• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.360-362
• /
• 2014

Health Level Seven(HL7)에서 V2.x, V3 보다 향상된 FHIR(Fast Healthcare Interoperabilty Resources)를 표준을 개발하고 있고, 이를 채택한 솔루션 개발이 활발하고, 각 국가 의료환경에서의 검증이 필요하다. 현재 미국에서 성공적으로 널리 사용되는 V2.x Message와 V3 Clinical Document Architecture(CDA)가 존재 하지만, 이 기술 표준들을 개발하고 사용하는데 긴 시간 투자의 문제점이 있다. 현재 V4로 불리우는 개선된 FHIR를 사용함으로 이러한 문제점을 해결할 방법인지 확인한다. 개인건강기록 관리 또한 사회적인 관심을 끌고 있고, 스마트폰 보급률이 급격히 증가하는 함을 반영하여 개인건강기록 관리 시스템을 스마트폰으로 접속 가능한 시스템으로 개발한다. 이를 구축하기 위해서는 Electronic Medical Record(EMR) 시스템과 Personal Health Profiling(PHP) 시스템간의 정보교류를 FHIR Open API로 구성한다. PHP 시스템에서는 이들 트랜잭션을 RESTful 서비스로 제공한다. 본 연구에서는 FHIR기반의 PHP 시스템을 통해 개인건강관리 시스템의 효율성을 검증하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.879-881
• /
• 2019

전자의무기록 (EMR)과 같은 의료 현장에서 수집되는 대용량의 데이터는 임상 해석적으로 잠재가치가 크고 활용도가 다양하나 결측값이 많아 희소성이 크다는 한계점이 있어 분석이 어렵다. 특히 EMR의 정보수집과정에서 발생하는 결측값은 무작위적이고 임의적이어서 분석 정확도를 낮추고 예측 모델의 성능을 저하시키는 주된 요인으로 작용하기 때문에, 결측치 대체는 필수불가결하다. 최근 통상적으로 활용되어지던 통계기반 알고리즘기반의 결측치 대체 알고리즘보다는 딥러닝 기술을 활용한 알고리즘들이 새로이 등장하고 있다. 본 논문에서는 Generative Adversarial Network를 기반한 최신 결측값 대치 알고리즘인 Generative Adversarial Imputation Nets을 적용하여 EMR에서의 성능을 분석해보고자 하였다.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.35 no.5
• /
• pp.132-138
• /
• 2021

Artificial intelligence technology sheds light on new ways of innovating acupuncture research. As acupoint selection is specific to target diseases, each acupoint is generally believed to have a specific indication. However, the specificity of acupoint selection may be not always same with the specificity of acupoint indication. In this review, we propose that the specificity of acupoint indication can be inferred from clinical data using reverse inference. Using forward inference, the prescribed acupoints for each disease can be quantified for the specificity of acupoint selection. Using reverse inference, targeted diseases for each acupoint can be quantified for the specificity of acupoint indication. It is noteworthy that the selection of an acupoint for a particular disease does not imply the acupoint has specific indications for that disease. Electronic medical record includes various symptoms and chosen acupoint combinations. Data mining approach can be useful to reveal the complex relationships between diseases and acupoints from clinical data. Combining the clinical information and the bodily sensation map, the spatial patterns of acupoint indication can be further estimated. Interoperable medical data should be collected for medical knowledge discovery and clinical decision support system. In the era of artificial intelligence, machine learning can reveal the associations between diseases and prescribed acupoints from large scale clinical data warehouse.

• The Journal of Society for e-Business Studies
• /
• v.24 no.3
• /
• pp.73-86
• /
• 2019

After the 4th industrial revolution, the healthcare industry is striving to find new business models through new technologies. Among them, blockchain technology is one of the technologies that have great interest in the healthcare industry. Most providers of personal health record systems have difficulty in securing marketability due to various problems. Therefore, they try to integrate blockchain technology to develop new systems and gain marketability. However, blockchain has limitations in solving the problems of the personal health record system. In this study, we have designed a personalized health data management framework that enables information subjects to acquire full ownership rights of individual's health data, based on distributed ledger technology. For the framework design, we refer to the structure of R3 Corda. It was designed with a different network structure than the existing blockchain systems so that the node can be operated on the personal user's mobile device. This allows information subjects to directly store and manage their own data and share data with authorized network members. Through the proposed system, the information utilization of the healthcare industry can be improved and the public health promotion and medical technology development can be realized.

