• Korean Journal of Artificial Intelligence
• /
• v.7 no.2
• /
• pp.19-24
• /
• 2019

Lung cancer is a chronic disease which ranks fourth in cancer incidence with 11 percent of the total cancer incidence in Korea. To deal with such issues, there is an active study on the usefulness and utilization of the Clinical Decision Support System (CDSS) which utilizes machine learning. Thus, this study reviews existing studies on artificial intelligence technology that can be used in determining the lung cancer, and conducted a study on the applicability of machine learning in determination of the lung cancer by comparison and analysis using Azure ML provided by Microsoft. The results of this study show different predictions yielded by three algorithms: Support Vector Machine (SVM), Two-Class Support Decision Jungle and Multiclass Decision Jungle. This study has its limitations in the size of the Big data used in Machine Learning. Although the data provided by Kaggle is the most suitable one for this study, it is assumed that there is a limit in learning the data fully due to the lack of absolute figures. Therefore, it is claimed that if the agency's cooperation in the subsequent research is used to compare and analyze various kinds of algorithms other than those used in this study, a more accurate screening machine for lung cancer could be created.

• Journal of Information Technology Applications and Management
• /
• v.21 no.2
• /
• pp.81-98
• /
• 2014

Recently, due to external environment like the changes in health policy and various healthcare accreditations, along with hospital's internal efforts to improve the quality of medical services, demands for the development of medical information systems are increasing. Some examples are clinical information like DUR (Drug Utilization Review), CVR (Critical Value Report), and automatic benefit processing by treatment purposes, or hospital DSS (Decision Support System) on overall medical practice. Such systems act as a guide in making clinic judgments during practice or in other medical practice, and their effects on the medical treatment improvements are being proven by previous studies. In the reality of increasing attention in the effects of medical treatment improvement, studies related to hospital DDS were mostly focused on clinical, technical, and engineering points of view, and studies focusing on the user viewpoint are very limited. In order to verify the effects of DSS on practice improvements and hospital's management performance, this study used a research model constructed to verify how SERVQUAL of hospital DSS affects hospital management performance in BSC (Balanced Score Card) point of view. To empirically verify the research model, a questionnaire was conducted on the basis of "K-University Hospital's DSS" on clinicians and hospital employees related to system development, and the relationships between the factors were analyzed through path analysis. As a result of path analysis, excluding reactivity, tangibility, confidence, reliability, empathy among service qualities, had partially significant effects on management performance factors (learning and growth, internal process, financial affairs). This study is to prepare the theoretical ground on the management performance analysis of hospital DSS, and suggest the service quality of the system that should be considered in the planning and development stages for improved system.

• Korean Journal of Clinical Pharmacy
• /
• v.30 no.3
• /
• pp.143-148
• /
• 2020

Objective: This study aimed to investigate pharmaceutical care for critically ill neonates and suggest targeted strategies compatible with the Korean health-system pharmacy. Methods: Articles that reported pharmacy practices for critically ill neonates were reviewed. Pharmaceutical care practices and roles of neonatal pharmacists were identified, and criteria were developed for neonates in need of specialized care by clinical pharmacists. Results: Neonatal pharmacists play many roles in the overall medication management pathway. For clinical decision support, multidisciplinary ward rounds, clinical pharmacokinetic services, and consultation for pharmacotherapy and nutrition support were conducted. Prevention and resolution of drug-related problems through review of medication charts contributed to medication safety. Pharmaceutical optimization of intravenous medication played an important role in safe and effective therapy. Information on the use of off-label medicine, recommended dosage and dosing schedules, and stability of intravenous medicine was provided to other health professionals. Most clinical practices for neonates in Korea included therapeutic drug monitoring and nutrition support services. Reduction in medication errors and adverse drug reactions, shortening the duration of weaning medicines, decreasing the use and cost of antimicrobials, and improvement in nutrition status were reported as the outcomes of pharmacist-led interventions. The essential criteria of pharmaceutical care, including for patients with potential high-risk factors for drug-related problems, was developed. Conclusion: Pharmaceutical care for critically ill neonates varies widely. Development and provision of standardized pharmaceutical care for Korean neonates and a stepwise strategy for the expansion of clinical pharmacy services are required.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.28 no.1
• /
• pp.113-121
• /
• 2014

With the development of information technology, knowledge information-oriented and information systems are being rapidly paced. In addition, doctor's needs of the system that assist decision making is gradually increasing. Because the complex process of decision-making should be a lot. We propose a web based system for supporting medical treatment based on Korean medicine ontology. There are three kinds of processes. First, a pattern is decided for patient' symptoms, a formula for the pattern is selected and medicinal materials constituting the formula is added or removed. Second, a formula is decided for patient' symptoms, medicinal materials constituting the formula is added or removed. Third, a Treat method is decided for patient' symptoms, medicinal materials constituting the formula is added or removed. We have designed and implemented the clinical decision support system that supports flexible processes and necessary information and functions. The system shows the appropriate form of ontology knowledge as interrelated and provide analysis and processing, does not show simply search. The system is one of the systems utilizing ontology and a web based system that can be used in anywhere. Therefore, This system Will be useful as for doctors to make decision.

