• 전기학회논문지
• /
• 제57권6호
• /
• pp.1058-1062
• /
• 2008

In clinical decision support system(CDSS), unlike rule-based expert method, appropriate data-driven machine learning method can easily provide the information of individual feature(clinical test) for disease classification. However, currently developed methods focus on the improvement of the classification accuracy for diagnosis. With the analysis of feature importance in classification, one may infer the novel clinical test sets which highly differentiate the specific diseases or disease states. In this background, we introduce a novel CDSS that integrate a classifier and feature selection module together. Random forest algorithm is applied for the classifier and the feature importance measure. The system selects the significant clinical tests discriminating the diseases by examining the classification error during backward elimination of the features. The superior performance of random forest algorithm in clinical classification was assessed against artificial neural network and decision tree algorithm by using breast cancer, diabetes and heart disease data in UCI Machine Learning Repository. The test with the same data sets shows that the proposed system can successfully select the significant clinical test set for each disease.

• 대한치과의사협회지
• /
• 제48권6호
• /
• pp.459-468
• /
• 2010

International Classification of Disease (ICD-10) is widely used as a crucial reference not only in the medical diagnosis of diseases but also within the health insurance system. It makes possible for medical personnel to make decisions systematically and for the people working in the health insurance or public health industries to better understand medical issues. However, this classification is often not enough or acceptable in a clinical setting. Many countries amend in their own way to make it more appropriate for their people. Korean Classification of Disease (KCD-5) was made by adding a 5 digit code for some diseases to clarify the conditions of the patients. The authors found problems of KCD-5 in temporomandibular disorders and several related medical problems. Medical treatment for these problems had not been covered even by public health insurance until 2000 in Korea. For the last decade, private insurance companies have introduced new items for reimbursement of the treatment fees the patients actually pay. The authors assumed that many patients with these medical problems encountered difficulties in the reimbursement from private insurance companies because KCD-5 did not classify these medical conditions appropriately. An overview of KCD-5 and suggestions for improvement are introduced in this study.

• Journal of Preventive Medicine and Public Health
• /
• 제31권3호
• /
• pp.540-563
• /
• 1998

This Study has been carried out to make a recommendation for the next amendment of the Infectious Disease Prevention Act with a specific focus on the kind of notifyable disease. Korean, Japanese, German, U.S, English and French acts on infectious diseases prevention were reviewed, compared with and analized in regards of numbers and kinds of notifyable infectious diseases and their tendency of amendments. An criteria was designed to assess the level of validity of diseases to be designated in the act. Four items, the fatality (greater than 10% or not), the possibility to make a big epidemic, the availability of efficient vaccination and the usefulness of isolation, are used in the assessment. This index is applied to the diseases in Korean and other countries' Infectious Disease Prevention Acts. Results are as follows: 1. The Korean Infectious Disease Preventon Act has a unique way of classifying the notifyable infectious disease, that is, the first, the second and the third class. But the author cannot find the basis of classification. No other countries reviewed have the similar classification. 2. The ten diseases, cholera, plague, yellow fever, diphtheria, typhoid fever, poliomyelitis, rabies, tetanus, malaria, and meningococcal meningitis are designated as the notifyable diseases not only in Korea but also in Japan, Germany, United States, England and france. 3. Thirty seven diseases including small pox, Lassa fever, anthrax, influenza, German measles, Legionellosis, infection with E. coli O157:H7, Q-fever, brucellosis, Lyme disease are designated as legal disease at least one of the above mentioned countries. 4. The Korea has been coped with the change of the infectious disease occurrence for last fifty years in amendment of the Infectious Disease Prevention Act. 5. Japan has a special infectious surveillance system composed of 3,880 clinics throughout the whole country. 6. Germany has classified infectious diseases in five categories which are based on seriousness of disease. Any confirmed death, cases and suspected cases in class I should be reported within 24 hours. But only confirmed death and cases in class II, but not suspected cases, are reportable in Germarny. 7. Plague, bacillary dysentery, pertussis, mumps, Japanese encephaltis and Korean hemorrhagic fevers are diseases with high credits validity index among Korean legal disease. 8. German measles, anthrax, E. coli O157 : H7 infection, Lassa fever, Q-fever, brucellosis are high in validity index among those which are not designated in Korea but designated in other countries. In conclusion, the Korean Infectious Disease Prevention Act has well been coped with the changes of infectious disease occurrence for last fifty years, but the classification basis and the validity of diseases to be designated as legal diseases is worth reevaluating.

