• Korea Journal of Hospital Management
• /
• v.26 no.1
• /
• pp.71-82
• /
• 2021

Purpose: The purpose of this study is to estimate incomes and costs of the medical clinics by using secondary data. Methodology: The medical incomes and costs were estimated from 405 clinics operated by sole practitioner providing out-patient services among all clinics subject to the Medical Cost Survey on National Health Insurance Patients in 2017, excluding dental clinics and oriental medical clinics. The incomes and costs of the medical clinics were reflected with incomes and costs of health insurance benefits and were calculated by types of medical services (i.e., basic care, surgery, general treatment, functional test, specimen test and imaging test). The costs were classified as follows: labor costs, equipment costs, material costs and overhead costs. Secondary data was used to estimate the incomes and costs of the medical clinics. For allocation bases for costs for each type of the medical service, the ratio of revenue from health insurance benefits by types of medical services was applied. However, labor costs were calculated with the activity ratio by types of medical services and occupations, using clinical expert panel data. Finding: The percentage of health insurance income for all medical income was 73.1%. The health insurance cost per clinic was 401,864 thousand won. Labor cost accounted for the largest portion of the health insurance income was 191,229 thousand won (47.6%), followed by management cost was 170,018 thousand won (42.3%), materials cost was 35,434 thousand won (8.8%), and equipment costs was 5,183 thousand won (1.3%). Practical Implications: This study suggests a method of estimating incomes and costs of medical clinic services by using secondary data. It could efficiently provide incomes and costs to assess an appropriate level of the health insurance fee to the clinics.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.3
• /
• pp.501-506
• /
• 2008

Medical environments incorporate complex and integrated data networks to transfer vast amounts of patient information, such as images, waveforms, and other digital data. To assure interoperability of images, waveforms and patient data, health level seven(HL7) was developed as an international standard to facilitate the communication and storage of medical data. We also adopted medical waveform description format encoding rule(MFER) standard for encoding waveform biosignal such as ECG, EEG and so on. And, the study converted a broad domain of clinical data on patients, including MFER, into a HL7 message, and saved them in a clinical database in hospital. According to results obtained in the test environment, it was possible to acquire the same HL7 message and biosignal data as ones acquired during transmission. Through this study, we might conclude that the proposed system can be a promising model for electronic medical record system in u-healthcare environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.1
• /
• pp.132-148
• /
• 2013

Via the Internet, the information infrastructure of modern health care has already established medical information systems to share electronic health records among patients and health care providers. Data hiding plays an important role to protect medical images. Because modern medical devices have improved, high resolutions of medical images are provided to detect early diseases. The high quality medical images are used to recognize complicated anatomical structures such as soft tissues, muscles, and internal organs to support diagnosis of diseases. For instance, 16-bit depth medical images will provide 65,536 discrete levels to show more details of anatomical structures. In general, the feature of low utilization rate of intensity in 16-bit depth will be utilized to handle overflow/underflow problem. Nowadays, most of data hiding algorithms are still experimenting on 8-bit depth medical images. We proposed a novel reversible data hiding scheme testing on 16-bit depth CT and MRI medical image. And the peak point and zero point of a histogram are applied to embed secret message k bits without salt-and-pepper.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.3
• /
• pp.250-261
• /
• 2020

Today, data subjects should be considered to utilize various personal data. To support this paradigm, the concept of "My Data" has proposed and has realized in various industrial sectors, including medial sectors. Based on the concept of the medical My Data, this paper proposes a personal health record (PHR) and an electronic medical record (EMR) data trading model. Particularly, this paper proposes a system model to support the medical My Data environment and relevant procedure among stakeholders for PHR/EMR data trading that ensures the rights of data subjects. Based on the proposed system model, this paper also proposes various mathematical models to analyze the behavior of stakeholders and shows the feasibility of the proposed data trading model that satisfies the requirements of both data subjects and data consumers.

• Progress in Medical Physics
• /
• v.30 no.2
• /
• pp.49-58
• /
• 2019

Purpose: Automated analytical systems have begun to emerge as a database system that enables the scanning of medical images to be performed on computers and the construction of big data. Deep-learning artificial intelligence (AI) architectures have been developed and applied to medical images, making high-precision diagnosis possible. Materials and Methods: For diagnosis, the medical images need to be labeled and standardized. After pre-processing the data and entering them into the deep-learning architecture, the final diagnosis results can be obtained quickly and accurately. To solve the problem of overfitting because of an insufficient amount of labeled data, data augmentation is performed through rotation, using left and right flips to artificially increase the amount of data. Because various deep-learning architectures have been developed and publicized over the past few years, the results of the diagnosis can be obtained by entering a medical image. Results: Classification and regression are performed by a supervised machine-learning method and clustering and generation are performed by an unsupervised machine-learning method. When the convolutional neural network (CNN) method is applied to the deep-learning layer, feature extraction can be used to classify diseases very efficiently and thus to diagnose various diseases. Conclusions: AI, using a deep-learning architecture, has expertise in medical image analysis of the nerves, retina, lungs, digital pathology, breast, heart, abdomen, and musculo-skeletal system.

