• 대한한의학회지
• /
• 제21권3호
• /
• pp.9-19
• /
• 2000

Objective : We proposed fundamental rules of prospective Korean Standard Classification of Diseases(Oriental Medicine). Methods : We analysed Korean Standard Classification of Diseases(Oriental Medicine)(established in 1994) in comparison with ICD-10 and Chinese Standard Classification of Disease(Traditional Chinese Medicine). Secondly, we analysed the diagnostic structure of Modem oriental medicine. Results : Korean Standard Classification of Diseases has an inappropriate writing structure, logical errors of classification, confusion of symptoms, 'bing', and 'zheng', inappropriate comparison of disease designations in oriental medicine and western medicine, and the ommission of important items. Secondly, we demonstrate the relations of 'bing' and 'zheng' in modem oriental medicine and disease designations in oriental medicine and western medicine. Conclusions : We propose the separate classification of 'bing' and 'zheng', the qualification of designated names, the structure of 'bing' and 'zheng' system, and a different writing method.

• 한국지능시스템학회논문지
• /
• 제16권1호
• /
• pp.101-107
• /
• 2006

In this research, we propose a hybrid inference architecture for medical diagnosis based on dynamic knowledge map (DKM) and relational database (RDB). Conventional expert systems (ES) and developing tools of ES has some limitations such as, 1) time consumption to extend the knowledge base (KB), 2) difficulty to change the inference path, 3) inflexible use of inference functions and operators. To overcome these Limitations, we use DKM in extracting the complex relationships and causal rules from human expert and other knowledge resources. The DKM also can help the knowledge engineers to change the inference path rapidly and easily. Then, RDB and its management systems help us to transform the relationships from diagram to relational table.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권7호
• /
• pp.3651-3658
• /
• 2016

Computer-aided diagnosis of breast cancer is an important medical approach. In this research paper, we focus on combining two major methodologies, namely fuzzy base systems and the evolutionary genetic algorithms and on applying them to the Saudi Arabian breast cancer diagnosis database, to aid physicians in obtaining an early-computerized diagnosis and hence prevent the development of cancer through identification and removal or treatment of premalignant abnormalities; early detection can also improve survival and decrease mortality by detecting cancer at an early stage when treatment is more effective. Our hybrid algorithm, the genetic-fuzzy algorithm, has produced optimized systems that attain high classification performance, with simple and readily interpreted rules and with a good degree of confidence.

• 대한핵의학회지
• /
• 제35권4호
• /
• pp.224-230
• /
• 2001

EBM is "the conscientious, explicit and judicious use of current best evidence in mating decisions about the care of the individual patient. It means integrating individual clinical expertise with the best available external clinical evidence from systematic research." EBM is the integration of clinical expertise, patient values, and the best evidence into the decision making process for patient care. The practice of EBM is usually triggered by patient encounters which generate questions about the effects of therapy, the utility of diagnostic tests, the prognosis of diseases, or the etiology of disorders. The best evidence is usually found in clinically relevant research that has been conducted using sound methodology. Evidence-based medicine requires new skills of the clinician, including efficient literature-searching, and the application of formal rules of evidence in evaluating the clinical literature. Evidence-based medicine converts the abstract exercise of reading and appraising the literature into the pragmatic process of using the literature to benefit individual patients while simultaneously expanding the clinician's knowledge base. This review will briefly discuss about concepts of evidence medicine and method of critical appraisal of literatures.

• 지능정보연구
• /
• 제3권2호
• /
• pp.93-104
• /
• 1997

The major economic health problem of dairy cattle is mastitis which can affect 10 to 50% of cow-quarters. This health problem is difficult for many dairy farmers and health advisors to understand, diagnose and control. Without special laboratory testing, most mastitis is overlooked. Estimates of annual mastitis cast per cow vary from $50 to $200. For the nearly 9 million cows in the United States, annual loss to the dairy industry amounts to over one billion. A knowledge-based decision aid has been developed to evaluate mastitis data retrieved electronically from two of nine U. S. regional dairy records processing centers. Heuristic rules to diagnose herd mastitis problems were collected and incorporated into the system from various domain experts. This system information. It allows users to select mastitis control schemes with various degrees of aggressiveness and teaches commonly accepted mastitis control practices.

• Clinical Pain
• /
• 제20권2호
• /
• pp.59-69
• /
• 2021

Patients with pain, numbness, and weakness in their elbows, wrists, and hands often need proper rehabilitation treatments. Among them, musculoskeletal injection therapy should be performed after a full evaluation of the patient, taking into account history and physical examination leading to clinical diagnosis. General rules such as accurate diagnosis and injection materials selection are used to achieve maximum benefit with minimal side effects. During injection, patient location, aseptic care, penetration techniques, follow-up and follow-up care must be maintained. Specific techniques may vary depending on the type, lesion, and location of the injection therapy. For optimal effectiveness, physician should inject directly into the lesion and avoid the injection of surroundings as much as possible. Therefore, ultrasound-guided injections are needed to accurately inject. These conditions and other conditions of the hands, wrists, and elbows can be effectively diagnosed and treated with diagnostic ultrasound and ultrasound-guided injections.

