Development of a prediction model for the depression level of the elderly in low-income households: using decision trees, logistic regression, neural networks, and random forest.

Korea is showing the fastest trend in the world in population aging; there is a high interest in the elderly population nationwide. Among the common chronic diseases, the elderly tends to have a high incidence of depression. That said, it has been vital to focus on preventing depression in the elderly in advance. Hence, this study aims to select the factors related to depression in low-income seniors identified in previous studies and to develop a prediction model. In this study, 2975 elderly people from low-income families were extracted using the 13th-year data of the Korea Welfare Panel Study (2018). Decision trees, logistic regression, neural networks, and random forest were applied to develop a predictive model among the numerous data mining techniques. In addition, the wrapper's stepwise backward elimination, which finds the optimal model by removing the least relevant factors, was applied. The evaluation of the model was confirmed via accuracy. It was verified that the final prediction model, in the case of a decision tree, showed the highest predictive power with an accuracy of 97.3%. Second, psychological factors, leisure life satisfaction, social support, subjective health awareness, and family support ranked higher than demographic factors influencing depression. Based on the results, an approach focused on psychological support is much needed to manage depression in low-income seniors. As predicting depression in the elderly varies on numerous influencing factors, using a decision tree may be beneficial to establish a firm prediction model to identify vital factors causing depression in the elderly population.

Influential factors for COVID-19 related distancing in daily life: a distinct focus on ego-gram.

BACKGROUND: The coronavirus disease 2019 (COVID-19) has necessitated that individuals comply with personal quarantine rules in daily life. South Korea is implementing the concept of "distancing in daily life" to raise awareness on personal quarantine measures, which is communicated through various media channels and platforms. The continued rise in COVID-19 cases demands that all individuals strictly adhere to personal quarantine rules. It is worth paying particular attention to the college student group, which has the highest percentage of confirmed cases among all age groups in South Korea. This group understands and practices "distancing in daily life" but with drastic variations among individuals. Previous studies have reported that the level of adherence to social norms is different according to each ego stated, and media exposure level is reported as a major influencing factor. Therefore, this study examined the media exposure level to COVID-19 prevention rules and its effect on the observance of distancing in daily life; it also verified the moderating effect of ego-gram on the relationship between media exposure level and distancing in daily life. METHODS: The participants comprised Korean university students (men = 143, women = 188, N = 331) aged 18-30 years, who were recruited through an online survey. The survey was conducted over 20 days from January 27 to February 15, 2021. Data were analyzed using SAS (version 9.4) to calculate hierarchical regression. RESULTS: First, media exposure level and distancing in daily life among Korean university students was above average. Second, media exposure level (ß = .161, P < .01) was identified as the most influential factor for distancing in daily life. Third, ego-grams had a moderating effect (ß = .136, P < .05) on the relationship between media exposure levels and distancing in daily life. CONCLUSIONS: This study examined the policy implications related to the development of diverse quarantine-related programs while considering influential factors and differences in how individuals' compliance with quarantine rules were presented. Considering the situation in which new infectious diseases such as COVID-19 occur every 4-5 years, this study serves as a preparation for future pandemics and is an important framework to enhance the level of personal quarantine.

Effect of COVID-19 stress on physical function performance and socioenvironmental factors of people with disabilities in Korea.

This study investigated the effect of stress during the COVID-19 pandemic and the potential moderating effects of socioenvironmental factors on the physical conditions of Korean people with disabilities. Data from 405 participants on depression, instrumental activities of daily living and socioenvironmental factors were analyzed using frequency analysis, descriptive statistics, t-tests, one-way analysis of variance, Pearson's correlations and hierarchical regression analysis. Stress caused by COVID-19 was significantly correlated with depression, instrumental activities of daily living and social participation. Using socioenvironmental factors as moderators of the relationship between stress and depression, we found that increased depression was alleviated by social attitudes (ß = 2.064; P < 0.01), family attitudes (ß = 2.028; P < 0.05) and healthcare services and policies (ß = -4.579; P < 0.001). Moreover, instrumental activities of daily living increased with decreased stress as moderated by social attitudes (ß = 0.140; P < 0.05) and healthcare services and policies (ß = -0.306; P < 0.001). Further, increased social participation alleviated stress as moderated by social attitudes (ß = 0.106; P < 0.01), mobility and convenience facilities (ß = 0.158; P < 0.01) and healthcare services and policies (ß = -0.342; P < 0.001). The results indicate that even in public healthcare crises, it is important for people with disabilities to manage their health and participate in social activities. Their self-management and social participation can be promoted by strengthening community-centered rehabilitation and providing consumer-oriented social services.

The Effect of Changes in Employment on Health of Work-Related Injured Workers: A Longitudinal Perspectives.

