An Emotion-Driven Vocal Biomarker-Based PTSD Screening Tool

Thomas F. Quatieri; Jing Wang; James R. Williamson; Richard Delaura; Tanya Talkar; Nancy P. Solomon; Stefanie E. Kuchinsky; Megan Eitel; Tracey Brickell; Sara Lippa; Kristin J. Heaton; Douglas S. Brungart; Louis French; Rael Lange; Jeffrey Palmer; Hayley Reynolds

doi:10.1109/OJEMB.2023.3284798

An Emotion-Driven Vocal Biomarker-Based PTSD Screening Tool

Thomas F. Quatieri^*, Jing Wang^*, James R. Williamson, Richard Delaura, Tanya Talkar, Nancy P. Solomon, Stefanie E. Kuchinsky, Megan Eitel, Tracey Brickell, Sara Lippa, Kristin J. Heaton, Douglas S. Brungart, Louis French, Rael Lange, Jeffrey Palmer, Hayley Reynolds

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Goal: This paper introduces an automated post-traumatic stress disorder (PTSD) screening tool that could potentially be used as a self-assessment or inserted into routine medical visits to aid in PTSD diagnosis and treatment. Methods: With an emotion estimation algorithm providing arousal (excited to calm) and valence (pleasure to displeasure) levels through discourse, we select regions of the acoustic signal that are most salient for PTSD detection. Our algorithm was tested on a subset of data from the DVBIC-TBICoE TBI Study, which contains PTSD Check List Civilian (PCL-C) assessment scores. Results: Speech from low-arousal and positive-valence regions provide the highest discrimination for PTSD. Our model achieved an AUC (area under the curve) of 0.80 in detecting PCL-C ratings, outperforming models with no emotion filtering (AUC = 0.68). Conclusions: This result suggests that emotion drives the selection of the most salient temporal regions of an audio recording for PTSD detection.

Original language	English
Pages (from-to)	621-626
Number of pages	6
Journal	IEEE Open Journal of Engineering in Medicine and Biology
Volume	5
DOIs	https://doi.org/10.1109/OJEMB.2023.3284798
State	Published - 2024
Externally published	Yes

Keywords

Emotional digital twin
PTSD
emotion sensing
neuromotor coordination
vocal biomarkers

Access to Document

10.1109/OJEMB.2023.3284798

Cite this

Quatieri, T. F., Wang, J., Williamson, J. R., Delaura, R., Talkar, T., Solomon, N. P., Kuchinsky, S. E., Eitel, M., Brickell, T., Lippa, S., Heaton, K. J., Brungart, D. S., French, L., Lange, R., Palmer, J., & Reynolds, H. (2024). An Emotion-Driven Vocal Biomarker-Based PTSD Screening Tool. IEEE Open Journal of Engineering in Medicine and Biology, 5, 621-626. https://doi.org/10.1109/OJEMB.2023.3284798

@article{1e42cba29ef24dafa70ce9092e5542b3,

title = "An Emotion-Driven Vocal Biomarker-Based PTSD Screening Tool",

abstract = "Goal: This paper introduces an automated post-traumatic stress disorder (PTSD) screening tool that could potentially be used as a self-assessment or inserted into routine medical visits to aid in PTSD diagnosis and treatment. Methods: With an emotion estimation algorithm providing arousal (excited to calm) and valence (pleasure to displeasure) levels through discourse, we select regions of the acoustic signal that are most salient for PTSD detection. Our algorithm was tested on a subset of data from the DVBIC-TBICoE TBI Study, which contains PTSD Check List Civilian (PCL-C) assessment scores. Results: Speech from low-arousal and positive-valence regions provide the highest discrimination for PTSD. Our model achieved an AUC (area under the curve) of 0.80 in detecting PCL-C ratings, outperforming models with no emotion filtering (AUC = 0.68). Conclusions: This result suggests that emotion drives the selection of the most salient temporal regions of an audio recording for PTSD detection.",

keywords = "Emotional digital twin, PTSD, emotion sensing, neuromotor coordination, vocal biomarkers",

