Abstract: Perceived Vulnerability to Disease (PVD), Resilience, and Mental Health Outcome of Korean Immigrants amid the COVID-19 Pandemic: A Machine Learning Approach (Society for Social Work and Research 26th Annual Conference - Social Work Science for Racial, Social, and Political Justice)

Perceived Vulnerability to Disease (PVD), Resilience, and Mental Health Outcome of Korean Immigrants amid the COVID-19 Pandemic: A Machine Learning Approach

Schedule:
Saturday, January 15, 2022
Supreme Court, ML 4 (Marriott Marquis Washington, DC)
* noted as presenting author
Shinwoo Choi, PhD, MSSW, Assistant Professor, Texas State University, San Marcos, FL
Yong Je Kim, Ph.D., Lecturer, Texas State University, San Marcos, TX
Joo Young Hong, Ph.D., Research Scientist, University of North Florida, Jacksonville, FL
Cristy Cummings, PhD, Assistant Professor, University of North Florida, FL
Soo-Jung Byoun, PhD, Research Associate, Korea Institute for Health and Social Affairs, Sejong City, Korea, Republic of (South)
Hadley Jauer, BSW Candidate, Texas State University, San Marcos, TX
Background and Purpose: The COVID-19 pandemic has rapidly increased Perceived Vulnerability to Disease (PVD) because it is easily contagious and critically threatens life (Shook et al. 2020). PVD is defined as “persons’ susceptibility to infectious diseases transmission and emotional distress of potential occurring of disease transmission”(Ahmadzadeh et al. 2013). Individuals’ PVD affects their specific health behaviors and coping strategies. PVD can lead individuals to engage in preventative health behaviors against the virus, but consistently feeling vulnerable towards the disease might lead into negative outcomes as well (Scharloo M 2000). As the COVID-19 pandemic continues, people around the world are suffering from the fear of potentially catching the deadly virus. It is indicated that people’s mental health status are deteriorating since the beginning of current pandemic (McGinty et al. 2020).

Methods: Through purposive sampling, both foreign-born and U.S. born Korean immigrants residing in the U.S. above the age of 18 years were invited to an online survey. Between May-June 2020, data collection took place, which yielded the final sample of 790 participants from 42 states. The Artificial Neural Network (ANN) was conducted to verify variables that predict the level of psychological distress on the participants. The model with one hidden layer holding six hidden neurons showed the best performance.

Results: In order to create a training sample, 68.8% of the entire dataset was chosen through a random selection. A testing sample used 25.5% , and the remaining was used as a holdout sample. The error rate for each of the training set, the testing set, and the holdout set was 28.4%, 25.5%, and 29.4%, respectively. The error rate was approximately 27 %, and the results from the sensitivity analysis, Receiver Operating Characteristics (ROC) curve, showed that the Area Under the Curve (AUC) was .801. The most powerful predicting variables in the neural network were resilience, fear of COVID-19, and PVD.

Conclusion and Implications: This study found that PVD and fear of COVID-19, have a negative impact on psychological distress among Korean Americans. Elements of individuals’ coping, specifically resilience and social support were protective factors against psychological distress, with resilience as the most powerful predictor in the study. Interventions and programs that provide mental health services, foster resilience, and support social connection and support are needed, however the recommended preventative health behaviors needed to navigate the COVID-19 pandemic limit traditional in-person interactions.