• Health Policy and Management
• /
• v.30 no.1
• /
• pp.15-25
• /
• 2020

While healthcare data sets include extensive information about patients, many researchers have limitations in analyzing them due to their intrinsic characteristics such as heterogeneity, longitudinal irregularity, and noise. In particular, since the majority of medical history information is recorded in text codes, the use of such information has been limited due to the high dimensionality of explanatory variables. To address this problem, recent studies applied word embedding techniques, originally developed for natural language processing, and derived positive results in terms of dimensional reduction and accuracy of the prediction model. This paper reviews the deep learning-based natural language processing techniques (word embedding) and summarizes research cases that have used those techniques in the health care field. Then we finally propose a research framework for applying deep learning-based natural language process in the analysis of domestic health insurance data.

• Journal of Medicine and Life Science
• /
• v.16 no.3
• /
• pp.90-95
• /
• 2019

The Korea Centers for Diseases Control and Prevention interpreted that recent outbreaks of scarlet fever in Korea since 2011 was resulted from the expansion of scarlet fever notification criteria. To suggest a relevant hypothesis regarding this emerging outbreak, a time series analysis(TSA) of scarlet fever incidence between 2002 and 2016 was conducted. The raw data was the nationwide insurance claims database administered by the Korean National Health Insurance Service. The inclusion criteria were children aged ≤14 years residing in Jeju Province, Korea who received any form of healthcare for scarlet fever from 2002 to 2016. The season was defined as winter (December, January, February; Q1), spring (March, April, May; Q2), summer (June, July, August; Q3), and autumn (September, October, November; Q4). There were seasonal variations with showing peak season on Q1 and Q3. And three phases as 2002 Q2~2005 Q2, 2005 Q2~2009 Q4, and 2010 Q1~2016 Q4 were found between 2002 and 2016. The results from TSA suggested that the recent outbreak of scarlet fever among children in Jeju Province might be a phenomenon from 'unknown birth-related environmental factors' changed after 2010.

• Health Policy and Management
• /
• v.22 no.4
• /
• pp.579-596
• /
• 2012

The purpose of the study is to examine the use of medication among adults by comparing the pattern of outpatient prescription drug use with the pattern of long term taking lifestyle drug use. Furthermore, the study investigates factors associated with the use of medication, particularity focusing on socioeconomic factors. Korea Health Panel data of 2008 was used to conduct the study analysis. By performing four different logistic regression models, the study noticed different patterns of the medication use between prescription drugs and lifestyle drugs. More specifically, the study showed that adults with lower education level tend to more frequently receive prescriptions while adults with higher education as well as income level tend to more use lifestyle drugs than their counterparts. Furthermore, other control factors such as age and gender were statistically significant for the use of both prescription and lifestyle drugs in different patterns. The study findings expect that reimbursement structure of drugs may be significantly associated with the different patterns and accordingly the accessability of medicine in particularly vulnerable population. Therefore, these policy factors should be considered in future study to more comprehensively understand about the diverse patterns in the medication use.

• The Korean Journal of Health Service Management
• /
• v.6 no.4
• /
• pp.143-152
• /
• 2012

This study analyzes Korea health panel data (2008) (beta version 1.2) of Korea Institute for Health and Social Affairs, and National Health Insurance Corporation to figure out determinants of healthcare expenditure. In result of Multiple Logistic Analysis, in-patents felt burden on the medical expenditure were 70.0%. As to the patients' payment of medical expenditure, patients over 65 years old had 4.765 times higher than those under 14 years, disabled patients 2.778 than non-disabled patients, chronic patients 1.632 times than non-chronic patients, patients belonging to 12 million won ~ 46 million won and under 12 million won in family income had 1.680 times and 2.168 times respectively than patients with over 46 million won, patients in professional recuperation facility 1.546 times than patients in hospital, patients in private medical institutions 1.700 times than patients in national and public medical institutions, patients using upper grade rooms 1.701 times than patients in non-upper grade rooms. As a health care safety net mechanism to protect people from medical expenditure burden, there is the patients' payment ceiling in the National Health Insurance System. Thus, in order to facilitate the patient's payment ceiling, it is required that the level of ceiling is to be specified according to the income level, and self-payment items is to be included.

• Journal of Intelligence and Information Systems
• /
• v.6 no.1
• /
• pp.73-82
• /
• 2000

This study examined the characteristicso f the knowledge discovery and data mining algorithms to demonstrate how they can be used to predict health outcomes and provide policy information for hypertension management using the Korea Medical Insurance Corporation database. Specifically this study validated the predictive power of data mining algorithms by comparing the performance of logistic regression and two decision tree algorithms CHAID (Chi-squared Automatic Interaction Detection) and C5.0 (a variant of C4.5) since logistic regression has assumed a major position in the healthcare field as a method for predicting or classifying health outcomes based on the specific characteristics of each individual case. This comparison was performed using the test set of 4,588 beneficiaries and the training set of 13,689 beneficiaries that were used to develop the models. On the contrary to the previous study CHAID algorithm performed better than logistic regression in predicting hypertension but C5.0 had the lowest predictive power. In addition CHAID algorithm and association rule also provided the segment characteristics for the risk factors that may be used in developing hypertension management programs. This showed that data mining approach can be a useful analytic tool for predicting and classifying health outcomes data.