author = "Quatieri, {Thomas F.} and Jing Wang and Williamson, {James R.} and Richard Delaura and Tanya Talkar and Solomon, {Nancy P.} and Kuchinsky, {Stefanie E.} and Megan Eitel and Tracey Brickell and Sara Lippa and Heaton, {Kristin J.} and Brungart, {Douglas S.} and Louis French and Rael Lange and Jeffrey Palmer and Hayley Reynolds",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.",

year = "2024",

doi = "10.1109/OJEMB.2023.3284798",

language = "English",

volume = "5",

pages = "621--626",

journal = "IEEE Open Journal of Engineering in Medicine and Biology",

issn = "2644-1276",

}

Quatieri, TF, Wang, J, Williamson, JR, Delaura, R, Talkar, T, Solomon, NP, Kuchinsky, SE, Eitel, M, Brickell, T, Lippa, S, Heaton, KJ, Brungart, DS, French, L, Lange, R, Palmer, J & Reynolds, H 2024, 'An Emotion-Driven Vocal Biomarker-Based PTSD Screening Tool', IEEE Open Journal of Engineering in Medicine and Biology, vol. 5, pp. 621-626. https://doi.org/10.1109/OJEMB.2023.3284798

TY - JOUR

T1 - An Emotion-Driven Vocal Biomarker-Based PTSD Screening Tool

AU - Quatieri, Thomas F.

AU - Wang, Jing

AU - Williamson, James R.

AU - Delaura, Richard

AU - Talkar, Tanya

AU - Solomon, Nancy P.

AU - Kuchinsky, Stefanie E.

AU - Eitel, Megan

AU - Brickell, Tracey

AU - Lippa, Sara

AU - Heaton, Kristin J.

AU - Brungart, Douglas S.

AU - French, Louis

AU - Lange, Rael

AU - Palmer, Jeffrey

AU - Reynolds, Hayley

PY - 2024

Y1 - 2024

N2 - Goal: This paper introduces an automated post-traumatic stress disorder (PTSD) screening tool that could potentially be used as a self-assessment or inserted into routine medical visits to aid in PTSD diagnosis and treatment. Methods: With an emotion estimation algorithm providing arousal (excited to calm) and valence (pleasure to displeasure) levels through discourse, we select regions of the acoustic signal that are most salient for PTSD detection. Our algorithm was tested on a subset of data from the DVBIC-TBICoE TBI Study, which contains PTSD Check List Civilian (PCL-C) assessment scores. Results: Speech from low-arousal and positive-valence regions provide the highest discrimination for PTSD. Our model achieved an AUC (area under the curve) of 0.80 in detecting PCL-C ratings, outperforming models with no emotion filtering (AUC = 0.68). Conclusions: This result suggests that emotion drives the selection of the most salient temporal regions of an audio recording for PTSD detection.

AB - Goal: This paper introduces an automated post-traumatic stress disorder (PTSD) screening tool that could potentially be used as a self-assessment or inserted into routine medical visits to aid in PTSD diagnosis and treatment. Methods: With an emotion estimation algorithm providing arousal (excited to calm) and valence (pleasure to displeasure) levels through discourse, we select regions of the acoustic signal that are most salient for PTSD detection. Our algorithm was tested on a subset of data from the DVBIC-TBICoE TBI Study, which contains PTSD Check List Civilian (PCL-C) assessment scores. Results: Speech from low-arousal and positive-valence regions provide the highest discrimination for PTSD. Our model achieved an AUC (area under the curve) of 0.80 in detecting PCL-C ratings, outperforming models with no emotion filtering (AUC = 0.68). Conclusions: This result suggests that emotion drives the selection of the most salient temporal regions of an audio recording for PTSD detection.

KW - Emotional digital twin

KW - PTSD

KW - emotion sensing

KW - neuromotor coordination

KW - vocal biomarkers

UR - http://www.scopus.com/inward/record.url?scp=85162656859&partnerID=8YFLogxK

U2 - 10.1109/OJEMB.2023.3284798

DO - 10.1109/OJEMB.2023.3284798

M3 - Article

AN - SCOPUS:85162656859

SN - 2644-1276

VL - 5

SP - 621

EP - 626

JO - IEEE Open Journal of Engineering in Medicine and Biology

JF - IEEE Open Journal of Engineering in Medicine and Biology

ER -

An Emotion-Driven Vocal Biomarker-Based PTSD Screening Tool

Abstract

Keywords

Access to Document

Fingerprint

Cite this