• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.1
• /
• pp.11-16
• /
• 2023

Accurate hospital case modeling and prediction are crucial for efficient healthcare. In this study, we demonstrate the implementation of regression analysis methods in machine learning systems utilizing mathematical statics and machine learning techniques. The developed machine learning model includes Bayesian linear, artificial neural network, decision tree, decision forest, and linear regression analysis models. Through the application of these algorithms, corresponding regression models were constructed and analyzed. The results suggest the potential of leveraging machine learning systems for medical research. The experiment aimed to create an Azure Machine Learning Studio tool for the speedy evaluation of multiple regression models. The tool faciliates the comparision of 5 types of regression models in a unified experiment and presents assessment results with performance metrics. Evaluation of regression machine learning models highlighted the advantages of boosted decision tree regression, and decision forest regression in hospital case prediction. These findings could lay the groundwork for the deliberate development of new directions in medical data processing and decision making. Furthermore, potential avenues for future research may include exploring methods such as clustering, classification, and anomaly detection in healthcare systems.

• Journal of Convergence Society for SMB
• /
• v.5 no.4
• /
• pp.17-23
• /
• 2015

Due to the development of information and communication technology as health care service is popular variety utilizing bioinformatics patient information services are being provided to the patient. In particular, the healthcare utilizing bioinformatics information, and change in a variety of healthcare trends. However, healthcare services using bioinformatics information of the patient and the complexity of the disease, new diseases (SARS, AIDS, etc .) due to the emergence of increasing health care costs and health promotion services provided to patients may not be smooth. In this paper, we propose a model for low-cost health services and medical care of patients bioinformatics fast access to information. The proposed model can be so big a bioinformatics data formation by the patient's patient information anytime / anywhere providing medical services in the home or the nearest hospital for their own disease management. In particular, the proposed model of health care services is characterized improve work efficiency, reducing the burden on hospitals by passing a medical illness to easily analyze patient information.

• Journal of Preventive Medicine and Public Health
• /
• v.26 no.4 s.44
• /
• pp.661-671
• /
• 1993

In order to compare the geographical distribution of physician by level of medical care and specialty, a log linear model was applied to the annual registration data of the Korean Medical Association as of the end of December, 1991 which was supplemented from related institutions and adjusted with relevant sources. Those physicians in primary and secondary care institutions were not statistically significantly unevenly distributed by province-level catchment area. There were some differences in physician distribution among big cities, medium and small-sized cities, and counties; however, those physicians for primary care level were equitably distributed between cities and counties. Specialties for secondary care physicians were less evenly distributed in county areas than in city areas, and generalists are distributed more evenly in cities and counties than in big cities. There is a certain limitation due to underregistration in the annual physician registration to the Korean Medical Association; however, the geographical distribution of physicians has been improved quantitatively. It is strongly suggested that specialties and the level of medical care should be considered for further physician manpower studies.

• Health Policy and Management
• /
• v.9 no.1
• /
• pp.72-109
• /
• 1999

This study is conducted to investigate the current status on the utilization of health care and plan for solving this problem. The claims data of the fiscal tear 1995 obtained from the regional health insurance society are used for the study. The main findings of the study are summarized as follows. Indexes(The Extremal Quotient(EQ), coefficients of variance(CV's))which represent the regional difference in the admission rate of the tertiary medical diagnosis group report that there is difference in quantity and quality of utilization of health care. The admission rate is lower in the big city areas, Kyoungkido, Kangwondo and Chunlapukdo. Even after age-sex adjustment, the admission rate is still low in Kangwondo, Chunlapukdo and Kyoungsangpukdo. The big city areas tend to have higher rates in the expenses per claim, hospital days per claim, and daily expenses but the rates are still low in some area in Kangwondo, Chunlanamdo and Kyoungsangpukdo. This result remains as same after age-sex adjustment. There is a large regional difference in average utilization rate for the tertiary hospital of the tertiary medical diagnosis group: 57.2%(SD 11.53). The utilization rates for the tertiary hospital in their large catchment area are 96.34%, 83.19% and 73.22% in each Kyoungin, Kyoungnam and Kyoungpuk areas whereas it is lower in a Chungpuk and Chungnam areas. The regional differences of health care utilization of the tertiary medical diagnosis group gave some relationships with their geographical characteristics such as socio-economic characteristics and supply factors of medical services. It is important that many medical policies should be developed in order to minimize and balance out the regional differences of health care utilization. The service allocation policy should include the reconstruction of manpower policy, developing the resource allocating formula, finding the self-sufficient catchment area and reforcing of public health services. Moreover, in order to achieve the balanced development by region, they should investigate and consider each county's microscopic properties under the consistent macrocopic policy. The further studies to find causes of regional difference are needed.

• Journal of Biomedical Engineering Research
• /
• v.44 no.4
• /
• pp.264-274
• /
• 2023

Purpose: The objective is to extract insights that can contribute to the formulation of harmonized international policies and support measures for innovative medical devices and management systems. This study aims to propose effective strategies for future medical device innovation and healthcare delivery. Results: It investigates technological advancements, regulatory approval systems, insurance policies, and successful commercialization cases in South Korea, the United States, and the European Union. In 2018, the FDA implemented insurance coverage for Software as a Medical Device (SaMD) and recognized insurance coverage for Digital Therapeutics (DTx). Germany is a country that ensures permanent reimbursement for healthcare applications since 2020, making it the first country to provide legal health insurance coverage for fostering a digital ecosystem. Conclusion: The findings of this research highlight the importance of cultivating a supportive regulatory and environmental framework to facilitate the adoption of innovative medical devices. Continuous support for research and development (R&D) efforts by companies, along with the validation of clinical effectiveness, is crucial.

