Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Infant and toddler teachers perspectives on interconnections between relationships and professional well-being during the COVID-19 pandemic.

Journal of early childhood research : ECR·2026

Same author

The Rewards and Stresses of Teaching for Infant and Toddler Educators.

Early childhood education journal·2026

Same author

Increasing Parental Well-Being After the Neonatal Intensive Care Unit Through Relational Savoring.

Family process·2026

Same author

Mothers' responses to relational savoring as a function of attachment: A qualitative study.

Infant mental health journal·2026

Same author

Pilot test of an adapted relational savoring intervention for Latine-serving community health workers.

Journal of counseling psychology·2026

Same author

Saliendo adelante: Understanding trauma and resilience in immigrant families from Central America.

Journal of traumatic stress·2026

Same journal

Stakeholder Experiences With the Pneumococcal Conjugate Vaccine Chatbot as a Complementary Capacity-Building Tool for Frontline Health Workers in India: Qualitative Study.

JMIR formative research·2026

Same journal

Acceptability and Perceived Usefulness of a Digital Gambling Harm Minimisation Tool: A Cross-Sectional Study.

JMIR formative research·2026

Same journal

Knowledge Graphs Based on Meta-Analysis Papers Improve the Quality of Case Formulation: Mixed Methods Design.

JMIR formative research·2026

Same journal

Expedited Transition to Digital Delivery of Recovery Support Services Due to the COVID-19 Pandemic: Mixed Methods Needs Assessment.

JMIR formative research·2026

Same journal

Impact of an mHealth App on Digital Transformation: Randomized Clinical Trial on Strengthening Digital Skills in Older Women.

JMIR formative research·2026

Same journal

Emotion Classification in Japanese Cancer Survivor Interview Narratives Using Sentiment Polarity and Plutchik Emotion Frameworks: Model Development and Evaluation Study.

JMIR formative research·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 21, 2026

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Published on: June 16, 2018

Detection of Posttraumatic Stress Disorder With Rest-Activity Data: Machine Learning Approach Using Wearable and

Katherine Wislocki¹, Ghazal Naderi¹, Jessica L Borelli¹

¹Department of Psychology, University of California, Irvine, 214 Pereira Dr, Irvine, CA, 92617, United States, 1 949 824 5574.

JMIR Formative Research

|May 19, 2026

Summary

This summary is machine-generated.

Machine learning models using actigraphy and sleep logs can predict posttraumatic stress disorder (PTSD) diagnosis. Combining subjective and objective data improved PTSD prediction accuracy in trauma-exposed service members and veterans.

Keywords:

actigraphy machine learning posttraumatic stress veterans wearables

More Related Videos

A Community-based Stress Management Program: Using Wearable Devices to Assess Whole Body Physiological Responses in Non-laboratory Settings

A Community-based Stress Management Program: Using Wearable Devices to Assess Whole Body Physiological Responses in Non-laboratory Settings

Published on: January 22, 2018

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

Related Experiment Videos

Last Updated: May 21, 2026

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Evaluation of Commercial-Off-The-Shelf Wrist Wearables to Estimate Stress on Students

Published on: June 16, 2018

A Community-based Stress Management Program: Using Wearable Devices to Assess Whole Body Physiological Responses in Non-laboratory Settings

A Community-based Stress Management Program: Using Wearable Devices to Assess Whole Body Physiological Responses in Non-laboratory Settings

Published on: January 22, 2018

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

Area of Science:

Computational psychiatry
Digital phenotyping
Wearable sensor technology

Background:

Disruptions in rest-activity rhythms are linked to posttraumatic stress disorder (PTSD).
Machine learning (ML) shows promise for analyzing actigraphy and self-report data in PTSD research.
Previous studies often predicted probable PTSD from self-reports, which may differ from clinical diagnoses.

Purpose of the Study:

To determine if wrist actigraphy and sleep logs can predict clinician-rated PTSD and probable PTSD diagnoses.
To identify key predictive features for PTSD diagnosis using ML.
To assess if PTSD prediction models account for other mental health disorders.

Main Methods:

Collected 1-week wrist actigraphy and sleep logs from 36 trauma-exposed service members and veterans.
Utilized extreme gradient boosting ML models with leave-one-subject-out cross-validation.
Predicted clinician-rated PTSD and probable PTSD (based on PCL-5 cutoffs of ≥31 and ≥38).

Main Results:

ML models accurately predicted PTSD diagnosis (AUC=0.83, 95% accuracy) and probable PTSD (PCL-5≥31 cutoff, AUC=0.84).
A combination of subjective and objective features was most predictive.
Models predicted PTSD even when controlling for other mental health diagnoses (P<.003).

Conclusions:

Subjective and objective rest-activity features enhance PTSD prediction.
Further research is needed to validate these findings.
Integrating wearable sensor data and subjective information can support PTSD assessment.