• Health Policy and Management
• /
• v.27 no.3
• /
• pp.199-210
• /
• 2017

Background: This paper aims to demonstrate current health expenditure (CHE) and National Health Accounts of the years 2015 constructed according to the SHA2011, which is a new manual of System of Health Accounts (SHA) that was published jointly by the Organization for Economic Cooperation and Development (OECD), Eurostat, and World Health Organization in 2011. Comparison is made with international trends by collecting and analysing health accounts of OECD member countries. Particularly, financing public-private mix is parsed in depth using SHA data of both HF as financing schemes as well as FS (financing source) as their revenue types. Methods: Data sources such as Health Insurance Review and Assessment Service's publications of both motor insurance and drugs are newly used to construct the 2015 National Health Accounts. In the case of private financing, an estimation of total expenditures for revenues by provider groups is made from the Economic Census data; and the household income and expenditure survey, Korean healthcare panel study, etc. are used to allocate those totals into functional classifications. Results: CHE was 115.2 trillion won in 2015, which accounts for 7.4 percent of Korea's gross domestic product. It was a big increase of 9.3 trillion won, 8.8 percent, from the previous year. Government and compulsory schemes's share (or public share) of 56.4% of the CHE in 2015 was much lower than the OECD average of 72.6%. 'Transfers from government domestic revenue' share of total revenue of HF was 17.8% in Korea, lower than the other contribution-based countries. When it comes to 'compulsory contributory health financing schemes,' 'Transfers from government domestic revenue' share of 14.9% was again much lower compared to Japan (44.7%) and Belgium (34.8%) as contribution-based countries. Conclusion: Considering relatively lower public financing share in the inpatient care as well as overall low public financing share of total CHE, priorities in health insurance coverage need to be repositioned among inpatient care, outpatient care and drugs.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.126-136
• /
• 2018

The purpose of this study was to develop a severity-adjustment model for predicting mortality in acute stroke patients using machine learning. Using the Korean National Hospital Discharge In-depth Injury Survey from 2006 to 2015, the study population with disease code I60-I63 (KCD 7) were extracted for further analysis. Three tools were used for the severity-adjustment of comorbidity: the Charlson Comorbidity Index (CCI), the Elixhauser comorbidity index (ECI), and the Clinical Classification Software (CCS). The severity-adjustment models for mortality prediction in patients with acute stroke were developed using logistic regression, decision tree, neural network, and support vector machine methods. The most common comorbid disease in stroke patients were hypertension, uncomplicated (43.8%) in the ECI, and essential hypertension (43.9%) in the CCS. Among the CCI, ECI, and CCS, CCS had the highest AUC value. CCS was confirmed as the best severity correction tool. In addition, the AUC values for variables of CCS including main diagnosis, gender, age, hospitalization route, and existence of surgery were 0.808 for the logistic regression analysis, 0.785 for the decision tree, 0.809 for the neural network and 0.830 for the support vector machine. Therefore, the best predictive power was achieved by the support vector machine technique. The results of this study can be used in the establishment of health policy in the future.