to enable multi-modal sensing of cardiovascular state of relevance to volume status monitoring. In this proposed work, the signals from this patch collected in prior work will be used as a dataset for training novel AI models for uncovering state variables associated with these signals that relate to quantifying volume status. The plan will be to bridge datasets collected in a variety of physiological conditions to allow generalization of algorithm design, and for gaining insight into how these signals relate to underlying hemodynamics. The variability in the signals will also be explored as a feature for sub-optimal volume status. The project will result in optimized real-time algorithms for extraction blood volume decompensation status that will be relevant for Warfighter health and protection, specifically with regards to volume status monitoring in hemorrhaging casualties. Approved for Public Release.

Document Details

Document Type
DoD Grant Award
Publication Date
Apr 10, 2025
Source ID
N000142512219

Entities

People

  • Ömer İnan

Organizations

  • Georgia Tech Research Corporation
  • Office of Naval Research
  • United States Navy

Tags

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Cardiovascular Physiology
  • Oncology and Biomarker-Based Cancer Detection.

Technology Areas

  • AI & ML