Purpose: This study aimed to understand how changes in income due to the COVID-19 pandemic have affected the health behavior and mental health status of self-employed individuals. Methods: We compared the health behavior and mental health status of regular wage workers and self-employed individuals with no change in income, with that of self-employed individuals with reduced income due to the spread of COVID-19. Results Smoking status, average amount of smoking per day, changes in the amount of smoking and drinking due to COVID-19, drinking frequency per year, monthly binge drinking experiences, subjective stress, and suicidal thoughts experienced by self-employed individuals with decreased income were not only higher than those of wage workers and self-employed individuals with maintained income, but their happiness index was also lower than the latter group. Conclusion: This study suggests that the change in total household income due to COVID-19 adversely affects the health behavior and mental health status of self-employed individuals. However, COVID-19-related policies focus only on economic loss compensation, and the health behavior and mental health management for self-employed individuals is insufficient. Therefore, it is necessary to establish policies for health behavior and mental health management of self-employed individuals.

Purpose: This study uses data from the 12th~17th Korea Welfare Panel (2017~2022) to analyze changes in depression scores due to the COVID-19 outbreak and the factors that influenced depression scores according to employment type. Methods: The difference in depression scores according to employment types before COVID-19 (12th~14th) and after COVID-19 (15th~17th) was analyzed. A fixed-effect model analysis was conducted before and after the occurrence of COVID-19. Results: After the outbreak of COVID-19, job satisfaction and family life satisfaction influenced the depression scores of regular wage workers. After the outbreak of COVID-19, annual income, health status, and satisfaction with family life affected the depression scores of non-regular wage workers. After the outbreak of COVID-19, leisure life satisfaction and family relationship satisfaction influenced the depression scores of self-employed. Self-esteem played a role as a control variable in lowering the depression scores of regular and non-regular workers, but did not play a role as a control variable for self-employed. Conclusion Rather than the direct impact of infectious diseases such as COVID-19, social and economic changes resulting from policies implemented to prevent the spread affect workers' depression, and the impact varies depending on the type of employment. When implementing policies to prevent the spread of infectious diseases in the future, policies that take employment type into consideration rather than uniform policies should be prepared, and measures for mental health also need to be prepared.

Objective: Radiomic modeling using multiple regions of interest in MRI of the brain to diagnose juvenile myoclonic epilepsy (JME) has not yet been investigated. This study aimed to develop and validate radiomics prediction models to distinguish patients with JME from healthy controls (HCs), and to evaluate the feasibility of a radiomics approach using MRI for diagnosing JME. Materials and Methods: A total of 97 JME patients (25.6 ± 8.5 years; female, 45.5%) and 32 HCs (28.9 ± 11.4 years; female, 50.0%) were randomly split (7:3 ratio) into a training (n = 90) and a test set (n = 39) group. Radiomic features were extracted from 22 regions of interest in the brain using the T1-weighted MRI based on clinical evidence. Predictive models were trained using seven modeling methods, including a light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, with radiomics features in the training set. The performance of the models was validated and compared to the test set. The model with the highest area under the receiver operating curve (AUROC) was chosen, and important features in the model were identified. Results: The seven tested radiomics models, including light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, showed AUROC values of 0.817, 0.807, 0.783, 0.779, 0.767, 0.762, and 0.672, respectively. The light gradient boosting machine with the highest AUROC, albeit without statistically significant differences from the other models in pairwise comparisons, had accuracy, precision, recall, and F1 scores of 0.795, 0.818, 0.931, and 0.871, respectively. Radiomic features, including the putamen and ventral diencephalon, were ranked as the most important for suggesting JME. Conclusion Radiomic models using MRI were able to differentiate JME from HCs.