• 한국정보처리학회논문지
• /
• 제4권1호
• /
• pp.137-148
• /
• 1997

고장진단 문제는 지식기반 시스템를 이용해 해결하려는 시도가 많이 있어왔다. 그러나 대부분의 방식은 휴리스틱 또는 모델기반 방식으로 단일 오류에 대한 문제에 많은 노력이 이루어져 왔다. 단일 오류에 대한 고장진단문제 해결방식을 다중 오류진 단으로 확대할 때 발생하는 지수적인 계산비용은 피할 수 없는 문제점으로 지적되어 왔다. 이 논문에서는 시스템 구성에 따라 블록으로 구분하면 전체 탐색 영역을 국소 화할 수 있다는 점에 착안하여 다중 오류 진단을 위한 효율적인 알고리즘을 제안한 다. 이 알고리즘의 기본 원리는 오류진단을 위한 출력값 측정 지점에 따라 전체 회로 를 블록으로 나누고 다중오류에 대한 발생원인의 지수적 증가를 줄임으로 효율화 시 킬 수 있다. 각각의 블럭으로부터 발생하는 오류에 대해 결합하는 규칙을 개발하고 이를 통해 상호 논리적인 모순이 없는 최소 오류원인 집합을 구한다.

• Journal of the Korean Data and Information Science Society
• /
• 제26권3호
• /
• pp.611-618
• /
• 2015

오늘날 정보 기술과 소셜미디어의 확산으로 인하여 빅 데이터에 관심이 집중되고 있다. 이를 처리하기 위한 기술 중의 하나가 데이터마이닝기법인데, 이들 중에는 연관성 규칙이 많이 활용되고 있다. 연관성 규칙은 방향에 따라 양, 음, 그리고 역의 연관성 규칙 등이 존재하며, 평가 기준을 설정하고자 하는 경우에는 이들 세 가지 연관성 규칙을 동시에 고려하는 것이 바람직하다고 할 수 있다. 이를 위해 본 논문에서는 의학진단분야에서 활용되고 있는 진단도구들 중에서 민감도, 특이도, 위양성도, 그리고 위음성도를 고려한 균형비교신뢰도를 제안하고자 한다. 또한 흥미도 측도가 가져야 할 조건들을 점검한 후, 예제를 통하여 측도의 유용성을 고찰하였다. 그 결과, 균형비교신뢰도는 비교신뢰도와 역의 비교신뢰도가 양의 값을 가지는 경우에는 양의 값을 가지며, 이들 두 값이 음인 경우에는 음으로 나타났다. 따라서 연관성 규칙의 평가 기준 관점에서 볼 때 비교신뢰도와 역의 비교신뢰도를 개별적으로 이용하기 보다는 균형비교신뢰도를 활용하는 것이 더 바람직하다고 할 수 있다.

• 한국정보통신학회논문지
• /
• 제19권11호
• /
• pp.2609-2614
• /
• 2015

국가연구개발 사업을 계획하고 관리하는 기관에서는 연구개발비 오 남용 및 부정 집행을 방지하기 위하여 다양한 대책을 마련하여 시행하고 있으나 연구개발비의 오 남용을 방지하는 데는 한계를 드러내고 있다[1,2]. 본 논문에서는 이상거래에 대한 사후 적발로 인한 연구개발비 오 남용을 방지하고자 연구개발비 집행계획 단계부터 정보를 수집하여 이상거래를 탐지할 뿐만 아니라 그 결과를 주관연구기관, 전문기관, 신용카드사 간의 상호 실시간 연동으로 공유하여 활용하도록 하였다. 이를 위해 데이터 품질진단 기법 중 연구개발 관련 규정 및 매뉴얼, Q&A, FAQ, 담당자 인터뷰 결과 등과 같은 다양한 정보로부터 업무규칙을 도출하는 아웃사이드인(Outside-In) 분석 방법을 이용하였다.

• 한국지능시스템학회논문지
• /
• 제1권1호
• /
• pp.9-25
• /
• 1991

This tutorial paper has been written for biologists, physicians or beginners in fuzzy sets theory and applications. This field is introduced in the framework of medical diagnosis problems. The paper describes and illustrates with practical examples, a general methodology of special interest in the processing of borderline cases, that allows a graded assignment of diagnoses to patients. A pattern of medical knowledge consists of a tableau with linguistic entries or of fuzzy propositions. Relationships between symptoms and diagnoses are interpreted as labels of fuzzy sets. It is shown how possibility measures (soft matching) can be used and combined to derive diagnoses after measurements on collected data. The concepts and methods are illustrated in a biomedical application on inflammatory protein variations. In the case of poor diagnostic classifications, it is introduced appropriate ponderations, acting on the characterizations of proteins, in order to decrease their relative influence. As a consequence, when pattern matching is achieved, the final ranking of inflammatory syndromes assigned to a given patient might change to better fit the actual classification. Defuzzification of results (i.e. diagnostic groups assigned to patients) is performed as a non fuzzy sets partition issued from a "separating power", and not as the center of gravity method commonly employed in fuzzy control. It is then introduced a model of fuzzy connectionist expert system, in which an artificial neural network is designed to build the knowledge base of an expert system, from training examples (this model can also be used for specifications of rules in fuzzy logic control). Two types of weights are associated with the connections: primary linguistic weights, interpreted as labels of fuzzy sets, and secondary numerical weights. Cell activation is computed through MIN-MAX fuzzy equations of the weights. Learning consists in finding the (numerical) weights and the network topology. This feed forward network is described and illustrated in the same biomedical domain as in the first part.