• Health Policy and Management
• /
• v.8 no.2
• /
• pp.76-87
• /
• 1998

This study analyzed the effect of foreign currency exchange rate on the increasing rate of medical care cost by items of fee schedule of Korean Medical Insurance. This study uses the data of cost analysis including cost of imported goods and the data of for a university hospital National Federation's Medical Insurance for a trend of claim. The method of cost analysis is as same as that used in the study of the development of Korean RBRVS(Resource Based Relative Valus Scale). The main findings of this study are as follows; 1. The proportion of imported goods in cost related to Medical Insurance fee schedule is 7.93%, and in case of substitution of available domestic goods 6.96%. 2. If foreign currency exchange rate changes from 800wen per $1 to 1,300won, the affecting rate of Medical Insurance fee schedules is 5.00%. If the imported goods will be substituted with available domestic goods, the rate 4.35%. Our results can be used a data for updating Medical Insurance fee schedule. But this result is limited to be generalized, because this study used the cost analysis for a university hospital.

• Annual Conference of KIPS
• /
• 2013.05a
• /
• pp.695-697
• /
• 2013

Medical data sharing is increasing due to treatment duplication which increases the cost of medication. Medical healthcare system has been improved to combine with cloud computing. It reduces treatment delay and the medical data error. However, the concern about the privacy protection of medical information is also significant. Medical information is more sensitive than other information because involuntary disclosure can affect in both personal and social life. Privacy cloud brokerage has conquered great attention for solving these problems. Our method provides a security model in the cloud computing environment that facilitates the exchange of medical records between assigned custodians. It allows doctors to obtain a complete patient medical records which can help to avoid duplication, reduce the medical error and healthcare cost as well. In addition, our method offers a trustworthy solution against the privacy violence.

• Industrial Engineering and Management Systems
• /
• v.4 no.1
• /
• pp.102-108
• /
• 2005

This paper studies medical data classification methods, comparing decision tree and system reconstruction analysis as applied to heart disease medical data mining. The data we study is collected from patients with coronary heart disease. It has 1,723 records of 71 attributes each. We use the system-reconstruction method to weight it. We use decision tree algorithms, such as induction of decision trees (ID3), classification and regression tree (C4.5), classification and regression tree (CART), Chi-square automatic interaction detector (CHAID), and exhausted CHAID. We use the results to compare the correction rate, leaf number, and tree depth of different decision-tree algorithms. According to the experiments, we know that weighted data can improve the correction rate of coronary heart disease data but has little effect on the tree depth and leaf number.

• Journal of Trauma and Injury
• /
• v.29 no.4
• /
• pp.155-160
• /
• 2016

Purpose: Two years have passed since a level I trauma center was officially opened in the Gacheon Gil Hospital, South Korea. We analyzed 2014 and 2015 registered patient data from the Korean Trauma Data Base (KTDB) to identify trends in trauma patient care and factors that influence the quality of trauma care at the Gacheon Gil trauma center. Methods: Data was extracted from the KTDB included patient age, sex, systolic blood pressure at emergency room arrival, revised trauma score, injury severity score, trauma injury severity score, transfusion amount, and the cause of death was analyzed. Results: A total of 3269 trauma patients were admitted to our trauma center in 2014 and 3225 in 2015. Demographics and mechanism of injury were not significantly different between years. The severity of trauma injury was decreased in 2015 although the mortality rate was slightly increased. This requires further analysis. Conclusion: The aim of this study was to determine the general status and trends in trauma incidence and management outcomes for the Incheon area. We noted no significant changes in trauma status from 2014 to 2015. We need to collect and review trauma patient data over a long period in order to elucidate trauma incidence and management trends in the trauma field. Finally, studies using trauma patient data will indicate appropriate quality control factors for trauma care and help to improve the quality of trauma management.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.12
• /
• pp.7251-7256
• /
• 2013

Objectives: To estimate the proportion of liver cancer cases and deaths due to infection with hepatitis B virus (HBV), hepatitis C virus (HCV), aflatoxin exposure, alcohol drinking and smoking in China in 2005. Study design: Systemic assessment of the burden of five modifiable risk factors on the occurrence of liver cancer in China using the population attributable fraction. Methods: We estimated the population attributable fraction of liver cancer caused by five modifiable risk factors using the prevalence data around 1990 and data on relative risks from meta-analyses, and large-scale observational studies. Liver cancer mortality data were from the 3rd National Death Causes Survey, and data on liver cancer incidence were estimated from the mortality data from cancer registries in China and a mortality/incidence ratio calculated. Results: We estimated that HBV infection was responsible for 65.9% of liver cancer deaths in men and 58.4% in women, while HCV was responsible for 27.3% and 28.6% respectively. The fraction of liver cancer deaths attributable to aflatoxin was estimated to be 25.0% for both men and women. Alcohol drinking was responsible for 23.4% of liver cancer deaths in men and 2.2% in women. Smoking was responsible for 18.7% and 1.0%. Overall, 86% of liver cancer mortality and incidence (88% in men and 78% in women) was attributable to these five modifiable risk factors. Conclusions: HBV, HCV, aflatoxin, alcohol drinking and tobacco smoking were responsible for 86% of liver cancer mortality and incidence in China in 2005. Our findings provide useful data for developing guidelines for liver cancer prevention and control in China and other developing countries.

