Machine learning-based models successfully screened potential medical aid beneficiaries. Qualitative analysis of important features well reflected prior knowledge regarding public health. These findings can contribute to the soundness of healthcare finance and the improvement of public health.

Machine learning-based models successfully screened potential medical aid beneficiaries. Qualitative analysis of important features well reflected prior knowledge regarding public health. These findings can contribute to the soundness of healthcare finance and the improvement of public health.

This study investigates the influence of changes in physical activity (PA) patterns on depression risk across different socioeconomic statuses (SES) in Korea. Utilizing National Health Insurance Data (NHID) from over 1.2 million individuals during 2013-2016, we matched medical aid beneficiaries with health insurance beneficiaries, excluding those with prior depression or incomplete PA data. Changes in moderate-to-vigorous PA (MVPA) were categorized into 16 groups, and depression incidence was tracked from 2019 to 2021. After adjustment, medical aid beneficiaries consistently showed higher risks of depression compared to health insurance enrollees with the same physical activity (PA) change patterns. For those consistently inactive, the risk was 1.68 times higher (aOR, 1.68; 95% CI, 1.37-2.05). Those who increased PA from inactivity to moderate-to-vigorous activity 3-4 times per week had a 3.33 times higher risk (aOR, 3.33; 95% CI, 1.72-6.43). Additionally, the risk was 2.64 times higher for those increasing from 1-2 times to ≥5 times per week (aOR, 2.64; 95% CI, 1.35-5.15), and 2.83 times higher for those consistently engaging in PA 3-4 times per week (aOR, 2.83; 95% CI, 1.35-5.94). Across the overall PA patterns, medical aid beneficiaries consistently faced higher depression risks, with risk increases of 1.80 times for increased activity, 1.68 times for continuous inactivity, and 1.34 times for decreased activity compared to health insurance beneficiaries with the same PA change patterns. However, in the consistently very active group, no significant difference in the risk of depression was observed between the two groups. Limitations include potential bias in self-reported PA and the NHIS data not fully capturing depression severity. The findings underscore the significant impact of SES on mental health, with consistently high PA levels potentially mitigating SES-related depression risk.

Among cancer survivors in South Korea, increased physical activity post-diagnosis was associated with a significantly lower risk of dementia. These findings underscore the importance of promoting physical activity in cancer survivors for cognitive health.