• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.974-992
• /
• 2021

Recently, the healthcare field has undergone rapid changes owing to the accumulation of health big data and the development of machine learning. Data mining research in the field of healthcare has different characteristics from those of other data analyses, such as the structural complexity of the medical data, requirement for medical expertise, and security of personal medical information. Various methods have been implemented to address these issues, including the machine learning model and cloud platform. However, the machine learning model presents the problem of opaque result interpretation, and the cloud platform requires more in-depth research on security and efficiency. To address these issues, this paper presents a recent technology for Internet-of-Things-based (IoT-based) health big data processing. We present a cloud-based IoT health platform and health big data processing technology that reduces the medical data management costs and enhances safety. We also present a data mining technology for health-risk prediction, which is the core of healthcare. Finally, we propose a study using explainable artificial intelligence that enhances the reliability and transparency of the decision-making system, which is called the black box model owing to its lack of transparency.

• The Journal of Korean Obstetrics and Gynecology
• /
• v.32 no.2
• /
• pp.18-28
• /
• 2019

Objectives: The research is aimed at identifying the necessity of the support project of Korean medical treatment in infertility by analyzing the outcome of those subject and providing data for Korean medical treatment in infertility by analyzing the medical treatment of Korean medical doctors involved in the project. Methods: 98 patients who participated in the support project of Korean medical treatment in infertility in Jeollanamdo and 57 Korean medical doctors who participated as therapists were surveyed. Patients were given four months of treatment at local Korean medical clinics. After the treatment was completed, we analyzed the characteristics of the patients' group. And we sent questionnaires to doctors to answer the message. The content of the questionnaire consisted of infertility treatments, a wish for support project. These data were analyzed by frequency and t-test. Results: Analysis of the answer to the questionnaire obtained data on Korean medical treatment in infertility. The most desired thing for future support program was the introduction of husband and wife care. Conclusions: This survey by Korean medical doctors gave us reference data for Korean medical treatment in infertility and the direction in which therapy business should proceed.

• Journal of the Korean Data and Information Science Society
• /
• v.16 no.3
• /
• pp.515-527
• /
• 2005

The data mining is a new approach to extract useful information through effective analysis of huge data in numerous fields. We utilized this data mining technique to analyze medical record of 39,900 people. Whole data were separated by gender first and divided into three groups, including normal, stage 1 hypertension, and stage 2 hypertension. The data from each group were analyzed with data mining technique. Based on the result that we have extracted with this data mining technique, major risk factors for the hypertension are age, BMI score, family history.

• Journal of the Korean housing association
• /
• v.19 no.5
• /
• pp.57-65
• /
• 2008

The purpose of this study is to figure out the relationship between the residence stories in high-rise condominium and residents' disease patterns throughout the dweller's medical reports. Research basic data are obtained from medical fee request of National Health Insurance Corporation. Data are limited to 'A' high-rise condominium and a medical treatment time to 3 years (2004. 1-2006, 12). Data for analysis are composed of total 346,286 medical records, 43,159 disease records, and 8,999 personal records. Data are stored by sex, age, building story, residence story, visiting year and month, treatment days, main disease type (KCD-4). Treatment number, disease type and asthma in disease records and personal records are statistically analyzed by residence story considering age. Findings are as follows: 1) Women have more medical treatments than men, 40-50 age group is more treated, and the residents of 6-25 stories are more received medical treatments. According to KCD-4, diseases of the respiratory system and diseases of the eye and adnexa are relatively treated higher than other diseases. 2) The diseases of he respiratory system, the eye and adnexa, the skin and subcutaneous issue, the ear and mastoid process, and the asthma have not relation to the high-storied residence through the data of disease records and personal records. But the analysis on the data of children, age 7 and less, showed a significant relation. to conclude, there is no relationship between the residence of high-stories in the condominium and residents' disease patterns, but there is a little probable to the relationship in the pre-school child.

• The Journal of the Korea Contents Association
• /
• v.12 no.1
• /
• pp.80-90
• /
• 2012

Medical data sampled through medical sensor nodes can provide services properly only when the data are not lost even during the fault of a home health gateway. The loss of medical data can be minimized if a sensor node, in which it is expected that there are the most saving spaces, is selected after medical sensor nodes tentatively conduct local save or communicate with each other during a fault when data cannot received. Furthermore, efficient saving techniques are necessary since the cycle for sampling information is different according to the type of medical data and a space for distributed saving is different for each apparatus. So, this research suggests an efficient distributed archiving protocol (DAP) for medical data sensor nodes, each of which has a diverse sampling cycle. In order to confirm the usefulness of DAP, DAP between sensor node and gateway was designed and materialized. An experiment was conducted using the materialized program and earned a high level of recovery rate (99.3%) and of accuracy rate, which confirms that sensor nodes can play their role during a temporary fault.