• Korean Journal of Schizophrenia Research
• /
• v.22 no.2
• /
• pp.34-41
• /
• 2019

Objectives: This study was performed to examine the effects of the public attention to 'crime of schizophrenia' on the use of mental health services in patients with schizophrenia using big data analysis. Methods: Data on the frequency of internet searches for 'crime of schizophrenia' and the patterns of mental health service utilization by patients with schizophrenia spectrum disorders by month were collected from Naver big data and the Health Insurance Review and Assessment Services in Korea, respectively. Their correlations in the same and following month for lagged effect were examined. Results: The number of outpatients correlated negatively with public attention to 'crime of schizophrenia' in the same month. The lagged relationship between public attention and the number of admissions in psychiatric wards was also found. In terms of sex differences, the use of outpatient services among female patients correlated negatively with public attention in the same month while the number of male patients' admissions in both same and following month correlated positively with public attention. Conclusion: These findings suggested that public attention to 'crime of schizophrenia' could negatively affect illness behavior in patients with schizophrenia.

• Journal of Digital Convergence
• /
• v.13 no.4
• /
• pp.395-404
• /
• 2015

This study is exploring objective awareness of literary therapy by consideration of popular perception about literary therapy through analysis of big data. The purpose of this study is the deduction of meaning information through analysis in the viewpoint of big data at online social network service(SNS) about 'literary therapy'. Accordingly, the main way of research became content analysis of keyword linked to literary therapy by utilizing opinion mining method related to text mining. The study mainly grasped 'literary therapy' and analyzed 'bibliotherapy' comparatively. The period of study was from Oct. 10th to Nov. 10th, 2014(during 30 days), and SNS such as blog or twitter became the subject of search. Through the result of study analysis, the conclusion that the spread of literary therapeutic prospect, structural harmony of literary therapeutic field, and the solidity of perceptional axis about literary therapy are needed can be drawn. This study is worthwhile because it can investigate popular awareness about literary therapy and can suggest alternative for invigoration of literary therapy.

• Journal of Korea Artificial Intelligence Association
• /
• v.2 no.1
• /
• pp.7-14
• /
• 2024

In this paper, we explore the application of RNA-sequencing data and ensemble machine learning to predict lung cancer and treatment strategies for lung cancer, a leading cause of cancer mortality worldwide. The research utilizes Random Forest, XGBoost, and LightGBM models to analyze gene expression profiles from extensive datasets, aiming to enhance predictive accuracy for lung cancer prognosis. The methodology focuses on preprocessing RNA-seq data to standardize expression levels across samples and applying ensemble algorithms to maximize prediction stability and reduce model overfitting. Key findings indicate that ensemble models, especially XGBoost, substantially outperform traditional predictive models. Significant genetic markers such as ADGRF5 is identified as crucial for predicting lung cancer outcomes. In conclusion, ensemble learning using RNA-seq data proves highly effective in predicting lung cancer, suggesting a potential shift towards more precise and personalized treatment approaches. The results advocate for further integration of molecular and clinical data to refine diagnostic models and improve clinical outcomes, underscoring the critical role of advanced molecular diagnostics in enhancing patient survival rates and quality of life. This study lays the groundwork for future research in the application of RNA-sequencing data and ensemble machine learning techniques in clinical settings.

• The Journal of Korean Medicine
• /
• v.44 no.4
• /
• pp.150-162
• /
• 2023

Objectives: The aim of this study is to explore and investigate the status of EMR currently used in Korean medical institutions and the suitability of the existing certification criteria for Korean medicine EMR certification. Methods: The survey was conducted using a related questionnaire from September to October 2022. The survey for current status and the suitability of the existing certification criteria was conducted separately between Korean medical institutions and Korean medicine EMR companies. Results: In a survey of Korean medical institutions on the current status of EMR, more than 80% answered that the imaging system and Korean medicine EMR could be linked. Most medical institutions did not exchange clinical information between institutions. When asked about the intention to develop standard EMR of Korean medicine in the future, 57% of institutions answered 'yes'. In future, if Korean medicine EMR certification criteria are developed, all EMR companies are willing to develop the EMR that satisfy them. Looking at the satisfaction survey of the existing EMR certification criteria of the Korean medicine EMR system, it was found that high/low satisfaction was shown in various areas, and in particular, the overall clinical information exchange function was insufficient. Conclusion: In order to introduce the Korean medicine EMR certification criteria, it must be considered of the current status of EMR and applicability of Korean medicine EMR for establishment of Korean medicine standard EMR certification criteria. By developing Korean medicine EMR certification criteria, high-quality medical services can be provided to medical consumers who want Korean medical treatment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2359-2376
• /
• 2022

With the exponential growth of medical image big data represented by high-resolution CT images(CTI), the high-resolution CTI data is of great importance for clinical research and diagnosis. The paper takes lung CTI as an example to study. Retrieving answer CTIs similar to the input one from the large-scale lung CTI database can effectively assist physicians to diagnose. Compared with the conventional content-based image retrieval(CBIR) methods, the CBIR for lung CTIs demands higher retrieval accuracy in both the contour shape and the internal details of the organ. In traditional supervised deep learning networks, the learning of the network relies on the labeling of CTIs which is a very time-consuming task. To address this issue, the paper proposes a Weakly Supervised Similarity Evaluation Network (WSSENet) for efficiently support similarity analysis of lung CTIs. We conducted extensive experiments to verify the effectiveness of the WSSENet based on which the CBIR is performed.