Background: This study aimed to develop prediction models for the work-relatedness of shoulder diseases through machine learning algorithms. Methods: The dataset comprised 7,270 cases of 8,302 individuals who applied for occupational diseases and received the final approval decision from the Korea Workers' Compensation and Welfare Service's Disease Evaluation Committee, which is related to shoulder musculoskeletal disorders between January 2020 and December 2021. In this study, demographic analysis and difference of approval rate by shoulder diseases were performed. Additionally, machine learning algorithms, including logistic regression, support vector machine, decision tree, random forest, and the XGBoost, were utilized to construct prediction models for work-relatedness assessment. Results: The performance of each model was evaluated. XGBoost showed an accuracy of 81.64% and an area under the curve of 0.73, and random forest showed an accuracy of 84.46% and an area under the curve of 0.73. Key factors influencing work-relatedness assessment were employment period, physical burden score, gender, and age. Conclusion The application of various machine learning techniques showed high performance score, representing that it would be helpful to reduce the differences in judgment between occupational environment medicine physicians.

BACKGROUND: Disease burden can be represented by health-related parameters such as disability-adjusted life years and economic burden. Economic burden is an important index, as it estimates the maximum possible cost reduction if a disease is prevented. This study aimed to determine the economic burden of 238 diseases and 22 injuries in Korea in 2015. METHODS: Economic burden was estimated with a human resources approach from a social perspective, and direct and indirect costs were calculated from insurance claims data and a cause of death database. Direct costs were divided into medical costs (including hospital admission, outpatient visit, and medication use) and nonmedical costs (including transportation and caregiver costs). Indirect costs from lost productivity, either from the use of healthcare service or premature death, were analyzed. RESULTS: In 2015, the estimated economic burden was USD 133.7 billion (direct: USD 65.5 billion, indirect: USD 68.2 billion). The total cost of communicable diseases was USD 16.0 billion (11.9%); non-communicable diseases, USD 92.3 billion (69.1%); and injuries, USD 25.4 billion (19.0%). Self-harm had the highest costs (USD 8.3 billion), followed by low back pain (LBP, USD 6.6 billion). For men, self-harm had the highest cost (USD 7.1 billion), while LBP was the leading cost (USD 3.7 billion) for women. CONCLUSION A high percentage of Korea's total socioeconomic disease burden is due to chronic diseases; however, unnoticed conditions such as infectious diseases, injuries, and LBP are high in certain age groups and differ by gender, emphasizing the need for targeted social interventions to manage and prevent disease risk factors.

OBJECTIVES: The aim of this study was to investigate continuously on how a short-term family psychoeducation program for schizophrenia would change the emotional stress and the knowledge of the family members. METHODS: Subjects were the family members who participated in the short-term family psychoeducation program for schizophrenia. The participants were asked to fill out self-reporting forms for 3 times-before commencing the 6-week family education, immediately after completing the program, and 3 months after completing the program respectively. RESULTS: A total of 46 subjects participated, and 20 of them responded to all questionnaires. Three months after the completion of psychoeducation, depression and anxiety subscale score among the General Health Questionnaire-28 decreased by 2.60 (p=0.04) and 2.20 (p=0.04) respectively. In caregiver burden criterion, the score decreased by 9.45 (p=0.04) in 3 months after completing the education. In knowledge about schizophrenia test, the score increased by 2.60 score (p<0.001), and this result was maintained after 3 months. CONCLUSION: It was found that a short-term family education program for schizophrenia was effective not only in improving the knowledge on the disease but also in reducing anxiety and depression, and this effect was maintained immediately after the psychoeducation and so was it as time passed as well.
Anxiety ; Caregivers ; Depression ; Education ; Humans ; Surveys and Questionnaires ; Schizophrenia* ; Stress, Psychological