• Journal of the Health Care and Life Science
• /
• v.11 no.1
• /
• pp.105-114
• /
• 2023

This study aims to analyze the secondary data of disease distribution and medical service behavior according to gender and income by using the 17th wave data of the Korea Welfare Panel, which is being distributed in April 2023. Data for 7,865 people of raw data generated using the R language were collected, and among them, missing values (NA, - 2,012) were analyzed for 5,853 people. For analysis, average income by health status and gender, relationship with chronic diseases, outpatient visits to medical institutions by gender/age group, type of medical institution used by age group, and annual health checkup usage rate by gender/age group were examined. Through this, the medical utilization rate was higher in men than in women, and the utilization rate of hospitals and clinics was high.

• Korean Public Health Research
• /
• v.44 no.4
• /
• pp.35-49
• /
• 2018

Objective : The purpose of this study was to investigate the risk factors of dehydration from the subjects who underwent anthropometric and blood parameters testing during a comprehensive health screening. Methods : For the study analysis, 5,391 samples with valid data of the levels of Sodium($Na^+$), BUN (Blood Urea Nitrogen) and FBS(Fasting Blood Sugar) were selected to calculate a dehydration indicator of plasma osmolality. The study data was collected from the health screening examinees who visited Sahmyook Medical Center Seoul Adventist Hospital Comprehensive Health Check-up Center from 2014.01.01 to 2015.12.31. The relationship between dehydration and age group, BMI, disease exposures(hypertension, diabetes mellitus, dyslipidemia, kidney disorder) were analyzed by gender. Results : The odds ratio of dehydration showed statistical significance from age ${\geq}50$ in both male and female, respectively. The female obese group was vulnerable to dehydration while the male study group showed no statistical significance in the BMI difference. The disease exposed groups(hypertension, diabetes mellitus, dyslipidemia, kidney disorder) were vulnerable to dehydration. Also, the more types of disease carried by the exposed patients, the higher odds ratio and susceptibility to dehydration. Conclusions : Aging, increasing BMI, and exposed to diseases were found to be the risk factors for vulnerability to dehydration. To prevent dehydration, special caution to be taken for those in the ${\geq}50s$ group, along with controlling BMI and chronic diseases. Further studies are suggested to investigate the risk factors of dehydration that may affect increasing plasma osmolality as a potential stimulus mechanism in disease outbreaks.

• Journal of Advanced Navigation Technology
• /
• v.25 no.1
• /
• pp.96-101
• /
• 2021

This paper presents a machine learning model that predicts stroke risks in atrial fibrillation patients using public big data. As the training data, 68 independent variables including demographic, medical history, health examination were collected from the Korean National Health Insurance Service. To predict stroke incidence in patients with atrial fibrillation, we applied deep neural network. We firstly verify the performance of conventional statistical models (CHADS2, CHA2DS2-VASc). Then we compared proposed model with the statistical models for various hyperparameters. Accuracy and area under the receiver operating characteristic (AUROC) were mainly used as indicators for performance evaluation. As a result, the model using batch normalization showed the highest performance, which recorded better performance than the statistical model.

• Information Systems Review
• /
• v.14 no.2
• /
• pp.1-19
• /
• 2012

Recently due to the enhancement of education and lifestyle, the trend of healthcare services are changed to a more active and differentiated service in which a continuous self health care is possible. The Smart-Telemedicine system offers medical services by merging Blue-tooth and telecommunication modules to former blood pressure, blood sugar, heartbeat and temperature measuring devices. Moreover, it could analyze one's health pattern which would be helpful for the patient to prevent potential future illness. In addition, the easier accesses to various remote controllable medical check-up programs are offered to public as a number of available smart phone are rapidly escalating. The Smart-Telemedicine system provides the most ideal interactive medical service via accessible smart phones and mobile medical check-up devices at anywhere and anytime. It is very beneficial since it can save patients' time and money because people can reach to the service right at their home and be allowed to take charge of their health care process via longitudinal health data. Therefore, not only social costs that occur in elderly community would be saved, but also business in various forms of medical service field transactions could be possible. This paper will suggest the Smart-Telemedicine System for preventive medicine, its design and analysis of business models and the evaluation of those model.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.6
• /
• pp.1253-1261
• /
• 2010