• 한국멀티미디어학회논문지
• /
• 제20권2호
• /
• pp.205-215
• /
• 2017

The brain magnetic resonance images (MRI) is an important imaging biomarker in Alzheimer's disease (AD) as the cerebral atrophy has been shown to strongly associate with cognitive symptoms. The decrease of volume estimates in different structures of the medial temporal lobe related to memory correlates with the decline of cognitive functions in neurodegenerative diseases. During the past decades several methods have been developed for quantifying the disease related atrophy of hippocampus from MRI. Special effort has been dedicated to separate AD and mild cognitive impairment (MCI) related modifications from normal aging for the purpose of early detection and prediction. We trained a multi-class support vector machine (SVM) with probabilistic outputs on a sample (n = 58) of 20 normal controls (NC), 19 individuals with MCI, and 19 individuals with AD. The model was then applied to the cross-validation of same data set which no labels were known and the predictions. This study presents data on the association between MRI quantitative parameters of hippocampus and its quantitative structural changes examination use on the classification of the diseases.

• 대한음성언어의학회:학술대회논문집
• /
• 대한음성언어의학회 2003년도 제19회 학술대회
• /
• pp.208-211
• /
• 2003

This paper introduces a history and achievements of the research activities on screening of laryngeal diseases using acoustic analysis. First domestic and international research trends are introduced. Next brief introduction of the research results by the authors are mentioned. First, classification method of the laryngeal diseases using neural network is summarized. Then similar research using ARS (Automatic Response System) is mentioned. Finally, current research activities on screening of laryngeal diseases on internet is introduced.

• 스마트미디어저널
• /
• 제9권1호
• /
• pp.16-22
• /
• 2020

본 연구에서는 Multi-Tasking U-net를 사용하여 영역 세분화 작업(Segmentation) 과 분류 작업(Classification) 이 동시에 수행되게 함으로써 파프리카 병과 충 진단을 수행하였다. 시설 농장의 파프리카에는 병의 종류가 다양하지 않다. 이 연구에서는 비교적 발생빈도가 높은 흰가루병과 응애에 의한 피해, 정상 잎 3개의 클래스에 대해서만 진단 할 수 있도록 하였다. 이를 위한 중추 모델로는 U-net을 사용하였다. 또, 이 모델의 Encoder와 Decoder의 최종 단을 활용하여 분류 작업과 영역 세분화 작업이 각 각 수행되게하여, U-net의 Encoder가 분류작업과 영역 세분화 작업에 공유되도록 하였다. 학습 데이터로는 정상 잎 680장, 응애에 의한 피해 잎 450장, 흰가루병 370장을 사용하였다. 테스트 데이터로는 정상 잎 130장, 응애에 의한 피해 잎 100장, 흰가루병 90장을 사용하였고, 이를 통한 테스트 결과로는 89%의 인식률을 얻었다.

• ETRI Journal
• /
• 제46권2호
• /
• pp.263-276
• /
• 2024

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

• Tuberculosis and Respiratory Diseases
• /
• 제78권3호
• /
• pp.180-189
• /
• 2015

Accurate lymph node staging of lung cancer is crucial in determining optimal treatment plans and predicting patient outcome. Currently used lymph node maps have been reconciled to the internationally accepted International Association for the Study of Lung Cancer (IASLC) map published in the seventh edition of TNM classification system of malignant tumours. This article provides computed tomographic illustrations of the IASLC nodal map, to facilitate its application in day-to-day clinical practice in order to increase the appropriate classification in lung cancer staging.

