• Journal of Korea Multimedia Society
• /
• v.11 no.9
• /
• pp.1267-1276
• /
• 2008

The time taken for an ischemic heart disease patient to have a percutaneous coronary intervention because of acute myocardial infarction after arriving at the hospitals (door-to-balloon time) affects the patient's mortality significantly. To improve the emergency service system that has been previously used in the hospitals, this study focused on reducing door-data time and data-to-decision time among three time stages. The newly established e-emergency service system has set up the database of patients that had an emergency operation for acute myocardial infarction in the emergency service system of the hospital and has issued health cards for the patients that regularly visit the Busan National University Hospital. In addition, it has stored prior operation permits in the form of a certified electronic document. The new electronic system will reduce the complex treatment and operation procedures innovatively. Therefore, it is expected that this will make the life save (or the emergency patients easier and reduce the mortality. Moreover, it will also settle down the hospital staff's and patients' predicaments caused by the complex procedure of the legacy system.

• 대한상한금궤의학회지
• /
• v.14 no.1
• /
• pp.41-50
• /
• 2022

Objective : The purpose of this study is to explore the most suitable machine learning model algorithm for Shanghanlun diagnostic system classification using natural language processing (NLP). Methods : A total of 201 data items were collected from 『Shanghanlun』 and 『Clinical Shanghanlun』, 'Taeyangbyeong-gyeolhyung' and 'Eumyangyeokchahunobokbyeong' were excluded to prevent oversampling or undersampling. Data were pretreated using a twitter Korean tokenizer and trained by logistic regression, ridge regression, lasso regression, naive bayes classifier, decision tree, and random forest algorithms. The accuracy of the models were compared. Results : As a result of machine learning, ridge regression and naive Bayes classifier showed an accuracy of 0.843, logistic regression and random forest showed an accuracy of 0.804, and decision tree showed an accuracy of 0.745, while lasso regression showed an accuracy of 0.608. Conclusions : Ridge regression and naive Bayes classifier are suitable NLP machine learning models for the Shanghanlun diagnostic system classification.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2003.05a
• /
• pp.271-285
• /
• 2003

In the conduct of this study, a web-enabled healthcare system for the management of hypertension was implemented through a hyperlink-based inference approach. The hyperlink-based inference platform implemented using the hypertext capacity of HTML which ensured accessibility, multimedia facilities, fast response, stability, ease of use and upgrade, and platform independency of expert systems. Many HTML documents, which are hyperlinked to each other based on expert rules, were uploaded beforehand to perform the hyperlink-based inference. The HTML documents were uploaded and maintained automatically by our proprietary tool called the Web-Based inference System (WeBIS) that supports a graphical user interface (GUI) for the input and edit of decision graphs. Nevertheless, the editing task of the decision graph using the GUI tool is a time consuming and tedious chore when the knowledge engineer must perform it manually. Accordingly, this research implemented an automatic generator of the decision graph for the management of hypertension. As a result, this research suggests a methodology for the development of Web-enabled healthcare systems using the hyperlink-based inference approach and, as an example, implements a Web-enabled healthcare system for hypertension, a platform which peformed especially well in the areas of speed and stability.

• Journal of Digital Contents Society
• /
• v.9 no.1
• /
• pp.27-31
• /
• 2008

u-Health is a representative realization method of ubiquitous IT and it is being embossed as an industry that can make our lives abundant. Through the u-Health, the diagnosis will go beyond the restriction of space, which is based on hospital, and be positioned as a universal value in a daily life by combining diagnosis and life naturally. The purpose of this study is to suggest systematic, intelligent, mobile medical information system that has the same effect as the assistant of specialist by providing scientific and objective knowledge, which is suitable for u-Health age. Mobile medical information system can provide user with the opinion of specialist by planting the experience, knowledge and decision making process of specialist that are necessary for solving the problem requiring special medical knowledge and passing through an inference process.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.5
• /
• pp.3308-3314
• /
• 2015

The purpose of this study is to investigate the casual relationships among purchase decision factors of medical devices, satisfaction and repurchasing intention. Data of this study is a 2012 survey on medical institutions using medical devices of MW(ministry of health and welfare) and We analyzed 116 medical institutions having ultrasound imaging system lager than general hospitals among data. For empirical analysis, we carried out confirmative factor analysis and path-analysis using AMOS 21.0 package. Main results of this study are as follows: First, brand has positive influence on satisfaction and satisfaction has positive impaction on repurchase intention. Second, although not statistically significant, performance and service have positive impaction on satisfaction and price has negative influence on satisfaction. The significance of this study is to provide empirical basis on establishment of efficient marketing strategy and enhancement of competitiveness for the medical device industry.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.10
• /
• pp.1328-1336
• /
• 2014

This paper proposes Power System Health Index(PSHI) newly. The paper describes several kind of power system health indices based on two main categories, which are adequacy and security. In adequacy, four kinds of health indices of Frequency, Voltage, Reserve(Operating Reserve Power and Frequency Regulation Reserve Power) and Overload of lines and transformers are proposed. In security, four kinds of health indices of Voltage(154kV, 345kV and 765kV), Overload of lines and transformers, Power flow constraint among areas and SPS are proposed. All indices are mapped with three domains, which are indicated as Health, Margin and Risk, defined with expert interview. While domains of health, margin and risk is defined similar with the conventional well being analysis of power system. The criterion of the domains is proposed using an interview with expert operators and practical reliability codes in Korea. The several kinds of health index functions, which are linear ratio, piecewise linear ration and reverse ratio function etc. are developed in this paper. It will be expected that the developed health indices can help operators to control power system more successfully and also prevent power system from accident as like as black out in future because operator can make a decision immediately based on more easily visual information of system conditions from too much indices acquisition of complex power system.

