Objective: The aim of this study was to develop, compare, and validate models for predicting cardiovascular disease (CVD) mortality and hospitalization with hypertension using a conventional statistical model and a deep learning model. Methods: Using the database of Korean National Health Insurance Service, 2,037,027 participants with hypertension were identified. Among them, CVD (myocardial infarction or stroke) death and/or hospitalization that occurred within one year after the last visit were analyzed. Oversampling was performed using the synthetic minority oversampling algorithm to resolve imbalances in the number of samples between case and control groups. The logistic regression method and deep neural network (DNN) method were used to train models for assessing the risk of mortality and hospitalization. Findings: Deep learning-based prediction model showed a higher performance in all datasets than the logistic regression model in predicting CVD hospitalization (accuracy, 0.863 vs. 0.655; F1-score, 0.854 vs. 0.656; AUC, 0.932 vs. 0.655) and CVD death (accuracy, 0.925 vs. 0.780; F1-score, 0.924 vs. 0.783; AUC, 0.979 vs. 0.780). Interpretation: The deep learning model could accurately predict CVD hospitalization and death within a year in patients with hypertension. The findings of this study could allow for prevention and monitoring by allocating resources to high-risk patients.
National dementia plans were applied in dementia support centers established in Seoul, Korea between 2007 and 2009. However, the annual incidence rates of dementia in Seoul have not been reported. We investigated this annual incidence and the characteristics of incident cases from 2003 to 2018. The customized research database of the Korean National Health Insurance Services was used. The annual crude and age-standardized incidence of dementia patients and their characteristics were analyzed. This study analyzed 108,596 incident dementia cases aged ≥60 years. The incidence rate increased from 2003 to 2011, including a rapid increment from 2007 to 2011. From 2011 to 2018, the crude (age-standardized) incidence per 105 person-years decreased from 641.51 (577.12) to 448.26 (361.23). The proportion of incident dementia cases was highest in the highest income group every year. However, the proportion of incident dementia cases in the lowest income group increased from 10.4% in 2003 to 25.8% in 2011. The annual incidence rate of dementia showed a sharp increase immediately after 2007, the year dementia support centers began to be introduced, and then stabilized after 2011. The characteristics of incident dementia cases have changed, including the proportion in the low-income group.