Menu Close

Classification and Prediction of Post-Trauma Outcomes Related to PTSD using Circadian Rhythm Changes Measured via Wrist-Worn Research Watch in a Large Longitudinal Cohort

Citation

Cakmak, Ayse Selin; Perez Alday, Erick Andres; Da Poian, Giulia; Bahrami Rad, Ali; Metzler, Thomas J.; Neylan, Thomas C.; House, Stacey L.; Beaudoin, Francesca L.; An, Xinming; & Stevens, Jennifer J., et al. (Online ahead of print). Classification and Prediction of Post-Trauma Outcomes Related to PTSD using Circadian Rhythm Changes Measured via Wrist-Worn Research Watch in a Large Longitudinal Cohort. IEEE Journal of Biomedical and Health Informatics.

Abstract

Post-Traumatic Stress Disorder (PTSD) is a psychiatric condition resulting from threatening or horrifying events. We hypothesized that circadian rhythm changes, measured by a wrist-worn research watch are predictive of post-trauma outcomes.
APPROACH: 1618 post-trauma patients were enrolled after admission to emergency departments (ED). Three standardized questionnaires were administered at week eight to measure post-trauma outcomes related to PTSD, sleep disturbance, and pain interference with daily life. Pulse activity and movement data were captured from a research watch for eight weeks. Standard and novel movement and cardiovascular metrics that reflect circadian rhythms were derived using this data. These features were used to train different classifiers to predict the three outcomes derived from week-eight surveys. Clinical surveys administered at ED were also used as features in the baseline models.
RESULTS: The highest cross-validated performance of research watch-based features was achieved for classifying participants with pain interference by a logistic regression model, with an area under the receiver operating characteristic curve (AUC) of 0.70. The ED survey-based model achieved an AUC of 0.77, and the fusion of research watch and ED survey metrics improved the AUC to 0.79.
SIGNIFICANCE: This work represents the first attempt to predict and classify post-trauma symptoms from passive wearable data using machine learning approaches that leverage the circadian desynchrony in a potential PTSD population.

URL

http://dx.doi.org/10.1109/jbhi.2021.3053909

Reference Type

Journal Article

Article Type

Regular

Year Published

Online ahead of print

Journal Title

IEEE Journal of Biomedical and Health Informatics

Author(s)

Cakmak, Ayse Selin
Perez Alday, Erick Andres
Da Poian, Giulia
Bahrami Rad, Ali
Metzler, Thomas J.
Neylan, Thomas C.
House, Stacey L.
Beaudoin, Francesca L.
An, Xinming
Stevens, Jennifer J.
Zeng, Donglin
Linnstaedt, Sarah D.
Jovanovic, Tanja
Germine, Laura T.
Bollen, Kenneth A.
Rauch, Scott L.
Lewandowski, Christopher A.
Hendry, Phyllis L.
Sheikh, Sophia
Storrow, Allan B.
Musey, Paul I.
Haran, John P.
Jones, Christopher W.
Punches, Brittany E.
Swor, Robert A.
Gentile, Nina T.
Mcgrath, Meghan E.
Seamon, Mark J.
Mohiuddin, Kamran
Chang, Anna M.
Pearson, Claire L.
Domeier, Robert M.
Bruce, Steven E.
O'Neil, Brian J.
Rathlev, Niels K.
Sanchez, Leon D.
Pietrzak, Robert H.
Joormann, Jutta
Barch, Deanna M.
Pizzagalli, Diego A.
Harte, Steven E.
Elliott, James M.
Koenen, Karestan C.
Ressler, Kerry J.
Kessler, Ronald C.
Li, Qiao
Mclean, Samuel A.
Clifford, Gari D.

Continent/Country

United States of America