Multivariate Machine Learning Analysis of M-ECG-derived Heart Rate Variability in TBI Veterans, With and Without Current PTSD and Additional Psychiatric Comorbidity
- 1Wake Forest University School of Medicine
Abstract
Traumatic brain injury (TBI) and posttraumatic stress disorder (PTSD) frequently co-occur in Veterans, producing overlapping symptoms and shared autonomic dysregulation. Heart rate variability (HRV) offers a noninvasive measure of autonomic function. This study explored whether multivariate HRV features extracted from MEG-derived electrocardiogram (M-ECG) signals contained information related to group classification of Veterans with TBI alone (TBI-alone; n = 42) versus those with current PTSD, with or without additional psychiatric comorbidity (TBI+PTSD; n = 40). Time-domain, frequency-domain, geometric, and nonlinear HRV metrics were analyzed using a nested cross-validated Random Forest classifier, with Boruta-based feature selection and SHapley Additive exPlanations for model interpretability. The classifier demonstrated modest exploratory discrimination (Random Forest AUC = 0.663, 95% CI: 0.540-0.778). LF/HF ratio, low-frequency proportion, and approximate entropy were among the features contributing most to distinguishing the TBI+PTSD group, suggesting that multivariate HRV analysis of M-ECG signals may capture subtle, yet potentially informative, autonomic patterns associated with current PTSD and psychiatric burden among Veterans with TBI. The modest classification performance indicates that these findings should be considered preliminary and hypothesis-generating. Larger, independent studies are needed to determine the robustness and potential clinical relevance of these findings.
Related
- Acid-sensing ion channels in pain and psychiatric disorders: from basic properties to comorbidity mechanisms
- Understanding non-psychiatric nurses' experiences of caring for patients with mental-physical comorbidity: a descriptive phenomenological study.
- Psychiatric comorbidity in dissociative identity disorder: A meta-analysis
- Psychiatric Comorbidity Outweighs Headache Subtype As A Predictor Of Disability In Chronic Daily Headache: A Matched-Control Study.
- Associations between psychiatric comorbidity and intensive care unit length of stay, hospital length of stay, and in‐hospital mortality: A retrospective observational study
BibTeX
@misc{izadysadr2026multivariate,
title = {{Multivariate Machine Learning Analysis of M-ECG-derived Heart Rate Variability in TBI Veterans, With and Without Current PTSD and Additional Psychiatric Comorbidity}},
author = {A. Izadysadr and H. S. Bagherzadeh and J. Rowland and S. L. Martindale and J. R. Stapleton-Kotloski and D. Godwin},
howpublished = {medRxiv},
year = {2026},
month = jun,
doi = {10.64898/2026.06.05.26354915},
url = {https://www.medrxiv.org/content/10.64898/2026.06.05.26354915v2},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Multivariate Machine Learning Analysis of M-ECG-derived Heart Rate Variability in TBI Veterans, With and Without Current PTSD and Additional Psychiatric Comorbidity
AU - A. Izadysadr
AU - H. S. Bagherzadeh
AU - J. Rowland
AU - S. L. Martindale
AU - J. R. Stapleton-Kotloski
AU - D. Godwin
PY - 2026
DA - 2026/06/05
PB - medRxiv
DO - 10.64898/2026.06.05.26354915
UR - https://www.medrxiv.org/content/10.64898/2026.06.05.26354915v2
AB - Traumatic brain injury (TBI) and posttraumatic stress disorder (PTSD) frequently co-occur in Veterans, producing overlapping symptoms and shared autonomic dysregulation. Heart rate variability (HRV) offers a noninvasive measure of autonomic function. This study explored whether multivariate HRV features extracted from MEG-derived electrocardiogram (M-ECG) signals contained information related to group classification of Veterans with TBI alone (TBI-alone; n = 42) versus those with current PTSD, with or without additional psychiatric comorbidity (TBI+PTSD; n = 40). Time-domain, frequency-domain, geometric, and nonlinear HRV metrics were analyzed using a nested cross-validated Random Forest classifier, with Boruta-based feature selection and SHapley Additive exPlanations for model interpretability. The classifier demonstrated modest exploratory discrimination (Random Forest AUC = 0.663, 95% CI: 0.540-0.778). LF/HF ratio, low-frequency proportion, and approximate entropy were among the features contributing most to distinguishing the TBI+PTSD group, suggesting that multivariate HRV analysis of M-ECG signals may capture subtle, yet potentially informative, autonomic patterns associated with current PTSD and psychiatric burden among Veterans with TBI. The modest classification performance indicates that these findings should be considered preliminary and hypothesis-generating. Larger, independent studies are needed to determine the robustness and potential clinical relevance of these findings.
ER -