Saved in:
Bibliographic Details
Main Authors: Kemmerer, Jeremy P., Williamson, James R., Kim, Joseph, Halford, Elizabeth, Rao, Hrishikesh M., Smalt, Christopher J.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.09508
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913837086670848
author Kemmerer, Jeremy P.
Williamson, James R.
Kim, Joseph
Halford, Elizabeth
Rao, Hrishikesh M.
Smalt, Christopher J.
author_facet Kemmerer, Jeremy P.
Williamson, James R.
Kim, Joseph
Halford, Elizabeth
Rao, Hrishikesh M.
Smalt, Christopher J.
contents Repeated exposure to blast overpressure in occupational settings has been associated with changes in cognitive and psychological health, as well as deficits in neurosensory subsystems. In this work, we describe a wearable system to simultaneously monitor physiology and blast exposure levels and demonstrate how this system can identify individualized exposure levels corresponding to acute physiological response to blast exposure. Machine learning was used to develop a dose-response model that fused multiple physiological measures (electrooculuography, gait, and balance) into a single risk score by predicting the level of blast exposure on held-out subjects (Fused model, R = 0.60). We found that blast events with peak pressure levels as low as 0.25 psi could be related to physiological changes and hence may contribute to blast injury. We also identified an individual subject with deteriorating reaction time scores that consistently showed a rapid and anomalous change in physiology-based risk scores after exposure to low-level blast events. Our results suggest that the wearable approach to blast monitoring is viable in weapons training environments as a complement to more direct but sparsely administered brain health assessments, potentially viable in austere environments, and that fusing multiple physiological signals can improve sensitivity.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09508
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Wearable Tracking of Eye and Body Movements During Breaching Training: Towards Real-Time Blast Injury Monitoring
Kemmerer, Jeremy P.
Williamson, James R.
Kim, Joseph
Halford, Elizabeth
Rao, Hrishikesh M.
Smalt, Christopher J.
Signal Processing
Repeated exposure to blast overpressure in occupational settings has been associated with changes in cognitive and psychological health, as well as deficits in neurosensory subsystems. In this work, we describe a wearable system to simultaneously monitor physiology and blast exposure levels and demonstrate how this system can identify individualized exposure levels corresponding to acute physiological response to blast exposure. Machine learning was used to develop a dose-response model that fused multiple physiological measures (electrooculuography, gait, and balance) into a single risk score by predicting the level of blast exposure on held-out subjects (Fused model, R = 0.60). We found that blast events with peak pressure levels as low as 0.25 psi could be related to physiological changes and hence may contribute to blast injury. We also identified an individual subject with deteriorating reaction time scores that consistently showed a rapid and anomalous change in physiology-based risk scores after exposure to low-level blast events. Our results suggest that the wearable approach to blast monitoring is viable in weapons training environments as a complement to more direct but sparsely administered brain health assessments, potentially viable in austere environments, and that fusing multiple physiological signals can improve sensitivity.
title Wearable Tracking of Eye and Body Movements During Breaching Training: Towards Real-Time Blast Injury Monitoring
topic Signal Processing
url https://arxiv.org/abs/2505.09508