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.