We develope the predictive model for the incidence of the stomach cancer by utilizing the health screening data of the National Health Insurance in Korea. We also explore the characteristics for the stomach cancer. We perform the logistic regression analysis using the data mining methodology and use SAS Enterprise Miner 4.1. This study shows that there exists a higher rate of the stomach cancer for males than females. Our study confirms that the major influencing factors for the incidence of the stomach cancer are age, drinking and a family history of cancer, lack of exercise. For man, the age is the most important determinant of the stomach cancer incidence, whereas the drinking is the most important determinant of the stomach cancer incidence for women.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.151-155
• /
• 2019

Recently heart attack is 80% of the sudden death of elderly. The causes of a heart attack are complex and sudden, and it is difficult to predict the onset even if prevention or medical examination is performed. Therefore, early diagnosis and proper treatment are the most important. In this paper, we show the accuracy of normal and abnormal classification with neural network using weighted fuzzy function for accurate and rapid diagnosis of myocardial infarction. The data used in the experiment was data from the UCI Machine Learning Repository, which consists of 14 features and 303 sample data. The algorithm for feature selection uses the average of weight method. Two features were selected and removed. Heart attack was classified into normal and abnormal(1-normal, 2-abnormal) using the average of weight method. The test result for the diagnosis of heart attack using a weighted fuzzy neural network showed 87.66% accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.201-208
• /
• 2021

This study aims to provide the relevant basis upon which prediction of dyslipidemia should be made based on body information. Using the National Health Insurance big data (3,312,971 people) canonical correlation analysis was performed between body information and lipid-profile. Body information included age, height, weight and waist circumference, while the lipid-profile included total cholesterol, triglycerides, HDL cholesterol and LDL cholesterol. As a result, when the waist circumference and the weight are large, triglycerides increase and HDL cholesterol level decreases. In terms of age, weight, waist circumference, and HDL cholesterol, the canonical variates (the degree of influence) were significantly different according to sex. In particular, the canonical variate was dramatically changed around the forties and fifties in women in terms of weight, waist circumference, and HDL cholesterol. The canonical correlation results of the health care big data presented in this study will help construct a predictive model that can evaluate an individual's health status based on body information that can be easily measured in a non-invasive manner.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.9
• /
• pp.177-187
• /
• 2013

Association rule mining is a popular data mining technique with a wide range of application domains, and aims to extract the cause-and-effect relations between the discrete items included in transaction data. However, analysts sometimes have trouble in interpreting and using the plethora of association rules extracted from a large amount of data. To address this problem, this paper aims to propose a novel approach called HTM for extracting the interesting association rules from given transaction data. The HTM approach consists of three main steps, hierarchical clustering, table-view, and mosaic plot, and each step provides the analysts with appropriate visual representation. For illustration, we applied our approach for analyzing the mass health examination data, and the result of this experiment reveals that the HTM approach help the analysts to find the interesting association rules in more effective way.

• The Korean Journal of Applied Statistics
• /
• v.21 no.4
• /
• pp.639-647
• /
• 2008

This study used the characteristics of the knowledge discovery and data mining algorithms to develop tailored hypertension follow up management model - hypertension care predictive model and hypertension care compliance segmentation model - for hypertension management using the Korea National Health Insurance Corporation database(the insureds’ screening and health care benefit data). This study validated the predictive power of data mining algorithms by comparing the performance of logistic regression, decision tree, and ensemble technique. On the basis of internal and external validation, it was found that the model performance of logistic regression method was the best among the above three techniques on hypertension care predictive model and hypertension care compliance segmentation model was developed by Decision tree analysis. This study produced several factors affecting the outbreak of hypertension using screening. It is considered to be a contributing factor towards the nation’s building of a Hypertension follow up Management System in the near future by bringing forth representative results on the rise and care of hypertension.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.1
• /
• pp.199-204
• /
• 2020

With the development of IT. convergence systems are applied and operated in many different fields. A representative field among them is medical service, which develops in diverse types in combination with nano-technology and bio technology. However, there is a lack of technical innovation in terms of medical data operation and management. For example, data and documents are saved and integrated separately depending on their forms when electronic health records or data like SAM files are transmitted or kept. In other cases, such records and data are still kept after being recorded in paper. This study tries to design and implement the EMR system that makes it possible to capsulize forms of data and documents and to digitalize documents in work process as they are in terms of operation and storage. The system is expected to support efficient operation of electronic documents in the aspects of work and management.