• The Journal of Korean Physical Therapy
• /
• 제5권1호
• /
• pp.47-60
• /
• 1993

This study was conducted to investigate the changes diseases of physical therapy patient. Through the analysis, of total 2,902 cases in one university hospital and one general hospital in Taegu, of which 1,619 cases for 1989 and 1,283 cases for 1981. The physical records were analyzed in terms of sex, age, pattern in PT diseases, fee, and medical department of PT. The international classification of Diseases, 9th revision was used fer the study. Major results are as follows : 1. The ratio of male me female nae 1.51 to 1 in 1989, 1.53 to 1 in 1991. The proportion of the elderly over 60 was $15.6\%$ in 1989, $22.0\%$ in 1989. And the age groups of 50-59 years ranked the first an years. 2. As to the PT patients of medical department, Orthopaedics$(50.3\%)$, Neurosurgery$(28.1\%)$. Neuromedicine$(8.0\%)$. Plastic surgery$(4.4\%)$, and Dentry$(3.2\%)$ in that order in 1989. On the other hand, Orthopaedics$(51.2\%)$, Neurosurgery$(22.1\%)$, Neuromedicine$(9.6\%)$, Plastic surgery$(6.5\%)$, and Internal medicine$(6.5\%)$ in that order in 1991. 3. No significant difference was observed by season of PT patients, but winter (December, January and February) ranked the first all years. 4. No significant difference was observed changes in diseases as for the 56 international classification of diseases of PT patients, Diseases of the musculoskeletal system and connective tissue occupied the largest proportion all years. Fractures increased from $21.4\%$ in 1989, $24.5\%$ in 1991. On the other hand, Diseases of the nervous system remarkably increased from $8.9\%$ in 1989, $19.7\%$ in 1991.

• 지능정보연구
• /
• 제26권3호
• /
• pp.127-147
• /
• 2020

세계는 신형 코로나바이러스 감염증(COVID-19)으로 수 많은 인명 피해와 경제적 손실을 기록하고 있는 상황이다. 우리나라 정부는 연구개발(Research & Development)을 통해 국가 감염병 위기를 극복하려는 전략을 수립하고 실행하기 위한 투자방향을 수립하였다. 기존 기술분류나 과학기술 표준분류에 따른 통계를 활용하면 특정 R&D 분야의 특이점 및 변화를 발견하기 어렵다는 한계가 존재해왔다. 최근 우리나라 감염병 연구개발 과제를 대상으로 수요자의 목적에 맞게 분류체계를 수립하고 연구비 비교 분석을 통해 투자가 요구되는 연구 분야를 제시하는 연구들이 진행되었다. 하지만 현재 국가 보건 안보와 신성장 산업육성이라는 목표를 달성하기 위한 실행방안으로 요구되고 있는 전염병 연구분야의 국가간 협력전략 수립에 필요한 정보를 체계적으로 제공하고 있지 못한 상황이다. 따라서 국가 공동 연구개발 전략 수립을 위한 분류체계와 분류모델기반의 정보서비스에 대한 연구가 요구되고 있다. 우선 감염병관련 NTIS 과제데이터를 기반으로 정성분석을 통해 7개의 분류체계를 도출하였다. 스코퍼스(Scopus) 데이터와 양방향 RNN모델을 사용하여, 분류체계 모델을 학습시켰다. 최종적인 모델의 분류 성능은 90%이상의 높은 정확도와 강건성을 확보하였다. 실증연구를 위해 주요 국가의 코로나바이러스 연구개발 과제를 대상으로 전염병 분류체계를 적용하였다. 주요 국가의 감염병(코로나바이러스) 연구개발 과제를 분류체계별로 분석한 결과, 세계적으로 유행하는 바이러스의 예상치 못한 창궐이 확산되는 속도에 비해 백신과 치료제 개발이 제대로 이뤄지지 않는 원인의 배경을 간접적으로 확인할 수 있었다. 국가별 비교분석을 통해 미국과 일본은 상대적으로 모든 영역에 골고루 연구개발 투자를 하고 있는 것으로 나타난 반면, 유럽은 상대적으로 특정 연구분야에 많은 투자를 하는 집중화 전략을 취하는 것으로 나타났다. 동시에 주요 국가의 코로나 바이러스 주요 연구조직에 대한 정보를 분류체계별로 제공하여 국제 공동R&D 전략의 기초정보를 제공하였다. 본 연구 결과를 통해 세 가지 정책적 의미를 도출할 수 있다. 첫째, 데이터기반 과학기술정책 관점에서 수요자 관심분야에 대한 국가 R&D사업의 정보를 글로벌 기준으로 문서를 분류하는 방안을 제시하였다. 둘째, 감염병관련 국가 R&D사업 영역에 대한 정보분석 서비스 기획의 기반을 마련하였다. 마지막으로 국가 감염병 R&D 분류체계 수립을 통해 분류 체계의 궁극적 목표인 산업, 기업, 정책 정보를 제공할 수 있는 기반을 마련한 것이다.