Research    Publications    Funding    Professor    People    Course

Joo Young Chun, Hyun-Jin Kim, Ji-Won Hur, Dooyoung Jung, Heon-Jeong Lee, Seung Pil Pack, Sungkil Lee, Gerard Kim, Chung-Yean Cho, Seung-Moo Lee, Hyeri Lee, Seungmoon Choi, Taesu Cheong, and Chul-Hyun Cho

JMIR Serious Games, 10(3), e38284, 2022.
Background: Social anxiety disorder (SAD) is a fear of social situations where a person anticipates being evaluated negatively. Changes in autonomic response patterns are related to the expression of anxiety symptoms. Virtual reality (VR) sickness can inhibit the VR experiences. Objective: This study predicts the severity of specific anxiety symptoms and VR sickness in patients with SAD using machine learning based on in-situ autonomic physiological signals (heart rate and galvanic skin response) during VR treatment sessions. Methods: This study had 32 participants with SAD taking part in six VR sessions. During each VR session, all participants’ heart rate and galvanic skin response were measured in real-time. We assessed specific anxiety symptoms using the Internalized Shame Scale (ISS), the post-event rumination scale (PERS), and VR sickness using the simulator sickness questionnaire (SSQ) during four VR sessions (#1, #2, #4 and #6). Logistic regression, random forest, and naive Bayes classification classified and predict the severity groups in the ISS, PERS, and SSQ subdomains based on in-situ autonomic physiological signal data. Results: The severity of social anxiety disorder was predicted with three machine learning models. According to the F1 score, the highest prediction performance among each domain for severity was as follows: The F1 score of the ISS mistake anxiety subdomain was 0.8421 using the logistic regression model, the PERS positive subdomain was 0.7619 using the naïve Bayes classifier, and the total VR sickness was 0.7059 using the random forest model. Conclusions: This study could predict specific anxiety symptoms and VR sickness during VR intervention by autonomic physiological signals alone in real-time. Machine learning models predict individuals' severe and non-severe psychological states based on in-situ physiological signal data during VR intervention for real-time interactive services. These models support the diagnosis of specific anxiety symptoms and VR sickness with minimal participant bias. Clinical Trial: CRIS Registration Number-KCT0003854.
@ARTICLE{chun22:anxiety, title={{Prediction of specific anxiety symptoms and VR sickness based on in-situ autonomic physiological signals during VR treatment in patients with social anxiety disorder: mixed-methods study}}, author={Joo Young Chun and Hyun-Jin Kim and Ji-Won Hur and Dooyoung Jung and Heon-Jeong Lee and Seung Pil Pack and Sungkil Lee and Gerard Kim and Chung-Yean Cho and Seung-Moo Lee and Hyeri Lee and Seungmoon Choi and Taesu Cheong and Chul-Hyun Cho}, journal={{JMIR Serious Games}}, volume={10}, number={3}, pages={e38284}, year={2022} }

27336, College of Software, Sungkyunkwan University, Tel. +82 31-299-4917, Seobu-ro 2066, Jangan-gu, Suwon, 16419, South Korea
Campus map (how to reach CGLab)