• Convergence Security Journal
• /
• v.5 no.1
• /
• pp.19-27
• /
• 2005

This paper presents the content regarding electronic medical examination chart and data processing for efficient medical examination and fast treatment by realizing remote medical examination system of mutual conversation type among 3 parties(patient, doctor, pharmacist) on internet base, and establishment of database enabled system integration for efficient data processing in both on-line and off-line mode by interconnecting ASP and SQL on IIS 4.0 web server, consultation between patient and doctor, medical examination on off-line mode, transmission of prescription sheet to the pharmacist designated by patient, preparation of medicine, semieternal storage of medical examination data owing to storage and check of medical examination data, more accurate medical examination and prescription using this medical examination data by patient and doctor, and so on. And, data processing between doctor and pharmacist is differently performed based on class such as general member and charge member, and service access right pursuant to this is endowed, so that certification of each member must follow by all means.

• Korean Medical Education Review
• /
• v.25 no.2
• /
• pp.109-113
• /
• 2023

An educational outcome cohort has been established at Keimyung University School of Medicine to help make educational policy decisions and improve educational programs based on data. The purpose of the educational outcome cohort is to support educational policy decisions for achieving graduation outcomes smoothly and to accomplish the intended human resources development of the university through objective analyses and regular monitoring, providing continuous feedback. The data collected for the educational outcome cohort include the student identifications of freshmen, entrance exam scores, premedical and medical school grades, titles and forms of student academic research, the results of psychological testing, scholarship recipient lists, volunteer clubs, and so forth. The data are collected using an information utilization agreement approved by the Institutional Review Board, and the collected data are encrypted and stored on a dedicated computer for enhanced personal information security. Proposals to access and utilize the educational outcome cohort data must be discussed and approved by the Educational Outcome Cohort Committee, which decides on the scope and method of utilization. The collected and managed educational outcome cohort data have been used to develop comparative programs to improve students' competency and to support admission policy decisions through an analysis of the characteristics and performance of medical school students. The establishment and utilization of the educational outcome cohort will play an important role in determining the School of Medicine's educational policies and suggesting new directions for educational policies in the future.

• Journal of Biomedical Engineering Research
• /
• v.42 no.4
• /
• pp.175-185
• /
• 2021

Purpose: Vital sign are used to help assess the general physical health of a person, give clues to possible diseases, and show progress toward recovery. Researchers are using vital sign data and AI(artificial intelligence) to manage a variety of diseases and predict mortality. In order to analyze vital sign data using AI, it is important to select and extract vital sign data suitable for research purposes. Methods: We developed a method to visualize vital sign and early warning scores by processing retrospective vital sign data collected from EMR(electronic medical records) and patient monitoring devices. The vital sign data used for development were obtained using the open EMR big data MIMIC-III and the wearable patient monitoring device(CareTaker). Data processing and visualization were developed using Python. We used the development results with machine learning to process the prediction of mortality in ICU patients. Results: We calculated NEWS(National Early Warning Score) to understand the patient's condition. Vital sign data with different measurement times and frequencies were sampled at equal time intervals, and missing data were interpolated to reconstruct data. The normal and abnormal states of vital sign were visualized as color-coded graphs. Mortality prediction result with processed data and machine learning was AUC of 0.892. Conclusion: This visualization method will help researchers to easily understand a patient's vital sign status over time and extract the necessary data.

• Journal of Radiation Protection and Research
• /
• v.37 no.3
• /
• pp.146-148
• /
• 2012

The use of GEANT4 simulation toolkit has increased in the radiation medical field for the design of treatment system and the calibration or validation of treatment plans. Moreover, it is used especially on calculating dose simulation using medical data for radiation therapy. However, using internal visualization tool of GEANT4 detector constructions on expressing dose result has deficiencies because it cannot display isodose line. No one has attempted to use this code to a real patient's data. Therefore, to complement this problem, using the result of gMocren that is a three-dimensional volume-visualizing tool, we tried to display a simulated dose distribution and isodose line on medical image. In addition, we have compared cross-validation on the result of gMocren and GEANT4 simulation with commercial radiation treatment planning system. We have extracted the analyzed data of dose distribution, using real patient's medical image data with a program based on Monte Carlo simulation and visualization tool for radiation isodose mapping.

• International Journal of Knowledge Content Development & Technology
• /
• v.7 no.2
• /
• pp.21-40
• /
• 2017

Considering the need for quality health information and resultant health care services in any society, this study was carried out to look into the status of library and information resources and services provided by medical libraries in Enugu State, Nigeria. The main objective of the study was to find out the information resources and services available for medical library users towards quality health care provision. Five (5) medical libraries of major teaching hospitals were used for the study with 980 registered users as the study population from where 245 users were sampled. Observation checklist was used to collect data on resources while questionnaire was used to collect data from the respondents on the services provided. The Medical Library Association Standard guided the analysis of data from observation while frequency counts and mean scores were used to analyze data from the questionnaire. Major findings showed that even though some of the required resources and services are available and provided the medical libraries, most of the required resources and services are not adequately provided by these libraries.