Hostname: page-component-76fb5796d-wq484 Total loading time: 0 Render date: 2024-04-25T13:25:48.636Z Has data issue: false hasContentIssue false
  • English
  • Français

Prediction and classification of anxiety-related psychological scale and VR sickness based on autonomic physiological responses during VR treatment in patients with social anxiety disorder

Published online by Cambridge University Press:  01 September 2022

J.Y. Chun ,
H.-J. Kim ,
S. Lee ,
M. Kim ,
T. Cheong  and
C.-H. Cho
J.Y. Chun
Affiliation:
Korea University, School Of Industrial And Management Engineering, Seoul, Korea, Republic of
H.-J. Kim
Affiliation:
Chungnam National University Sejong Hospital, Psychiatry, Sejong, Korea, Republic of
S. Lee
Affiliation:
Chungnam National University Sejong Hospital, Psychiatry, Sejong, Korea, Republic of
M. Kim
Affiliation:
Chungnam National University Sejong Hospital, Psychiatry, Sejong, Korea, Republic of
T. Cheong
Affiliation:
Korea University, School Of Industrial And Management Engineering, Seoul, Korea, Republic of
C.-H. Cho*
Affiliation:
Chungnam National University Sejong Hospital, Psychiatry, Sejong, Korea, Republic of
*
*Corresponding author.

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.
Introduction

Social anxiety disorder (SAD) can accompany emotional symptoms as well as physical reactions. The assessment and real-time measurement of SAD is difficult in real-world.

Objectives

This study aims to predict the severity of specific anxiety states and virtual reality (VR) sickness in SAD patients by a machine learning model based on only quantitative measuring of autonomic physiologic signals during VR therapy sessions.

Methods

In total, 32 individuals with SAD symptoms were enrolled in VR participatory sessions. We assessed patients’ specific anxiety symptoms through Internalized Shame Scale (ISS) and Post-Event Rumination Scale (PERS), and VR sickness through Simulator Sickness Questionnaire (SSQ). Specific anxiety symptoms and VR sickness were divided into severe and non-severe states based on the total score of each scale by K-means clustering. Logistic regression, Random Forest, Naïve Bayes classifier, and Support Vector Machine were used based on the physiological signal data to predict the severity group in subdomains of ISS, PERS, and SSQ.

Results

Prediction performance (F1 score) for the severity of the ISS mistake anxiety subdomain was higher than other scales with 0.8421. For VR sickness, prediction performance for the severity of the physical subdomain was higher than the non-physical subdomain with 0.7692.

Conclusions

The study findings present that mistake anxiety and physical sickness could be predicted more accurately by only autonomic physiological signals, suggesting these features are probably associated with autonomic responses. Based on the present study results, we could provide the evidence for predicting the severity of specific anxiety or VR adverse effects only based on in-situ physiological signals.

Disclosure

No significant relationships.

Keywords

physiological responsesocial anxiety disordervirtual realityAnxiety
Type
Abstract
Information
European Psychiatry , Volume 65 , Special Issue S1: Abstracts of the 30th European Congress of Psychiatry , June 2022 , pp. S577
Creative Commons
Creative Common License - CCCreative Common License - BY
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
Copyright
© The Author(s), 2022. Published by Cambridge University Press on behalf of the European Psychiatric Association
Submit a response

Comments

No Comments have been published for this article.