• 한국전자통신학회논문지
• /
• 제13권3호
• /
• pp.661-668
• /
• 2018

피부 저항을 이용한 생체 신호는 스트레스성 질환에 따라 각각 다른 특성을 보이고 있으며 이 특성을 이용하여 스트레스성 질환을 진단하는 생체진단 장비들이 개발 되었으며, 장비들은 피부 저항 측정기에서 측정한 신호를 해석하기 쉽게 출력해주며, 그 분야의 전문가는 출력 신호를 직접 보고 어떤 스트레스성 질환의 가능성이 높은지를 판단하게 된다. 하지만 각 측정 대상자에게서 측정된 생체 신호를 분석하여 측정 대상자가 어떤 스트레스성 질환을 가지고 있는지를 사람이 정확히 판단하기는 매우 어려울 뿐만 아니라 판단의 결과가 잘못될 가능성도 매우 높다. 이런 문제점을 해결하기 위하여 본 연구에서는 머신러닝 기법을 이용하여 측정된 신호가 어떤 스트레스성 질환의 신호에 해당하는지를 판단하는 기능을 구현하였다. 측정 장비의 낮은 컴퓨팅 능력을 고려하여 분류 기법은 SVM을 사용하였으며, 훈련 데이터와 테스트 데이터는 13개의 질환을 중심으로 오차범위 5를 사용하여 각 질환 당 1,000개를 랜덤하게 생성하여 사용하였다. 모의실험 결과에서 90% 이상의 판단 정확도를 보였으며 앞으로 측정 장비가 실제로 환자들에게 적용되면 다시 생성된 데이터로 분류기를 재훈련 할 수 있게 구성하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2006년도 춘계학술발표대회
• /
• pp.407-410
• /
• 2006

방대한 양의 다양한 데이터들이 발생되는 의료분야에서는 임상데이터를 기반으로 보다 정확하고 효율적으로 현상을 분석/판단하여 의사가 환자진료 시 정확한 진단과 치료를 수행할 수 있도록 보조해주는 적절한 의사결정지원시스템이 요구되고 있다. 따라서, 이와 같은 요구를 충족시키기 위해서는 다종 다양한 데이터로부터 간결하면서도 효과적으로 개념들을 추출하고 구조화하여 개념계층구조로 표현할 수 있어야 하며, 실세계의 데이터에 대한 구조화와 요약을 제공하고 필요한 정보를 수월하게 접근할 수 있어야 한다. 본 연구에서는, 도메인 내의 다양한 데이터들로부터 개념들을 추출하고, 개념들 사이의 상하위 관계를 파악하여 개념계층구조를 구축하기위한 정형화된 데이터분석기법으로서 형식개념분석기법(Formal Concept Analysis)을 소개하고, 이를 치과 교정학 분야의 환자 임상데이터 분석기법(Cephalometric Analysis)에 융합한 형태의 임상의사결정지원시스템 개발 및 향후 연구과제 등에 관해 설명한다.

• 보건행정학회지
• /
• 제28권3호
• /
• pp.263-271
• /
• 2018

Health technology assessment (HTA) is defined as multidisciplinary policy analysis to look into the medical, economic, social, and ethical implications of the development, distribution, and use of health technology. Following the recent changes in the social environment, there are increasing needs to improve Korea's healthcare environment by, inter alia, assessing health technologies in an organized, timely manner in accordance with the government's strategies to ensure that citizens' medical expenses are kept at a stable level. Dedicated to HTA and research, the National Evidence-based Healthcare Collaborating Agency (NECA) analyzes and provides grounds on the clinical safety, efficacy, and economic feasibility of health technologies. HTA offers the most suitable grounds for decision making not only by healthcare professionals but also by policy makers and citizens as seen in a case in 2009 where research revealed that glucosamine lacked preventive and treatment effects for osteoarthritis and glucosamine was subsequently excluded from the National Health Insurance's benefit list to stop the insurance scheme from suffering financial losses and citizens from paying unnecessary medical expenses. For the development of HTA in Korea, the NECA will continue exerting itself to accomplish its mission of providing policy support by health technology reassessment, promoting the establishment and use of big data and HTA platforms for public interest, and developing a new value-based HTA system.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• 제30권4호
• /
• pp.145-152
• /
• 2019

Objectives: The detection of autism spectrum disorder (ASD) is based on behavioral observations. To build a more objective datadriven method for screening and diagnosing ASD, many studies have attempted to incorporate artificial intelligence (AI) technologies. Therefore, the purpose of this literature review is to summarize the studies that used AI in the assessment process and examine whether other behavioral data could potentially be used to distinguish ASD characteristics. Methods: Based on our search and exclusion criteria, we reviewed 13 studies. Results: To improve the accuracy of outcomes, AI algorithms have been used to identify items in assessment instruments that are most predictive of ASD. Creating a smaller subset and therefore reducing the lengthy evaluation process, studies have tested the efficiency of identifying individuals with ASD from those without. Other studies have examined the feasibility of using other behavioral observational features as potential supportive data. Conclusion: While previous studies have shown high accuracy, sensitivity, and specificity in classifying ASD and non-ASD individuals, there remain many challenges regarding feasibility in the real-world that need to be resolved before AI methods can be fully integrated into the healthcare system as clinical decision support systems.

