• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.149-152
• /
• 2024

본 논문에서는 자치구별 집 가격과 인프라 데이터를 통한 분석을 기반으로, 저렴한 주택 지역에 입주하는 사람들의 우려와 관련하여 좋은 동네와 안좋은 동네의 차이를 다각도로 조망하고자 한다. DataSet은 서울 열린 데이터 광장과 보건의료 빅데이터 개방 시스템에서 수집한 공공데이터를 활용한다. dependent variable로는 자치구별 인프라 데이터셋을 사용하였으며, independent variable는 자치구별 집 가격을 기반으로 데이터 분석을 수행한다. 본 논문에서는 다양한 분석 기법을 활용하여 모델의 정확도와 신뢰성을 향상시키고, 이를 토대로 동네의 특징과 주거 환경의 차이를 명확히 도출하여 결론을 이끌어내고자 한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.3
• /
• pp.163-170
• /
• 2020

With the development of information and communication technologies, the growing volume of data is increasing exponentially, raising interest in big data. As technologies related to big data have developed, big data is being collected, stored, processed, analyzed, and utilized in many fields. Big data analytics in the health care sector, in particular, is receiving much attention because they can also have a huge social and economic impact. It is predicted that it will be able to use Big Data technology to analyze patients' diagnostic data and reduce the amount of money that is spent on simple hospital care. Therefore, in this thesis, patient data is analyzed to present to patients who are unable to go to the hospital or caregivers who do not have medical expertise with close care guidelines. First, the collected patient data is stored in HDFS and the data is processed and classified using R, a big data processing and analysis tool, in the Hadoop environment. Visualize to a web server using R Shiny, which is used to implement various functions of R on the web.

• Health Policy and Management
• /
• v.32 no.2
• /
• pp.154-163
• /
• 2022

Background: The costliness index (CI) is an index that is used in various ways to improve the quality of medical care and the management of appropriate treatment in medical institutions. However, the current calculation method for CI has a limitation in reflecting the actual medical cost of the patient unit because the outpatient and inpatient costs are evaluated separately. It is desirable to calculate the CI by integrating the medical cost into the episode unit. Methods: We developed an episode-based CI method using the episode classification system of the Centers for Medicare and Medicaid Services to the National Inpatient Sample data in Korea, which can integrate the admission and ambulatory care cost to episode unit. Additionally, we compared our new method with the previous method. Results: In some episodes, the correlation between previous and episode-based CI was low, and the proportion of outpatient treatment costs in total cost and readmission rates are high. As a result of regression analysis, it is possible that the level of total medical costs of the patient unit in low volume medical institute and rural area has been underestimated. Conclusion: High proportion of outpatient treatment cost in total medical cost means that some medical institutions may have provided medical services in the ambulatory care that are ancillary to inpatient treatment. In addition, a high readmission rate indicates insufficient treatment service for inpatients, which means that previous CI may not accurately reflect actual patient-based treatment costs. Therefore, an integrated patient-unit classification system which can be used as a more effective CI indicator is needed.

• Journal of the Korean Society of Radiology
• /
• v.15 no.5
• /
• pp.667-673
• /
• 2021

As we enter the era of the 4th industrial revolution, it is judged that the scope of work of radiologists will be further expanded according to the innovation and advancement of radiation medical technology development. In this study, the current status of medical equipment and radiology technicians was identified, and basic data were provided for the plan for nurturing talents in the field of radiation medical technology in the era of the 4th industrial revolution, as well as career and employment counseling. Data from the second quarter of 2020 and the second quarter of 2021 were analyzed using health and medical big data. As a result of comparing the status of medical equipment by type in 2021 compared to 2020, C-Arm X-ray examination equipment increased by 5.83% to 6,638 units, followed by MRI examination equipment 1,811 units 5.29%, and angiography equipment 725 units 5.22% , general X-ray examination equipment 21,557 units increased 3.99%, CT examination equipment 2,136 units 3.03%, and breast examination equipment 3,425 units increased 3.00%. As a result of a comparison of the total number of radiologists in 2021 compared to 2020, the number was 29,038, an increase of 2.73%. As a result of comparing the status of radiographers by region, the increase was highest in the Gyeonggi region with 5.96%, followed by the Gangwon region with a 5.66% increase and the Chungnam region with a 3.81% increase. In a situation where the number of medical equipment and radiologist manpower is increasing, universities are developing specialized knowledge and practical competency through subject development related to the understanding and utilization of customized artificial intelligence and big data that can be applied in the medical radiation technology field in the era of the 4th industrial revolution. It is necessary to nurture qualified radiographers, and at the level of the association, it is thought that active policies are needed to create new jobs and improve employment.