• Korean Journal of Radiology
• /
• v.24 no.11
• /
• pp.1061-1080
• /
• 2023

Artificial intelligence (AI) in radiology is a rapidly developing field with several prospective clinical studies demonstrating its benefits in clinical practice. In 2022, the Korean Society of Radiology held a forum to discuss the challenges and drawbacks in AI development and implementation. Various barriers hinder the successful application and widespread adoption of AI in radiology, such as limited annotated data, data privacy and security, data heterogeneity, imbalanced data, model interpretability, overfitting, and integration with clinical workflows. In this review, some of the various possible solutions to these challenges are presented and discussed; these include training with longitudinal and multimodal datasets, dense training with multitask learning and multimodal learning, self-supervised contrastive learning, various image modifications and syntheses using generative models, explainable AI, causal learning, federated learning with large data models, and digital twins.

• Proceeding of Spring/Autumn Annual Conference of KHA
• /
• 2008.04a
• /
• pp.187-192
• /
• 2008

This purpose of this study is to figure out the inter-relationship between the residence stories in high-rise mixed-use apartments and their residents' disease patterns throughout the dweller's medical reports in high-rise mixed-use apartments. Research basic data are obtained from medical fee request of National Health Insurance Corportion. Data are limited a housing complex to 'A' high-rise mixed-use apartment and a medical treatment time to 3 years(2004-2006). Analysis data of total 346,286 medical records, 43,159 disease records, and 8,999 persons are collected. By analyzing those data, findings are as follows: 1) Women is more medical treatments than men, 40-50 age group is more treated, and the residents of 6-25 stories are more received medical treatments. Diseases of the respiratory system and diseases of the eye and adnexa are relatively treated higher than other diseases. 2) The diseases of the respiratory system, the eye and adnexa, the skin and subcutaneous tissue, 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, 7 ages and less, is showed a significant relation. And to conclude, there is no relationship between the residence of high-stories in that apartment and dwellers' disease patterns, but there is a little probable to the relationship in the pre-school child.

• Journal of Internet Computing and Services
• /
• v.18 no.6
• /
• pp.75-84
• /
• 2017

As there has been growing interests in PHR-based personalized health management project, various institutions recently explore safe methods of recording personal medical and health information. In particular, innovative medical solution can be realized when medical researchers and medical service institutes can generally get access to patient data. As EMR data is extremely sensitive, there has been no progress in clinical information exchange. Moreover, patients cannot get access to their own health data and exchange it with researchers or service institutions. It can be operated in terms of technology, yet policy environment are affected by state laws as well as Privacy and Security Policy. Blockchain technology-independent, in transaction, and under test-is introduced in the medical industry in order to settle these problems. In other words, medical organizations can grant preliminary approval on patient information exchange by using the safely encrypted and distributed Blockchain ledger and can be managed independently and completely by individuals. More apparently, medical researchers can gain access to information, thereby contributing to the scientific advance in rare diseases or minor groups in the world. In this paper, we focused on how to manage personal medical information and its protective use and proposes medical treatment exchange system for patients based on a permissioned Blockchain network for the safe PHR operation. Trusted Model for Sharing Medical Data (TMSMD), that is proposed model, is based on exchanging information as patients rely on hospitals as well as among hospitals. And introduce medical treatment exchange system for patients based on a permissioned Blockchain network. This system is a model that encrypts and records patients' medical information by using this permissioned Blockchain and further enhances the security due to its restricted counterfeit. This provides service to share medical information uploaded on the permissioned Blockchain to approved users through role-based access control. In addition, this paper presents methods with smart contracts if medical institutions request patient information complying with domestic laws by using the distributed Blockchain ledger and eventually granting preliminary approval for sharing information. This service will provide an independent information transaction and the Blockchain technology under test will be adopted in the medical industry.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.6
• /
• pp.303-308
• /
• 2017

Nowadays, living standard is improved and people have high interest to the personal health care problem. Accordingly, people desire to know the personal physical condition and the related medical treatment. Thus, there is the necessary of the personalized medical treatment, and there are many studies about the automatic disease diagnosis and the related services. Those studies focus on the particular disease prediction which is based on the related particular data. However, there is no studies about the medical treatment prediction. In our study, national health data based medical treatment predictor is built by using SVM, and the performance is evaluated by comparing with other prediction methods. The experimental results show that the health data based medical treatment prediction resulted in the average accuracy of 80%, and the SVM performs better than other prediction algorithms.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.38-40
• /
• 2021

Medical domain has a massive number of data records without the response value. Self-supervised learning is a suitable method for medical data since it learns pretext-task and supervision, which the model can understand the semantic representation of data without response values. However, since self-supervised learning performance depends on the expression learned by the pretext-task, it is necessary to define an appropriate Pretext-task with data feature consideration. In this paper, to actively exploit the unlabeled medical data into artificial intelligence research, experimentally find pretext-tasks that suitable for the medical data and analyze the result. We use the x-ray image dataset which is effectively utilizable for the medical domain.