• 지능정보연구
• /
• 제11권1호
• /
• pp.17-33
• /
• 2005

자기공명영상과 계층적 신경망을 이용하여 간경변증을 단계별로 분류하고자 하였다. 내원한 231명의 데이터를 분석하였으며, 각 단계별 분류는 정상,1, 2, 3단계로 분류하였다. TI강조 자기공명 간 영상으로부터 정상 간 실질과 간 경변 결절을 추출하고, 간 경화증의 단계를 객관적으로 해석 분류하였다. 간 경변 분류기 구현은 계층적 신경망을 이용하였고, 명암도 분석과 간 결절 특성을 통하여 정상간과 3단계의 간 경변으로 구분하였다. 제안한 신경망 분류기는 오류 역전파 알고리듬을 이용하였다. 분류결과 인식율이 정상군은 $100\%$, 1 단계는 $82.8\%$, 2 단계는 $87.1\%$, 3 단계는 $84.2\%$의 분류율을 나타내었다. 신경망 분류 결과와 전문의 판독 결과를 서로 비교한 결과 인식률은 매우 높게 나타났다. 만일 더욱더 충분한 데이터나 파라미터를 가지고 지속적으로 수행한다면 간 경변 환자들에게 임상적으로 지원하는 도구뿐만 아니라 의료전문 신경망으로도 기대된다.

• 지역사회간호학회지
• /
• 제29권2호
• /
• pp.170-183
• /
• 2018

Purpose: Although innovative interventions using technologies have been introduced in long-term care settings, available evidence is still anecdotal. The purpose of this study is to investigate and synthesize the outcomes of interventions using technologies delivered to nursing home residents. Methods: Published clinical trials were identified through PubMed, CINHAL, Cochrane and PsycINFO databases and manually hand-searching. Eligible studies were articles published between 1997-2016 in English or Korean with a randomized controlled trial or quasi-experimental design in which interventions using technologies were delivered to nursing home residents. Results: A total of 20 studies were selected for this review. Types of interventions using technologies were classified into the electronic documentation technology (n=1), the clinical decision support system (n=1), the safety technology (n=1), the health and wellness technology (n=10), and the social connectedness technology (n=7). Overall resident outcomes indicated that interventions using technologies improved behavioral symptoms and psycho-social outcomes, but mixed results were shown in the aspects of physical function, cognitive function, social relationship and quality of service. Conclusion: This review demonstrates that incorporating technologies into nursing home care have positive effects on residents' psycho-social outcomes and behavioral symptoms. To disseminate the effectiveness of interventions using technologies, further research is needed to determine what mechanisms underlying such relationships exist.

• 셀메드
• /
• 제6권3호
• /
• pp.15.1-15.4
• /
• 2016

Evidence based practice (EBP) is a system of applying the most current and valid high quality evidence to support clinical decision making in a healthcare setting. In the twenty five years since its inception, EBP has become the accepted benchmark for excellence in healthcare. Although the system emerged within the biomedical sciences, in the years since EBP has become normative across all healthcare modalities from dentistry, allied health to complementary and alternative medicine (CAM). Practicing evidence based medicine within any modality potentially offers the patient the best available care based on high quality evidence. Yet it is the nature of the evidence that provokes some questions about the suitability of EBP across all modalities of healthcare. The meta analysis of randomized controlled trial (RCT) stands at the pinnacle of the hierarchy of evidence in EBP. This forms a challenge to CAM due to the difficulty in reducing the elementals of a holistic naturopathic assessment of a patient into an answerable question to be tested within a RCT. On one level this makes EBP paradigmatically incompatible with CAM, yet on another level it presents the opportunity to redefine the parameters of what is considered high level evidence. EBP has become a tool, and at times a weapon wielded by governments and health insurance companies to direct healthcare funding and policy. The implications of the nature of accepted evidence are becoming far reaching. The pursuit of the best available healthcare for each individual is the focus of EBP. However, the injudicious use of this system to direct health policy is fraught with biomedical bias and dominance. This issue raises the challenge to CAM to present high level evidence according to the rules of evidence, or face the annihilation of centuries of empirical knowledge.

