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

Research output: Contribution to journalArticlepeer-review


<italic>Goal:</italic> 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 for PTSD diagnosis and treatment. <italic>Methods:</italic> 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. <italic>Results:</italic> Speech from low-arousal and positive-valence regions provide the best discrimination for PTSD. Our model achieved an AUC (area under the curve) equal to 0.80 in detecting PCL-C ratings, outperforming models with no emotion filtering (AUC &#x003D; 0.68). <italic>Conclusions:</italic> This result suggests that emotion drives the selection of the most salient temporal regions of an audio recording for PTSD detection.

Original languageEnglish
Pages (from-to)1-7
Number of pages7
JournalIEEE Open Journal of Engineering in Medicine and Biology
StateAccepted/In press - 2023
Externally publishedYes


  • Acoustics
  • Brain injuries
  • Feature extraction
  • Machine learning
  • Mathematical models
  • Sociology
  • Standards


Dive into the research topics of 'An Emotion-Driven Vocal Biomarker-Based PTSD Screening Tool'. Together they form a unique fingerprint.

Cite this