• Journal of Korean Neurosurgical Society
• /
• 제57권6호
• /
• pp.440-444
• /
• 2015

Quality of life is the current trend and issue for the most of human diseases. In moyamoya disease (MMD), surgical revascularization has been recognized as the possible assistance to reduce the neurological insult. However, the progressive nature of the disease has been invincible so far. To improve the quality of life of MMD patients not only the protection from the neurological insult but also the maintenance or improvement of cognitive function is inevitable. For pediatric MMD patients, younger age or longer duration of disease is the key factor among the prognostic factors for bad neurological outcomes. Hence, 'the earlier, the better' is the most precious rule for treatment. Protection from neurological insult is very critical and foremost important to improve cognitive outcome. Clinicians need to know the neuropsychological profile of MMD patients for the care of whole person and make an effort to protect the patients from neurological insults to maintain or improve it.

• 한국컴퓨터정보학회논문지
• /
• 제18권9호
• /
• pp.43-51
• /
• 2013

신뢰성 있는 부정맥 진단을 위해서는 리듬 구간 및 심박 단위의 종합적인 분석을 통하여 심전도 신호에 대한 분류 결과가 제시되어야 한다. 본 논문에서는 심전도 신호의 특징점에 기반하여 규칙기반 분류를 이용한 일정 구간의 리듬 분석을 수행하고 SVM기반 분류를 이용한 심박 단위의 리듬분석을 첨가하였다. 규칙기반 분류에서는 리듬 구간의 특징에 대하여 임상 자료로부터 도출된 규칙 베이스를 이용하여 리듬 유형을 분류하도록 하며, SVM기반 분류에서는 심박 단위의 특징에 대하여 미리 학습된 다중 SVM 분류기를 이용하여 단조 리듬 및 주요 비정상 심박을 분류하도록 한다. MIT-BIH 부정맥 데이터베이스를 이용한 실험을 통하여 11가지 리듬 유형에 대하여 규칙기반 방법만을 적용하였을 경우 68.52%, 규칙기반과 SVM기반의 융합 방법을 적용하였을 경우 87.04%의 분류 성능을 각각 보였다. SVM기반 방법으로 단조 리듬과 배열 리듬에 대한 오분류 개선을 통하여 분류 성능에서 19% 정도가 향상됨을 확인하였다.

• 한국지능시스템학회논문지
• /
• 제22권4호
• /
• pp.405-413
• /
• 2012

심전도 신호의 신뢰성 있는 진단을 위해서는 높은 분류 정확도와 함께 낮은 오분류 성능이 중요하며, 특히 비정상을 정상으로 진단하는 것은 심검자에게 치명적인 문제로 귀결될 수 있다. 본 논문에서는 임상 진단 기준을 반영하는 규칙기반 분류 알고리즘을 이용하여 비정상 리듬을 검출 및 분류하는 방법을 제안한다. 규칙기반 분류는 리듬 구간의 특징에 대한 규칙 베이스를 이용하여 리듬 유형을 분류하도록 하며, 이 때 규칙 베이스는 임상 및 내과 분야의 심전도 전문 임상 자료에 기반한 본 논문의 기준표에 따라 구성된다. MIT-BIH 부정맥 데이터베이스를 이용한 제안 방법의 실험을 통하여 정상동조율, 박동조율, 및 다양한 비정상 리듬에 대한 리듬 유형의 분류가 가능함을 확인하였으며, 특히 비정상 리듬 검출 측면에서는 오분류가 전혀 발생되지 않는 결과를 보였다.

• 한국콘텐츠학회논문지
• /
• 제17권5호
• /
• pp.565-573
• /
• 2017

재난 재해 발생 시, 정부의 위기 대응방식에 대한 사후 평가는 향후 유사한 위기 상황이 발생할 경우를 대비하고 국가의 장기적인 위기관리의 초석이 되는 필수적인 단계이다. 본 논문에서는 국내에서 발생한 구제역에 관하여 정부에서 어떠한 대응 전략을 펼쳤는지를 언론에 보도된 기사 내용을 통해 분석한 연구로써, 먼저 온라인 뉴스 기사로부터 구제역에 관한 키워드들을 추출하여 데이터 큐브를 구성한 후, OLAP 연산과 연관규칙 분석을 수행함으로써 시간 축에 따른 정부의 위기상황 대응행동 및 그에 따른 사회적 파급 효과들을 분석한다. 구제역이 가장 심각했던 2010년 11월부터 2011년 12월까지 국내에서 발생한 구제역에 관한 정부의 위기 상황 대응 방법을 사례분석을 통해 분석하였다.

• ETRI Journal
• /
• 제37권2호
• /
• pp.222-232
• /
• 2015

In this paper, we propose a dual-phase approach to improve the process of heart disease prediction in a mobile environment. Firstly, only the confident frequent rules are extracted from a patient's clinical information. These are then used to foretell the possibility of the presence of heart disease. However, in some cases, subjects cannot describe exactly what has happened to them or they may have a silent disease - in which case it won't be possible to detect any symptoms at this stage. To address these problems, data records collected over a long period of time of a patient's heart rate variability (HRV) are used to predict whether the patient is suffering from heart disease. By analyzing HRV patterns, doctors can determine whether a patient is suffering from heart disease. The task of collecting HRV patterns is done by an online artificial neural network, which as well as learning knew knowledge, is able to store and preserve all previously learned knowledge. An experiment is conducted to evaluate the performance of the proposed heart disease prediction process under different settings. The results show that the process's performance outperforms existing techniques such as that of the self-organizing map and gas neural growing in terms of classification and diagnostic accuracy, and network structure.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• 제46권1호
• /
• pp.66-69
• /
• 2020

Hydatid disease is a zoonotic infection in humans. The disease is endemic in some parts of the world, including Africa, Australia, and Asia, where cattle grazing is common; the disease is spread by an enteric route following the consumption of food contaminated with the eggs of the parasite. Failure to identify this parasite results in delayed diagnosis and increased morbidity to the patient. Upon diagnosis, every possible step should be taken, both surgical and medical, to prevent anaphylactic reactions from the cystic fluid. Postsurgical long-term follow up along with periodical ultrasonography of the liver and computed tomography scan of the abdomen is essential to rule out possible recurrence.