This longitudinal study attempted to identify changes in employment status and overall health status. The participants were workers who had experienced work-related injuries in the past. In this study, we used the Panel Study of Workers' Compensation Insurance from 2013 to 2017. This study utilized propensity score matching for a quasi-experimental design study of the first year to exclude the effects of the confounding variables and exclude the effect of employment status, which is the main independent variable. After applying propensity score matching the research subjects totaled 1070. Changes in employment status were found to have a negative effect on overall health status. This raises new implications for existing industrial accident-related support policies. Thus, it is considered that the scope should be expanded from policies related to re-employment of workers after an industrial accident to improving quality of life through maintaining employment from a long-term perspective. The notable point of this study was to apply the PSM methods. By applying PSM, we clearly identified the effect of changes in employment status on health status.

Developmental trajectory and relationships between Adolescents' social capital, self-esteem, and depressive symptoms: A latent growth model.

The aim of this study was to evaluate the longitudinal influence of social capital and self-esteem on depressive symptoms among adolescents. A multivariate latent growth model was used to test secondary data obtained from the Korea Youth Panel Survey. Social capital and self-esteem tended to increase over periods of four years, whereas depressive symptoms had a tendency to decrease in the same periods. In the case of indirect effects on depressive symptoms by way of self-esteem, significant indirect associations were identified. The results indicated that the intercept of social capital had a significant indirect effect and total effect on the intercept of depressive symptoms. In addition, the slope of social capital had a significant indirect effect and total effect on the slope of depressive symptom. The initial development of social capital and self-esteem is shown to be effective for reducing adolescents' depressive symptoms.

Influence of various gypsum materials on precision of fit of CAD/CAM-fabricated zirconia copings.

The clinical applicability of CAD/CAM-fabricated zirconia copings is tested using working models made from four different highstrength Type IV gypsum materials. Each of the four materials was used to fabricate 15 zirconia copings. Precision of fit was measured with a digital electron microscope using the silicone replica technique. The mean and standard deviation of each reference point were analyzed using the one-way analysis of the variance (ANOVA) and Tukey's honest significant difference (HSD) tests (α=0.05). The overall marginal and internal fits of the zirconia copings were as follows: GS (GS: Grey Stone) group: 91.43 µm, LS (LS: Light green Stone) Group: 87.89 µm, RS (RS: Red Stone) Group: 88.75 µm, BS (BS: Beige Stone) Group: 82.78 µm. There were no significant differences between the mean adaptations of the gypsum varieties (p>0.05). This confirmed that the type of gypsum material used does not determine the precision of fit of a prosthesis.

Determinants of community capacity influencing residents' health status in Seoul, South Korea.

The effect of community capacity on health was evaluated by assessing the community via a questionnaire that included a capacity index in the social capital scale. The impact of the length of residence and the size and solidarity of networking on community capacity was also explored. The authors used logistic regression models controlling for sociodemographic factors and health behaviors among 1019 residents. The results indicate that lower community identity and social trust all led to statistically poor health levels. The manner in which members perceive their community was determined by cohesion, participation, length of residence, and the extent and strength of a member's network. Partnerships among and the subsequent organization of public resources by community members helped solidify the sense of community. With enhanced levels of sense of community, the collective level of health among residents can be readily and effectively improved.

A randomized controlled trial to determine the effect of spinal stabilization exercise intervention based on pain level and standing balance differences in patients with low back pain.

BACKGROUND: A number of studies have evaluated exercise interventions compared with other treatment strategies for subjects with recurrent low back pain (LBP); however, subject pain level and balance were not carefully considered. The purpose of this study was to investigate the effectiveness of spinal stabilization exercises (SSE) for managing pain and increasing balance strategy changes following unexpected perturbations in patients diagnosed with recurrent LBP. MATERIAL/METHODS: Twenty-one age- and gender-matched patients participated in a supervised SSE or control exercise program 5 times a week over a 4-week period. The Million Visual Analogue Scale (MVAS) and Oswestry Disability Index (ODI) were used to measure each patient's level of pain and disability. Balance measurements were derived from recordings of the anterior-posterior (A/P) and medio-lateral (M/L) center of pressure (COP) displacements during 3 consecutive, unexpected random perturbations. RESULTS: The level of reported pain and disability significantly decreased following treatment for both groups. Although the M/L sway was not significantly different in either group (p=0.86), there was a significant difference between group and measurement time during A/P sway (p=0.04). The A/P displacement of the SSE group significantly decreased compared with the control group. The decreased A/P displacement can be linked to the SSE intervention, which helps prevent further injury by limiting an individual's response rate to external perturbations. CONCLUSIONS: Clinicians might consider SSE for LBP patients as a possible rehabilitation strategy to reduce A/P displacement.

Predictive modeling of dental pain using neural network.

The mouth is a part of the body for ingesting food that is the most basic foundation and important part. The dental pain predicted by the neural network model. As a result of making a predictive modeling, the fitness of the predictive modeling of dental pain factors was 80.0%. As for the people who are likely to experience dental pain predicted by the neural network model, preventive measures including proper eating habits, education on oral hygiene, and stress release must precede any dental treatment.