English

Using Convolutional Variational Autoencoders to Predict Post-Trauma Health Outcomes from Actigraphy Data

Machine Learning 2020-11-23 v2 Signal Processing

Abstract

Depression and post-traumatic stress disorder (PTSD) are psychiatric conditions commonly associated with experiencing a traumatic event. Estimating mental health status through non-invasive techniques such as activity-based algorithms can help to identify successful early interventions. In this work, we used locomotor activity captured from 1113 individuals who wore a research grade smartwatch post-trauma. A convolutional variational autoencoder (VAE) architecture was used for unsupervised feature extraction from four weeks of actigraphy data. By using VAE latent variables and the participant's pre-trauma physical health status as features, a logistic regression classifier achieved an area under the receiver operating characteristic curve (AUC) of 0.64 to estimate mental health outcomes. The results indicate that the VAE model is a promising approach for actigraphy data analysis for mental health outcomes in long-term studies.

Keywords

Cite

@article{arxiv.2011.07406,
  title  = {Using Convolutional Variational Autoencoders to Predict Post-Trauma Health Outcomes from Actigraphy Data},
  author = {Ayse S. Cakmak and Nina Thigpen and Garrett Honke and Erick Perez Alday and Ali Bahrami Rad and Rebecca Adaimi and Chia Jung Chang and Qiao Li and Pramod Gupta and Thomas Neylan and Samuel A. McLean and Gari D. Clifford},
  journal= {arXiv preprint arXiv:2011.07406},
  year   = {2020}
}

Comments

Fixed typo in author affiliations

R2 v1 2026-06-23T20:13:34.042Z