• The Korean Journal of Health Service Management
• /
• v.14 no.1
• /
• pp.93-102
• /
• 2020

Objectives: This study analyzed the prescription characteristics of medication for acute respiratory diseases before and after pay-for-performance to provide basic data on effective medical quality management policies. Methods: The research data were collected from the 2013-2014 sample cohort of the National Health Insurance Corporation, from Internal Medicine, Pediatrics, Otorhinolaryngology, Family Medicine and General practitioner clinics (classification of disease codes: J00-J06, J20-J22, J40 outpatients). Results: The antibiotics prescription rates decreased from 43.9% in 2013 to 43.5% in 2014 when the major diagnosis was for upper respiratory infections and increased from 62.0% in 2013 to 62.5% in 2014 when the major diagnosis was for lower respiratory infections. Conclusions: There is a need to identify the correct antibiotic prescription method by expanding the current assessment standards. Such standards must include acute lower respiratory infections and minor diagnoses as the current evaluation techniques focus only on the major diagnosis of acute upper respiratory infections.

• The Korean Journal of Health Service Management
• /
• v.13 no.4
• /
• pp.121-132
• /
• 2019

Objectives: This study analyzed the prescription antibiotics characteristics of Acute respiratory infection outpatients. It provides a basis for establishing the correct evaluation project on appropriate prescribing indicators. Methods: The research data were collected from the National Health Insurance Corporation's 2014 sample cohort for Internal Medicine, Pediatrics, Otorhinolaryngology, Family Medicine and General practitioner clinics classification of diseases codes J00-J06, J20-J22, J40 outpatients. Results: The antibiotic prescription rate on the evaluation project for appropriate prescribing indicators of Health Insurance Review & Assessment Service was 43.54%, whereas in this study it was about 10% higher because the analysis targeted the entire acute respiratory infection diagnosis. Conclusions: There is a need to identify the correct antibiotic prescription by expanding the current assessment standard. Such standard must include acute lower respiratory infections and minor diagnosis because current evaluation projects on appropriate prescribing indicators targets only the major diagnosis of acute upper respiratory infection.

• Korea Journal of Hospital Management
• /
• v.26 no.3
• /
• pp.56-67
• /
• 2021

There are few domestic studies on medical services in medically vulnerable areas where medical use is not met due to a lack of medical resources. The past studies on smart medicine targeting medically vulnerable areas grasp only the overall satisfaction level, or the sub-dimensions of satisfaction are not classified clearly. Also, it lacks consideration of the patient's needs. This study aims to analyze the effect of users' experience of the smart medicine pilot project conducted in medically vulnerable areas on satisfaction and demand. The user's experience was measured by variables in the dimensions of structure, process, and outcome. Among the pilot project participants, 282 subjects responded to the 2019 survey. Using the hierarchical regression method, we tried to find out the determinants of satisfaction and service demands. Experience factors affecting satisfaction were found to be accessibility, certainty, effectiveness, and efficiency. In addition, it was found that the demand in their 60s was high and that accessibility, certainty, effectiveness, and efficiency had a statistically significant effect on the demand. It is expected that the smart medicine pilot project will be effectively operated by well utilizing the factors influencing satisfaction and demand revealed in this study.

• 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.

• Proceedings of the Korea Contents Association Conference
• /
• 2017.05a
• /
• pp.33-34
• /
• 2017

In 2015, Ministry of Health and Welfare of Korea announced a research and development plan of using Korean healthcare data to support decision making, reduce cost and enhance a better treatment. This project relies on the adoption of BigData technology such as Apache Hadoop, Apache Spark to store and process HealthCare Data from various institution. Here we present an approach a design and implementation of OLAP server in Korean HealthCare BigData platform. This approach is used to establish a basis for promoting personalized healthcare research for decision making, forecasting disease and developing customized diagnosis and treatment.

• Journal of Digital Convergence
• /
• v.14 no.3
• /
• pp.319-327
• /
• 2016

This research attempts an analysis that fuses the big data concerning weather variation and health care from January 1, 2011 to December 31, 2014; it gives the weather factor as to what kind of influence there is for the incidence of food poisoning, and also endeavors to be helpful regarding national health prevention. By using R, the Logistic and Lasso Logistic Regression were analyzed. The main factor germ generating the food poisoning was classified and the incidence was confirmed for the germ of bacteria and virus. According to the result of the analysis of Logistic Regression, we found that the incidence of bacterial food poisoning was affected by the following influences: the average temperature, amount of sunshine deviation, and deviation of temperature. Furthermore, the weather factors, having an effect on the incidence of viral food poisoning, were: the minimum vapor pressure, amount of sunshine deviation and deviation of temperature. This study confirmed the correlation of meteorological factors and incidence of food poisoning. It was also found out that even if the incidence from two causes were influenced by the same weather factor, the incidence might be oppositely affected by the characteristic of the germs.