• The Journal of Churna Manual Medicine for Spine and Nerves
• /
• v.17 no.2
• /
• pp.131-139
• /
• 2022

Objectives This study aimed to analyze the medical utilization of low back pain (LBP) patients after back surgery and estimate the medical costs of Korean and Western medicine collaborative treatment, odds ratio, and hazard ratio between the two groups using the 2019 Health Insurance Review and Assessment Service-National Patient Sample (HIRA-NPS-2019). Methods Data management and descriptive analysis, logistic regression, and survival analysis were conducted for defining and estimating the LBP patients after back surgery in the NPS 2019 dataset. Results A total of 216,424 patients out of 991,189 were identified as having LBP. Among the patients with LBP, 1,734 were treated with surgery while 214,690 were not. Among those who had surgery, 937 were treated with conventional treatments only and 797 underwent Korean medicine treatments. The odds ratio of the logistic regression analysis was 0.7129, suggesting that Korean medical treatment experience group had a 28.7% lower risk of reoperation than the Western medical treatments only group. The hazard ratio of the survival analysis was 0.9145; thus, the risk probability of reoperation was estimated to be approximately 8.55% lower. The 50% risk of reoperation was 69 days (0.5044) for the conventional group, and 97 days (0.5008) for the Korean medical group in the survival analysis using the Kaplan-Meier graph. Conclusions These results could be utilized in future studies in conducting economic evaluation for estimating cost-effectiveness of Western medicine and Korean medicine treatment compared to Western medicine alone in LBP patients after back surgery in a South Korean perspective. mended and should be applied while taking the necessary precautions.

• Korean Journal of Radiology
• /
• v.21 no.4
• /
• pp.387-401
• /
• 2020

Radiomics and deep learning have recently gained attention in the imaging assessment of various liver diseases. Recent research has demonstrated the potential utility of radiomics and deep learning in staging liver fibroses, detecting portal hypertension, characterizing focal hepatic lesions, prognosticating malignant hepatic tumors, and segmenting the liver and liver tumors. In this review, we outline the basic technical aspects of radiomics and deep learning and summarize recent investigations of the application of these techniques in liver disease.

• International journal of advanced smart convergence
• /
• v.5 no.1
• /
• pp.30-33
• /
• 2016

With the advent of big data, data mining is more increasingly utilized in various decision-making fields by extracting hidden and meaningful information from large amounts of data. Even as exponential increase of the request of unrevealing the hidden meaning behind data, it becomes more and more important to decide to select which data mining algorithm and how to use it. There are several mainly used data mining algorithms in biology and clinics highlighted; Logistic regression, Neural networks, Supportvector machine, and variety of statistical techniques. In this paper it is attempted to compare the classification performance of an exemplary algorithm J48 and REPTree of ML algorithms. It is confirmed that more accurate classification algorithm is provided by the performance comparison results. More accurate prediction is possible with the algorithm for the goal of experiment. Based on this, it is expected to be relatively difficult visually detailed classification and distinction.

• Korean Medical Education Review
• /
• v.24 no.2
• /
• pp.79-92
• /
• 2022

With increasing demands for medical care by society, the medical system, and general citizens and rapid changes in doctor's awareness, the competencies required of doctors are also changing. The goal of this study was to develop a doctor's competency framework from the patient's perspective, and to make it the basis for the development of milestones and entrustable professional activities for each period of medical student education and resident training. To this end, a big data analysis using topic modeling was performed on domestic and international research papers (2011-2020), domestic newspaper articles (2016-2020), and domestic social networking service data (2016-2020) related to doctor's competencies. Delphi surveys were conducted twice with 28 medical education experts. In addition, a survey was conducted on doctor's competencies among 1,000 citizens, 407 nurses, 237 medical students, 361 majors, and 200 specialists. Through the above process, six core competencies, 16 sub-competencies, and 47 competencies were derived as subject-oriented doctor's competencies. The core competencies were: (1) competency related to disease and health as an expert; (2) competency related to patients as a communicator; (3) competency related to colleagues as a collaborator; (4) competency related to society as a health care leader (5) competency related to oneself as a professional, and (6) competency related to academics as a scholar who contributes to the development of medicine.

• The Journal of Information Systems
• /
• v.29 no.2
• /
• pp.243-263
• /
• 2020

Purpose The purpose of this study is to analyze the causal relationship between user satisfaction, expected satisfaction, quality of service, perceived value, and expertise that should be emphasized in personalized medical information services for the development of personalized medical information services based on big data analysis and the spread of their demand. Design/methodology/approach This study established research models and hypotheses on the basis of the theory of reuse intent, and applied the PLS methodology for analysis, the factors that make it applicable to personalized medical services in the theory of service quality and satisfaction. Findings According to the empirical analysis result, this study confirmed that it can be seen that the expertise, perceived value, and quality of medical services did not directly affect the user's intention to reuse, but formed a direct causal relationship through variables such as whether they met expectations.

• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.38-39
• /
• 2019

본 논문은 R-CDM 의료영상정보를 기반으로 ELK Stack 기술을 적용하여 획득한 데이터의 분석 결과를 시각화하기 위한 시스템에 대해 기술한다. 제안한 시스템은 의료 빅데이터의 검색, 수집 그리고 분석 결과를 모니터링 할 수 있으며, 특히 대량의 데이터의 변화와 데이터간의 차이를 확인할 수 있다. 본 연구에서 제안한 시스템은 수집된 의료영상 빅데이터에 대해 적용하여 현황과 처리결과 그리고 실시간 분석결과에 대한 모니터링을 통해 관리의 효율성을 높여 실시간 검색 및 분석 서비스 분야에 기여할 것으로 기대된다.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.2
• /
• pp.95-106
• /
• 2016

Biometric data may appear different depending on the person and sasang Medicine has a close relationship with the Department. Biometric data not only mean a human heart rate, a blood pressure, a heart rate, and the past medical history, degree of aging, body mass index, but also is used as a reference measure for determining the state of health of the person. So biometric data should be reproduced for the application purposes, depending on their applications. In previous studies, because the biometric data is changed in real time and applies only to snap shut at the time of the continuity of the current time is excluded. Therefore, in this study in order to solve this problem, we propose a biometric data patton analysis model comprising a continuity of time in the big data environment consisting of biometric data. The proposed model can help determine the choice of needle position carefully when using the electronic acupuncture for care and health promotion.

• The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
• /
• v.34 no.2
• /
• pp.21-37
• /
• 2021

Objectives : Allergic rhinitis(AR) is a common chronic disease that accounts for 10-40% of the world's population. This study aims to analyze the status of claims, prevalence, and medical utilization of allergic rhinitis patients using representative patients sample data. Methods : This study used the National Patients Sample(HIRA-NPS) of the Health Insurance Review and Assessment Service for 7 years(2010-2016). And we defined AR patients as all statements including J30 or a subcategory of J30 as the main disease, using the Korean Standard Classification of Diseases(KCD-7). The trend of AR patients by year was divided into Western medicine(WM) and Korean medicine(KM), and analyzed by subgroup analysis such as inpatient/outpatient, gender, age, insurance type, and care institution. Results : Patients with AR were mainly claimed for first sub diagnosis in WM and major diagnosis in KM, and the number of claims increased about 1.3 times and 1.4 times compared to 2010 in WM and KM, respectively. In addition, the total annual medical expenses in 2016 increased 1.3 times and 1.7 times compared to 2010, respectively. Conclusions : Both WM and KM are showing a steadily increasing trend in medical use due to allergic rhinitis. Further research is needed by considering genetic and environmental factors and individual characteristics, and linking with additional data.

• Journal of radiological science and technology
• /
• v.31 no.4
• /
• pp.347-353
• /
• 2008

This study is to prepare an evaluation standard about personal information protection and security management of a medical institution and to build up a grade standard of evaluation in PACS environment. We built up evaluation index based on 10 detailed items in four big categories (political security, technical security, data management security and physical security) by referring to ISO17799 (BS 7799), HIPPA (Health Insurance and Portability and Accountability Act of 1996) and domestic medical law. We have investigated at the thirty places where medical facility with the extracted security criteria and security evaluation index. Average score of physical security list, one of the big categories, was 18.5/20 (93%) at all medical institutions. Political security score was 18.5/30 (62%), data management security score was 12/20 (60%) and technical security score was 17.5/30 (58%). Therefore, security evaluation score was average 67 in 30 general hospitals, which was 4th level. The results showed that it is necessary to establish evaluation and management standard about personal information protection and security consciousness which are weak in PACS environment.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.93-100
• /
• 2024

With the advent of the Fourth Industrial Revolution, cutting-edge technologies such as artificial intelligence, big data, the Internet of Things, and cloud computing are driving innovation across industries. These technologies are generating massive amounts of data that many companies are leveraging. However, there is a notable reluctance among users to share sensitive information due to the privacy risks associated with collecting personal data. This is particularly evident in the healthcare sector, where the collection of sensitive information such as patients' medical conditions poses significant challenges, with privacy concerns hindering data collection and analysis. This research presents a novel technique for collecting and analyzing medical data that not only preserves privacy, but also effectively extracts statistical information. This method goes beyond basic data collection by incorporating a strategy to efficiently mine statistical data while maintaining privacy. Performance evaluations using real-world data have shown that the propose technique outperforms existing methods in extracting meaningful statistical insights.