• Journal of Chest Surgery
• /
• 제20권3호
• /
• pp.582-587
• /
• 1987

Castleman`s disease, giant lymph node hyperplasia, is a rare benign disease. The lesion usually consists of a single node, unassociated with any abnormality of the adjacent lymph nodes or other organs. In the first accounts of giant lymph node hyperplasia of Castleman, the lesion was described as solitary and localized to the mediastinum, which is still the most frequent site of involvement. The disease occurs in all age groups and there is no particular sex preference. It is symptomless and is usually detected on chest films as an incidental finding. On a single involvement, it does not recur after excision, whether total or partial, and the main indication of operation is to rule out more serious tumors. Recently multicentric form appears to be a variant of classic giant lymph node hyperplasia and is associated with significant morbidity and mortality. Histologically, two distinct types have been reported; hyaline-vascular and plasma cell. The hyaline-vascular type of lesion is much more common than the plasma cell type. We report two cases of the hyaline-vascular type of Castleman`s disease.

• 대한공간정보학회지
• /
• 제24권2호
• /
• pp.55-62
• /
• 2016

Economic and social damages are expected due to yellow dust, occurring every year in Korea and risk of citizens is getting higher accordingly. This study acquired tweet data for yellow dust, which had been the greatest since 2009 for 11 days before and after February 23, 2015. After that, it conducted an analysis on the issue words and association rule. Regarding acquired tweet data, the results of analyzing issue words by using open source R, statistics language shows that 'Mask' was ranked to be the highest, followed by health-related issue words. This indicates that people put the priority in the use of mask for keeping their health, as a result of the occurrence of yellow dust, and subsequently, they showed an interest in diseases, caused by yellow dust. In addition, yellow dust-related diseases, 'cold', 'rhinitis', 'flu', 'asthma', 'bronchitis' were found as issue words, revealing that people had a high concern on the disease occurrence of the respiratory system. The analytical results are judged to reflect the citizen's thought effectively in the process of establishing measures for the prevention of yellow dust.

• Journal of Electrical Engineering and Technology
• /
• 제11권1호
• /
• pp.247-256
• /
• 2016

This paper proposes Context-Awareness Healthcare for Disease Reasoning based on Fuzzy Logic. It consists of a Fuzzy-based Context-Awareness Module (FCAM) and a Fuzzy-based Disease Reasoning Module (FDRM). The FCAM computes a Correlation coefficient and Support between a Condition attribute and a Decision attribute and generates Fuzzy rules by using just the Condition attribute whose Correlation coefficient and Support are high. According to the result of accuracy experiment using a SIPINA mining tool, those generated by Fuzzy Rule based on Correlation coefficient and Support (FRCS) and Improved C4.5 are 0.84 and 0.81 each average. That is, compared to the Improved C4.5, the FRCS reduces the number of generated rules, and improves the accuracy of rules. In addition, the FDRM can not only reason a patient’s disease accurately by using the generated Fuzzy Rules and the patient disease information but also prevent a patient’s disease beforehand.

• 한방안이비인후피부과학회지
• /
• 제17권3호
• /
• pp.1-7
• /
• 2004

Objectives: In order to establish a base for proper treatment and management of patients with dermal problems through correct diagnosis, I considered the naming rule for dermatology in Oriental Medicine, referring to the dermatology literature compared to western medicine. In addition, this paper examines the characteristic classification of dermatology. Methods: I examined the naming rule of dermatology in Oriental Medicine and then compared the disease names in Oriental and Western medicine and the characteristic classification of dermatology referred to the records. Results: The dermal diseases have been named according to their colors and morphologies, causes, progress of symptoms, recurrent sites, the character of distribution, recurrent seasons, ages, the character of patients' jobs and locations. Sometimes some have been named by referring to their main morphologies, sites, causes, colors and seasons synthetically. However it was found some names for dermal diseases, even though the same diseases, had been named differently according to for example: historical times, condition of locations and the quality of doctors whose process of naming developed and changed over time. The relationship between Oriental and Western medicine of each name for dermal diseases is basically divided into 5 types: same names - same diseases; same names but different diseases; same diseases but different names; one disease with multiple names; and one name with multiple diseases. Considering the methods of classification, these were generally achieved according to their places of origin. It is a method unique to Oriental medicine that we classified some dermal diseases into 疥, 癬, 瘡, 風, 丹, 疱, 疹, 癰, 痘, 疽 and so on and it is very easy to diagnose which part they belong to. This was classified by putting first the causes of diseases; for instance: viruses, bacteria, fungi. Sometimes, however there was a problem, connected to the classification of morphology. Conclusions: I suggest that we need to unify and refine dermatological terms in Oriental Medicine in order to establish a base for proper treatment and management of patients with dermal problems through correct diagnoses.