• The Journal of Health Technology Assessment
• /
• v.6 no.2
• /
• pp.81-87
• /
• 2018

With the recent change of healthcare environment including rapid technological development, evidences are more and more important and necessary to support relevant policies in health technology assessment to provide safe and effective health services, utilizing medical resources efficiently. Despite of the emphasis on the importance of real world data and real world evidence in health care research, current infrastructure supporting clinical research is considerably weak due to absence of legal and institutional basis. However, in accordance with the Article 26 of the Health and Medical Technology Promotion Act, there is a limited legal apparatus that can be used only in public data with other dataset for the purpose of healthcare technology assessment at the National Evidence-based Collaborating Agency. Although the use of linked data from various sources was often required in the field of clinical research, it was not yet working well due to insufficient environmental conditions. In order to support the decision-making of medical practice and health care policies, data-linking platform for clinical research is needed. If the legal system that can link up to the data of the private institutions without violating the significant value such as the protection of private informations is established, it will be a decisive foundation reinforcing the researches and policy making processes for the improvement of the national health care system.

• Journal of Sasang Constitutional Medicine
• /
• v.27 no.2
• /
• pp.222-230
• /
• 2015

Objectives The purpose of this study is to design a research to find clinical factors involved in the decision-making process for determining the constitutional prescription based on prospective clinical data. Methods We have created a draft of the case report form. Therefore, seven constitutional experts was interviewed for additional items to be important used to determine the constitutional prescription in clinic. Interviews were done from December 2012 to March 2014, experts per person 2-3 times, took time of about 120 minutes per interview. Since then, we developed the final case report form through the expert meeting. At the same time, the developing the electronic case report form (eCRF) and the protocol to collect constitutional treatment cases was also discussed. Results & Conclusions The items of the case report form were subject general, lifestyle, health measurement, record of expert, prescription and evaluation after medication. The part of the clinical symptoms of the record of expert allowed to be recorded in the 5-point scale for the collection of quantitative data as much as possible. Assuming a re-visit of the patient, if necessary, twice the recording were to be possible. At the same time, the eCRF and the protocol to collect constitutional treatment cases were also developed. In this study, it will be able to more objectively standardize the medical decision making process that the experts of constitutional prescription decision. As a result, it will be possible to provide the standardized constitutional medical services.

• Korean Journal of Digital Imaging in Medicine
• /
• v.10 no.2
• /
• pp.33-37
• /
• 2008

To keep the online medical records available to anyone without constraint of time and space, introducing EMR (Electronic medical record), which is a clinical support management system. The purpose of this study is to develop interface standard of clinical test device. Integration and sharing of medical information is faced with enormous obstacles because medical organizations and associated companies are separately developing the interface. I hope that multi-function management system with workstation concept is operated to efficiently transmit clinical device result data based on this study. Transfer of precise medical result data available for decision making will improve quality of health care service.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.11
• /
• pp.119-126
• /
• 2015

CDSS provides clinical doctors with knowledge to be required when they diagnose or make decision about treatment strategy. Arden Syntax is one of the language with which we write MLM that is a component of CDSS. It was designated as a standard by HL7/ANSI. ArdenML is an XML version of Arden Syntax. In this paper we propose a tool which translates Arden Syntax MLMs into ArdenML MLM. To this end we first defines the corresponding relation between two languages. Next we presents a modified version of Arden Syntax grammar to improve performance of lexical analysis and minimize parsing conflicts. Finally we presents syntax and semantics gaps between the both languages, which are a structural representation problem, a data type problem, and a disrelation problem. Our translator resolves such issues and generates exact ArdenML codes for an arbitrary Arden Syntax MLM.

• Health Policy and Management
• /
• v.15 no.4
• /
• pp.1-25
• /
• 2005

Legislation on pharmaceutical reimbursement decision using economic evaluation results was made in Korea in fm, but has yet to be fully implemented. We evaluated the quality of Korean economic evaluation studies of pharmaceuticals to understand gaps between legislation and implementation. From this evaluation, we propose policy options that might strengthen the research Infrastructure In order to support such studies. We reviewed 23 published studies for drugs conducted between 1996 and 2004. Evaluation criteria included methodological characteristics, healthcare system characteristics, population characteristics, and applicability of results. Large variation in study quality was observed, particularly with study design, outcome data, treatment patterns and interpretation. Korean clinical data used was mostly from observational studies of 1-2 hospitals. Foreign data was extracted from clinical trials that did not Include Asian population and their selection criterion was not clarified. With respect to treatment patterns, medical records and hospital bills were used without adjustment regarding area, hospital type, and others. And next frequent situation relied on expert opinion from academic physicians in specialty practice. preference measures, when used, were not elicited from the Korean population. $78.3\%$ of studies did not clarify the funding source. If the Korean economic evaluation policy is to provide meaningful data for decision makers, the quality of cost-effectiveness studies will need to improve dramatically. This may involve access to or creation of better data, more diverse funding, unproved training of researchers and evaluators, and partnerships with technology manufacturers.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.898-902
• /
• 2003

In this paper we proposes a new technique for identification of breast cancer by classification of proteome pattern generated from 2-D polyacrylamide gel electrophoresis (2-D PAGE) and development of cancer diagnosis system : HABIT. Proteome patterns reflect the underlying pathological state of a human organ and it is believed that the anomalies or diseases of human organs are identified by the analysis or classification of the patterns. Proteome patterns consist of quantitative information of the spots such as their size, position, and density in the proteome image produced from 2-D PAGE, for the Image mining of proteome pattern, SVM(support vector machine) and GA(genetic algorithm) are used to generate a decision model for the identification of breast cancer The decision model was then used to classify an independent set of test proteome patterns into the affecter and unaffecter classes. The proposed technique was tested by actual clinical test samples and showed a good performance of a hit ratio of 90%.