• Quality Improvement in Health Care
• /
• v.22 no.2
• /
• pp.15-25
• /
• 2016

Objectives: In this study, we examined the validity of Clostridium difficile culture results as a proxy measure of Clostridium difficile infection, and inferred the epidemiologic characteristics of Clostridium difficile infection by tracking the trends of Clostridium difficile culture results. Methods: We reviewed the medical records to figure out the actual possibilities of Clostridium difficile infection of those with positive or negative results of Clostridium difficile culture during the time span from January 2012 to March 2012. We calculated the positive and negative predictive value of Clostridium difficile culture results for Clostridium difficile infection. Furthermore, epidemiologic characteristics of Clostridium difficile infection in a tertiary general hospital in 2012 were analyzed. Result: The estimated positive predictive value of Clostridium difficile culture tests for Clostridium difficile infection was 100%, and the estimated negative predictive value was around 94.4~99.3% depending on the cutoff value of possibility of Clostridium difficile infection. A total of 622 cases were identified as Clostridium difficile infection in a tertiary general hospital in 2012 and there were 4.9 patients with Clostridium difficile infection per 1,000 inpatients. Conclusion: In conclusion, we identified that Clostridium difficile culture results can be used as a proxy measure of Clostridium difficile infection.

• Journal of Digital Convergence
• /
• v.12 no.9
• /
• pp.123-131
• /
• 2014

The demand of the real-time data was promoted by significant development of network and IT technology. In particular, the entry of an aging society and income growth increase the demand for personal health related data which attempt to provide various and evolutional healthcare services by several healthcare institutions. Especially the presentation of the medical examination result is the most basic healthcare services which should be expressed to maximize understanding in personal health records for their own health. However according to absence of systematic visualization framework and visualization model, intuitive understanding of healthcare related data is difficult. Cosequently In this study, customized visualization representation based on the results of medical examination was provided to aviod consistent format for health examinee and establish a variety of data representations.

• Journal of Korean Academy of Nursing
• /
• v.25 no.4
• /
• pp.709-728
• /
• 1995

The job related activities of sixty nine nurses, working in the emergency rooms of three university hospitals, were analyzed for six days according to preestablished checklist of nursing activities ; the frequency of these activities and the amount of time spent in each specific nursing activity. The established checklist was monitored every five minutes for the duration of the duty autu, thus producing 414 items of data. The data were not gathered on consecutive days but over the period of one month from May 6, 1994 to June 5, 1994. The following conclusions are derived from analysis of the data : 1. Twelve categories of nursing activities were obtained : The primary activity was communication related to the patient and all information pertaining to the patient. Other activities included maintaining the patient's record, observation and assessment of the patient, cooperation with other medical personnel, management of equipment and drugs, procedure and treatment, specimen collection, consultation and education for the patient, including drug management and personal hygiene and any other relevant education to the patient's condition. 2. The average frequency of categorized nursing activity can be classified as follows : communication related to patient was the highest at 17.6 times. The next was maintaining the patient's record at 17.3 times. The observation and assessment occurred 16.9 times. Consultation and education for patients and family, 8 times, medication, 5.7 times, and procedures and treatments, 6 times. 3. The average time required for each activity was as follows : 230.1 minutes (or maintaining the patient's record, 204.9 minutes for communication related to the patient, 199.2 minutes for observation and assessment, 71.2 minutes for medication, 66 minutes for consultation and education of the patient and family, and 51.8 minutes for procedures and treatment. 4. The most demanding nursing activity in the emergency room for the nurse was answering questions from the patient's family, maintaining communication between the medical staff, maintaining and reviewing the patient's charts, writing prescriptions and monitoring 1. V. infusion rates. 5. The most time consuming nursing activities for the emergency room nurse include maintaining and following the patient's charts, communication between the medical staff, answering questions from the patient's family, observation of the patient and relaying all of the appropriate patient information to the incoming nurses during a shift change. 6. The F-test was administered to measure the required time for the categorized nursing activities according to day, evening, and night-shift nurses. There were significant differences (p<.05) in specimen collection, observation and assessment, cooperation between medical staffs, personal hygiene, communication related to patient, education and re-search. Posterior multiple comparison test showed that specimen collection, cooperation between medical staffs and personal hygiene were mostly done by the evening-shift nurses. Also most observations and assessments were done by the night-shift nurses. Education and communication to patients were done by day-shift nurses. Thus there were significant difference between shifts for the main nursing activities. So there should considev a reallocation of the duty of nurses on each shift. 7. The F-test also indicated that there wes a similarity in time duration for procedures and treatments and for cooperation between medical staff and nurses in all three hospitals. However, the remaining categories of nursing activities also showed a significant difference between the three hospitals. This indicated that there were differences in each emergency room that influence time for each categorized nursing activities and this should be given more consideration. Recommendations : 1. A seasonal difference should be considered in the activities of nurses in the emergency room and a comparative analysis should be carried out to deter-mine seasonal differentiation. 2. A study on more objectively measurable nursing activities should be administered as well as one determining the subjective responds towards nursing activities in the emergency room.

