Predicting Efficacy of Virtual Reality-Based Stabilization for Individuals With Posttraumatic Stress Symptoms: A Machine Learning Approach

Abstract

Objective The global impact of respiratory infectious diseases led to significant mental health challenges, highlighting the need for proactive psychological interventions to prepare for future pandemics. In response, virtual reality-based stabilization (VRS) was developed to mitigate posttraumatic stress symptoms (PTSS) and related comorbidities. Methods This study evaluated and predicted the effectiveness of VRS in 43 coronavirus disease-2019 (COVID-19) survivors and healthcare workers from COVID-19 treatment units. The effectiveness of VRS, conducted over five sessions, was measured using preand post-intervention psychological assessments for PTSS, depression, anxiety, COVID-related fear, posttraumatic growth, and quality of life. Additionally, a machine learning model was used to predict the impact of the intervention on PTSS and depression based on preintervention psychological assessments and heart rate variability tests. Results The post-intervention results showed significant improvements in all psychological outcomes. The machine learning-based model demonstrated good predictive accuracy for changes in PTSS and depression (R2=0.414–0.723). Notably, individuals with higher pre-intervention scores for PTSS and related comorbidities, as well as elevated heart rate variability and younger age, exhibited more significant improvements. Conclusion These findings suggest that VRS is effective in addressing PTSS and related conditions, and incorporating clinical and demographic data can enhance prediction models, enabling more personalized intervention strategies.