• The Korean Journal of Applied Statistics
• /
• v.22 no.6
• /
• pp.1229-1237
• /
• 2009

In the long-term care insurance(LTCI) system, the question of how to provide the most appropriate care has become a major issue for the elderly, their family, and for policy makers. To help beneficiaries use LTC services appropriately to their needs of care, National Health Insurance Corporation(NHIC) provide them with the individualized care plan, named the Long-term Care User Guide. It includes recommendations for beneficiaries' most appropriate type of care. The purpose of this study is to develop a recommending system for care plan(Res-CP) in LTCI system. We used data set for Long-term Care User Guide in the 3rd long-term care insurance pilot programs. To develop the model, we tested four models, including a decision-tree model in data-mining, a logistic regression model, and a boosting and boosting techniques in an ensemble model. A decision-tree model was selected to describe the Res-CP, because it may be easy to explain the algorithm of Res-CP to the working groups. Res-CP might be useful in an evidence-based care planning in LTCI system and may contribute to support use of LTC services efficiently.

• Journal of Preventive Medicine and Public Health
• /
• v.53 no.2
• /
• pp.117-125
• /
• 2020

Objectives: This study investigated the role of information and communication technology and women's empowerment in contraceptive discontinuation in Indonesia. Methods: The study used data from the 2017 Indonesia Demographic and Health Survey and monthly contraceptive calendar data. A Gompertz proportional hazards model was used for analysis. Results: The 12-month contraceptive discontinuation rate was higher among women who had used the Internet in the past year, women who were mobile phone owners, and women who reported having fully participated in household decision-making than among their counterparts. These factors significantly impacted the risk of contraceptive discontinuation in Indonesia, even after controlling for contraceptive method, age, parity, contraceptive intent, education, work status, place of residence, and wealth status. Conclusions: After adjustment for the control variables, a higher risk of contraceptive discontinuation was associated with having used the Internet in the past year, owning a mobile phone, and not participating in household decision-making. Higher contraceptive discontinuation risk was also associated with using contraceptive pills, older age, lower parity, intent of spacing births, more education, current unemployment, and rural residence, and the risk was also significantly higher for those in the lowest household wealth quintile than for those in the fourth household wealth quintile. The association of contraceptive discontinuation with the use of modern information and communication technology and relatively disempowerment in household decision-making may imply that information regarding family planning and contraception should be conveyed via social media as part of setting up an eHealth system. This must include a strong communication strategy to empower and educate women in contraceptive decision-making.

• Health Policy and Management
• /
• v.2 no.2
• /
• pp.33-56
• /
• 1992

The objectives of this research are (i) to review the functional and financial distribution of public health adminstration between central and local governments, (ii) to find out, based on economic criteria, optimal distribution required to fullfil local need for public health, and finally, (iii) to suggest policy implications in health area in face of the newly arising local autonomy system in Korea. Judging from data on government expenditures and tax revenues, public health administration in Korea is highly concentrated into central government, both functionlally and financially. High dependency of public health on central government has often been critisized that local residents can not participate in the decision making process for local health problems. This study, however, shows that localization of public health administration does not necessarily result in efficient and equitable allocation of resource to satisfy local demand for public health. From this point of view, two eccnomic criteria are suggested, i.e. external effect and economies of scle, as distributive criteria of roles in public health administration between local and central government. In addition, superiority of central concentration of public health administration to localization is emphasized in that public health in a wide sense contains the nature of public good and is part of compulsory socil security system. As a consequence, planned intervention by government is desirable.

• The Korean Journal of Applied Statistics
• /
• v.31 no.6
• /
• pp.693-706
• /
• 2018

It is very important to support the elderly with disability ageing in place. Assisting devices can help them to live independently in their community; however, they have to be used appropriately to meet care needs. This study develops an assisting device recommendation system for the beneficiaries of long-term care insurance that include algorithms to decide the most appropriate type of assisting device for beneficiaries. We used long-term care (LTC) insurance data for grade assessment including 8,084 beneficiaries from July 2015 to June 2016. In addition, we collected standard care plans for assisting devices, that power-assessors made, considering their performance and ability that could subsequently be matched with grade assessment data. We used a decision-tree model in data-mining to develop the model. Finally, we developed 15 algorithms for recommending assisting devices. The findings might be useful in evidence-based care planning for assisting devices and can contribute to enhancing independence and safety in LTC.