Quantitative Evaluation of the Severity of Posttraumatic Stress Disorder through Transfer Learning from Specific Phobia Data
2026-05-25 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors developed a computer program using machine learning to help measure how bad PTSD symptoms are by looking at heart rate and skin signals. They trained their model with data related to fear and then tested it on military participants. Their program was able to tell who had PTSD with about 86% accuracy and could estimate PTSD severity fairly well. This approach could make PTSD assessment quicker, more objective, and easier to do in clinical settings. It shows promise for helping screen and monitor PTSD in patients using physiological data.
PTSDmachine learningmultivariate kernel density estimationheart rategalvanic skin responsefear-response modelPCL-Mclassification accuracymean absolute errorphysiological signals
Authors
Nicolas Ricka, Gauthier Pellegrin, Denis A. Fompeyrine, Thomas Rohaly, Leah Enders, Heather Roy
Abstract
Posttraumatic stress disorder (PTSD) is a prevalent and debilitating mental health condition with significant personal and societal impacts. Current clinical assessments of PTSD often rely on subjective evaluations, which can be time-consuming, costly, and prone to human bias. This study proposes a machine learning (ML) approach based on multivariate kernel density estimation (MKDE) technique for the objective evaluation of PTSD severity. We collected heart rate (HR) and galvanic skin response (GSR) signals as well as PTSD Checklist - Military Version (PCL-M) labels from 21 participants during an immersive simulation. A fear-response model was trained on a public arachnophobia dataset, and predictive features of PTSD were extracted from the fear-response curves estimated on the military dataset. The model achieved an accuracy of 86\% in classifying PTSD status, effectively distinguishing participants with and without PTSD (PCL-M threshold of 36). The average mean absolute error (MAE) of the models is 5.6, and it estimated a clinical PTSD severity scale with a mean absolute percentage error of 17\%. Our algorithm demonstrates promising potential for enhancing estimation of PTSD severity and followup by offering an objective and low-effort evaluation approach using physiology. These findings suggest clinical utility in both screening and follow-up settings.