• 한국컴퓨터정보학회논문지
• /
• 제27권12호
• /
• pp.69-76
• /
• 2022

본 논문에서는 MIMIC-IV(Medical Information Mart for Intensive Care) v2.0 데이터를 이용한 시계열 데이터의 정제 및 가공 방법을 제안한다. 더불어 해당 가공법을 기반으로 정제한 데이터셋을 활용하여 구축한 기계학습 기반의 욕창 조기 경보 시스템을 통해 해당 가공 방법의 유의성을 검증하였다. 구현된 욕창 조기 경보 시스템은 병변이 발생하기 전 12, 24시간에 미리 의료진에게 경보를 주는 시스템이다. 전자의무기록(Electronic Medical Record; EMR) 시스템과 연동하여 실시간으로 환자의 욕창 발생 위험도를 의료진에게 알려 중환자 의사결정을 지원하고, 나아가 효율적인 의료 자원 배분을 가능하게 한다. 여러 기계학습 모델 중 GRU 모델을 사용하였을 때, AUROC 평가지표를 기준으로 발생 전 12시간이 0.831, 24시간이 0.822로 가장 좋은 성능을 보였다.

• 한국컴퓨터정보학회논문지
• /
• 제26권7호
• /
• pp.9-17
• /
• 2021

본 연구는 대장암 환자의 치료방법 중 하나인 항암화학요법을 분류할 수 있는 시스템인 CDSS연구의 일환으로 시행되었다. 대장암 치료에서 환자의 상태에 맞는 항암화학요법의 선택은 환자의 생존 기간과 직결되기 때문에 매우 중요하다. 따라서 본 연구에서는 대장암 환자의 개인적, 병리학적 특성을 사용해 기저 모델, 병리학적 모델, 그리고 환자의 두 가지 특성을 모두 사용한 결합 모델을 만들어 머신러닝 알고리즘으로 항암화학요법을 분류하였다. Top-n Accuracy와 ROC 곡선, AUC로 모델의 예측 정확도를 비교한 결과, 결합 모델에서 가장 우수한 예측 정확도를 보였으며, LGBM 알고리즘의 성능이 가장 우수한 것을 알 수 있었다. 본 연구에서는 머신러닝 알고리즘을 이용해 환자 특성별 모델을 분류함으로써 환자의 상태에 맞는 항암화학요법 분류 모델을 구축하였다. 향후 연구에서 본 연구 결과를 기초한다면 더 좋은 성능의 항암화학요법 분류 모델을 만들어 CDSS 연구에 도움이 될 것이다.

• 지역사회간호학회지
• /
• 제12권2호
• /
• pp.361-374
• /
• 2001

This study was done to identify a status of home visiting project as a community health nursing system, that was the organization. personal who have age, educational background, marital status, position, experience of the home visiting in the public sectors in part of Seoul. Kyonggi, Kang-won area, It was done to provide basis data for the development of effective visiting nurses project in the health sectors, where was Health Centers in urban and rural. Branch of Health Center in rural and Health posts. The question airs were distributed 352 public health workers who working place was 118 health workers in 12 health centers in Seoul. 56 public health workers among 39 health center and other public health sectors in Kyonggi and 178 public health workers among health center and health care sectors. Data collected from October to December. 2000. The analysis by SAS system with F test, percentage and frequency. The major result were as follows. The general characteristics of the respondent show that most of them were graduates from community college and RN-BS with broadcast that they had not completed CPHN course but only two health workers have trained for the visiting nurses project. As for their grade in the position, the most of health workers have seventh level and the other CHP were above sixth level in the health care post that in the government structure. This indicates that workers do not have great authority in decision making, the most period of works in the position was one and two years indicating that they change jobs frequently. On an average their clinical experience was 4.11 years which is ideal for the total service. As for preparation of staff for home visiting workers education on visiting nurses program have to receive short term or longer term training course for strong emphasis. The analysis showed that public health visiting workers responds about active job performance that based on an area, approach of acting by districts, education and position are shown statistically significant difference between acceptance of the visiting nursing job show the same as well as visiting nurses project. Special concerns for visiting Nursing care spread came to burden, many of activity carry out main solution is covered the health problem connective support system needs of quality and quantity which out health problem. As 71.1% of visiting health service held on the poor population was under the guardianship of the law, but people who health insurance wide application under law shown a tendency to increase gradually. The general characteristics of the patients showed 56.2% of female on average of age was 66.1 years old, they have health problem was the most of 47.6% of high blood pressure and stroke, the other and as a problem that economics, which is complex welfare with out health problem. Community health care service should be combined health and social work program. The form of delivery of visiting health care given the most guide and education with counselling and support. (33.6%) Among the six category of visiting care service shown statistically significant difference and next is fundamental care, remedy care with priority.