• Health Policy and Management
• /
• v.31 no.4
• /
• pp.399-408
• /
• 2021

The emergency medical service system in Korea was built upon the Emergency Medical Service Act, 1995 to respond adequately to be much in demand for emergency medical services. In addition, the government recognized the importance of the trauma care system and set out to plan for the designation and establishment of the regional trauma center by 2012. This study aimed to investigate features of quality management and trauma fee schedule on better understanding of trauma care system. First, quality management of the regional trauma center has been implemented by several quality programs involved in quality assessment, committee on trauma quality management, and mortality and morbidity conference. Second, the trauma fee schedule has reflected a specific quality of severe traumatic conditions and added the result to it, which are graded A, B, and C according to quality assessment. Although the government has contributed to instituting a trauma quality assessment program and trauma fee schedule for the regional trauma center, it could not lead to such a fixed standard for quality management of them. Therefore, it will promote discussion on the sustainability of the regional trauma center that requires reducing preventable trauma death rate and the way to apply comprehensive quality management.

• The Korean Journal of Health Service Management
• /
• v.12 no.3
• /
• pp.13-26
• /
• 2018

Objectives: This study investigated how Korean daily newspapers frame the present government's health insurance coverage expansion policy, Moon Jae-in Care. Methods: A contents analysis was conducted to construct news frames represented in the four Korean daily newspapers' editorials and columns on Moon Jae-in Care during from April 2017 to April 2018. News text was classified into three different layers of frames: expressive element, narrative structure, and implied values. Results: The analysis revealed that the frequency of narrative frames was as follows: health system improvement (20.8%), public burden (14.6%), opposition by doctors (14.6%), and populism (12.5%). The financial sustainability accounted for 41.7% of the value frame, followed by procedural legitimation (18.8%), and coverage expansion (16.7%). The results also revealed that reported frames were different among newspapers: Chosun Ilbo tended to report in a negative tone, while Hankyoreh shinmun and Kyunghyang shinmun used a positive tone. Conclusions: This finding suggests that there are salient framings in reports on Moon Jae-in Care. Based on the results, the government needs to present a detailed financing plan on Moon Jae-in Care in detail. I discussed another implication of media frames results.

• Health Policy and Management
• /
• v.31 no.1
• /
• pp.17-23
• /
• 2021

With the introduction of national health insurance, the burden of health care costs decreased and choices of medical services widened. However, because of the rapid expansion of non-covered medical services by health insurance, financial security for health care expenditure is still low. This gives patients barriers to choose medical services especially for non-covered medical services, and it becomes narrower. Compared to Korea, Japan has high financial protection in health care utilization, but there exists a limitation using covered and non-covered medical services both together. This is called a prohibition of mixed treatment in health care. This study reviews the Japanese health care system that limits choosing medical services and the burden of health care costs. The prohibition of mixed treatment can alleviate the out-of-pocket burden in the non-benefit sector, but it can be found that it has a huge limitation in that it places restrictions on choices for both healthcare professionals and patients.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.314-323
• /
• 2021

The purpose of this study is to analyze the status of medical service use of foreigners living in Korea by their nationality and types of national health insurance. As of 2018, 1,058,886 people were extracted from the qualification DB, excluding people whose insurance premium is missing. The data analysis showed that nearly 78% of foreigners with national health insurance used medical services and the countries with the largest number of users were China, Vietnam, and the United States. The total cost of treatment per capita was highest in the United States regardless of hospitalization and outpatient. The number of medical treatments per person, and the medical expenses of outpatients & inpatients services were highest among the regionally-insured and the length of stay per person was highest among the workers' dependents. Lastly, it was found that Chinese and regionally-insured received much more benefits than other groups compared to the premium they pay. After July 2019, foreign nationals residing in Korea for six months or longer are obligated to enroll in the national health insurance program. Since the latest data was in 2018, the result did not properly reflect the current situation, but it is meaningful that it made basic data for future comparative analysis.

• Health Policy and Management
• /
• v.27 no.2
• /
• pp.128-138
• /
• 2017

Background: The purpose of this study is to analyze the effects of differential coinsurance policy on prescription drug coverage of outpatients by types of medical institutions. Methods: In this study, we used a sample cohort database of the National Health Insurance Service and frequency analysis and marginal logistic regression model using generalized estimating equation were used for statistical analysis. Results: The summary on the major research is followed. First, about 16% of patients who used only tertiary or general hospital due to 52 ambulatory care sensitive conditions before policy implementation moved to hospitals and clinics. However, about 57% of them still use tertiary or general hospital. Second, the factors influencing the utilization of hospitals and clinics after the implementation of the policy were gender, age, and income level. As a result, the policy is effective to reduce the medical use of outpatient mental patients in tertiary or general hospital, but the effect is not significant. Conclusion: Therefore, in order to achieve the purpose of the policy for establishing the health care delivery system, it is necessary to adjust the co-payment so as to feel the burden on the co-payment when the outpatient for 52 ambulatory care sensitive conditions is used at the tertiary or general hospital.