• Research in Community and Public Health Nursing
• /
• v.26 no.1
• /
• pp.11-17
• /
• 2015

Purpose: This study was to ascertain whether there are differences in health care utilization and expenditure for Type I Medical Aid Beneficiaries before and after applying Copayment. Methods: This study was one-group pretest posttest design study using secondary data analysis. Data for pretest group were collected from claims data of the Korea National Health Insurance Corporation and data for posttest group were collected through door to-door interviews using a structured questionnaire. A total of 1,364 subjects were sampled systematically from medical aid beneficiaries who had applied for copayment during the period from December 12, 2007 to September 25, 2008. Results: There was no negative effect of copayment on accessibility to medical services, medication adherence (p=.94), and quality of life (p=.25). Some of the subjects' health behaviors even increased preferably after applying for copayment including flu prevention (p<.001), health care examination (p=.035), and cancer screening (p=.002). However, significant suppressive effects of copayment were found on outpatient hospital visiting days (p<.001) and outpatient medical expenditure (p<.001). Conclusion: Copayment does not seem to be a great influencing factor on beneficiaries' accessibility to medical services and their health behavior even though it has suppressive effects on outpatients' use of health care.

• The Journal of Korean Obstetrics and Gynecology
• /
• v.21 no.3
• /
• pp.218-230
• /
• 2008

Purpose: This study was performed to investigate the percentage of the oriental medical Ob & GY disease group in Korean Medical Health Insurance and to gain the basic data of enlargement and improvement of Acupuncture Benefits in the oriental medical Ob & Gy field. Methods: We requested data about the status of Insurance Benefits in 2005. 2006 to Health Insurance Review & Assessmenstatus Service(HIRA). And on the basis of this 2005. 2006 data, we analyzed the status of Insurance Benefits and Acupuncture Benefits in the oriental medical Ob & Gy disease group. Results: 1. Total health care benefit costs of Korean medical health insurance in 2005, 2006 took 4.38 percent and 4.25 percent of total health care benefit costs of Health insurance. 2. Total health care benefit costs of the oriental medical Ob & Gy disease group in 2005, 2006 took 0.38 percent and 0.40 percent of total health care benefit costs of Korean medical health insurance. 3. The percentage of Acupuncture benefits costs of the oriental medical Ob & Gy disease group in 2005, 2006 was merely 0.22 percent and 0.23 percent of total Acupuncture Benefits costs. 4. The main sick and wounded name of Ob & Gy diseases of Acupuncture Benefits was limited to Menstrual Disorder(K01)과- Uterus Abnormality(K13). Conclusion: The percentage of the oriental medical Ob & Gy disease group in Korean Medical Health Insurance was very low and the percentage of Acupuncture Benefits of he oriental medical Ob & Gy disease group was also very low. From now on, Searching ay of enlargement of Acupuncture Benefits in the oriental medical Ob & Gy field is required.

• The Korean Journal of Emergency Medical Services
• /
• v.25 no.2
• /
• pp.19-38
• /
• 2021

Purpose: This study aimed to investigate the relationship between emergency medical service accessibility in different regions and the sudden death rate in elderly patients with ischemic heart disease using data analysis techniques and suggest improvements in regional emergency medical services. Methods: The study collected data from the NEDIS database and Statistics Korea. Data on a total of 75,867 patients aged ≥65 years were reviewed among patients with ischemic heart disease who visited emergency medical institutions in 2018. Frequency analysis, chi-square test, multiple logistic regression analysis, and simple logistic regression analysis were performed using SPSS PC Window 25.0. Results: With an emergency medical resource per 100km², there was a concomitant reduction in the risk of death. There was a decrease in the death rate by 0.967, 0.970, 0.997, and 0.391 times with the increase in the presence of a fire department, an ambulance, a paramedic, and a regional medical center, respectively. Furthermore, a decrement in the death rate was witnessed 0.844, 0.825, and 0.975 times with the initiation of a local emergency medical center, a local emergency medical institution, and an angiography device, respectively(p <.001). Conclusion: To improve the accessibility of emergency medical services, the population and geometric area of the region should be considered essential factors when deploying emergency medical resources.

• Korean Journal of Radiology
• /
• v.25 no.3
• /
• pp.224-242
• /
• 2024

The emergence of Chat Generative Pre-trained Transformer (ChatGPT), a chatbot developed by OpenAI, has garnered interest in the application of generative artificial intelligence (AI) models in the medical field. This review summarizes different generative AI models and their potential applications in the field of medicine and explores the evolving landscape of Generative Adversarial Networks and diffusion models since the introduction of generative AI models. These models have made valuable contributions to the field of radiology. Furthermore, this review also explores the significance of synthetic data in addressing privacy concerns and augmenting data diversity and quality within the medical domain, in addition to emphasizing the role of inversion in the investigation of generative models and outlining an approach to replicate this process. We provide an overview of Large Language Models, such as GPTs and bidirectional encoder representations (BERTs), that focus on prominent representatives and discuss recent initiatives involving language-vision models in radiology, including innovative large language and vision assistant for biomedicine (LLaVa-Med), to illustrate their practical application. This comprehensive review offers insights into the wide-ranging applications of generative AI models in clinical research and emphasizes their transformative potential.

• International Journal of Advanced Culture Technology
• /
• v.5 no.2
• /
• pp.82-89
• /
• 2017

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the GradientDescentOptimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.