• Journal of Korean Library and Information Science Society
• /
• v.47 no.1
• /
• pp.149-173
• /
• 2016

As cloud computing becomes more and more popular and ubiquitous, many organizations are deciding to move their whole information infrastructure to the cloud. The healthcare industry is one of those that is beginning to utilize cloud-based solutions en masse. Cloud based computing and storage offers numerous benefits including scalability, cost efficiency, and accessibility, which in turn have the potential to streamline hospital operations. Despite the potential benefits of acquiring this system, considerations must still be given to the migration of the massive amounts of personal and highly protected data to a cloud-based solution. Health care organizations must consider all matters of security, reliability, and availability, to ensure that patients' data remains compliant to the Health Insurance Portability and Accountability Act (HIPAA) compliant. This paper will examine the benefits and challenges of such operation to determine the best practices for the utilization of Electronic Medical Record (EMR) cloud based networking and storage for small to mid-sized hospitals.

• Journal of Pharmacopuncture
• /
• v.22 no.4
• /
• pp.260-268
• /
• 2019

Objectives: The Clinical Decision Support System (CDSS), which analyzes and uses electronic health records (EHR) for medical care, pursues patient-centered medical care. It is necessary to establish the CDSS in Korean medical services for objectification and standardization. For this purpose, analyses were performed on the points to be followed for CDSS implementation with a focus on herbal medicine prescription. Methods: To establish the CDSS in the prescription of Traditional Korean Medicine, the current prescription practices of Traditional Korean Medicine doctors were analyzed. We also analyzed whether the prescription support function of the electronic chart was implemented. A questionnaire survey was conducted querying Traditional Korean Medicine doctors working at Traditional Korean Medicine clinics and hospitals, to investigate their desired CDSS functions, and their perceived effects on herbal medicine prescription. The implementation of the CDSS among the audit software developers used by the Korean medical doctors was examined. Results: On average, 41.2% of Traditional Korean Medicine doctors working in Traditional Korean Medicine clinics manipulated 1 to 4 herbs, and 31.2% adjusted 4 to 7 herbs. On average, 52.5% of Traditional Korean Medicine doctors working in Traditional Korean Medicine hospitals adjusted 1 to 4 herbs, and 35.5% adjusted 4 to 7 herbs. Questioning the desired prescription support function in the electronic medical record system, the Traditional Korean Medicine doctors working at Korean medicine clinics desired information on 'medicine name, meridian entry, flavor of medicinals, nature of medicinals, efficacy,' 'herb combination information' and 'search engine by efficacy of prescription.' The doctors also desired compounding contraindications (eighteen antagonisms, nineteen incompatibilities) and other contraindicatory prescriptions, 'medicine information' and 'prescription analysis information through basic constitution analyses.' The implementation of prescription support function varied by clinics and hospitals. Conclusion: In order to implement and utilize the CDSS in a medical service, clinical information must be generated and managed in a standardized form. For this purpose, standardization of terminology, coding of prescriptions using a combination of herbal medicines, and unification such as the preparation method and the weights and measures should be integrated.

• Korea Journal of Hospital Management
• /
• v.19 no.3
• /
• pp.43-52
• /
• 2014

We empirically show that the effect of mobile EMR's technological characters on system qualities and user satisfaction. For the study, the relationship among technological characters of mobile, EMR's system quality, EMR's information quality, and user satisfaction were modelled and validated with hypotheses. An empirical test was performed for a path model using structural equation modeling on samples of 148 nurses in hospitals from various size and region. This study find that, for the overall sample, there are positive relationships among the technological characters of mobile, EMR's system quality, EMR's information quality, and user satisfaction. And the results support that mobile is an effective method for EMR. Findings of this study have several theoretical and practical implications as follows : First, this study empirically tested the relationship among technological characters of mobile, EMR's system quality, EMR's information quality. Second, the study shows that the technological characters of mobile should be considered for advance of EMR system's quality in mobile environment. And lastly, this study can practically suggest mobile healthcare information system for process effectiveness.