• 한국컴퓨터정보학회논문지
• /
• 제15권12호
• /
• pp.197-207
• /
• 2010

대용량(High-throughput) 형태로 얻어진 cDNA 마이크로어레이 데이터에 다양한 데이터 마이닝 기법을 적용하면 서로 다른 조직에서 추출한 유전자의 발현정도를 비교할 수 있고 정상세포와 암세포에서 발현량의 차이를 보이는 DEG(Differently Expression Gene) 유전자를 추출할 수 있다. 이들을 이용하여 병을 진단할 수 있을 뿐만 아니라, 암의 진행 단계(Cancer Stage)에 따른 치료 방법을 결정할 수 있다. 마이크로어레이를 기반으로 한 대부분의 암 분류자는 기계학습 기법을 이용하여 암 관련 유전자를 추출하여, 이들 유전자를 총체적으로 이용하여 독립 샘플의 클래스(암, 정상)를 판정한다. 하지만 유전자의 발현량의 차이뿐만 아니라 유전자와 유전자의 상관관계의 변화가 질병 진단에 활용될 수 있다. 대부분의 질병은 단독 유전자의 변이에 의한 것이 아니라 유전자의 모듈로 이루어진 유전자조절네트워크의 변이에 의한 것이기 때문이다. 본 논문에서는 조건에 따라 특이적 관계를 나타내는 유전자 쌍을 식별하여, 이들 유전자 쌍을 이용한 유전자 분류 모듈을 생성한다. 분류 모듈을 이용한 암 분류 방법이 기존의 암 분류 방법보다 높은 정확도로 암과정상 샘플을 분류함을 보여주고 있다. 분류 모듈을 구성하는 유전자의 수가 상대적으로 적으므로 임상키트로의 개발도 고려할 수 있다. 향후 분류 모듈에 속하는 유전자의 기능적 검증을, GO(Gene Ontology)를 활용함으로서, 밝혀지지 않은 새로운 암 관련 유전자를 식별하고, 분류 모듈을 확대하여 암 특이적 유전자조절네트워크 구성에 활용할 계획이다.

• 한국컴퓨터정보학회논문지
• /
• 제26권11호
• /
• pp.21-31
• /
• 2021

최근 코로나(Covid-19)의 영향으로 스마트 헬스케어 관련 산업과 비대면 방식의 원격 진단을 통한 질환 분류 예측 연구의 필요성이 증가하고 있다. 일반적으로 호흡기 질환의 진단은 비용이 많이 들고 숙련된 의료 전문가를 필요로 하여 현실적으로 조기 진단 및 모니터링에 한계가 있다. 따라서, 간단하고 편리한 청진기로부터 수집된 호흡음을 딥러닝 기반 모델을 활용하여 높은 정확도로 분류하고 조기 진단이 필요하다. 본 연구에서는 청진을 통해 수집된 폐음 데이터를 이용하여 이상 호흡음 분류모델을 제안한다. 데이터 전처리로는 대역통과필터(BandPassFilter)방법론을 적용하고 로그 멜 스펙트로그램(Log-Mel Spectrogram)과 Mel Frequency Cepstral Coefficient(MFCC)을 이용하여 폐음의 특징적인 정보를 추출하였다. 추출된 폐음의 특징에 대해서 효과적으로 분류할 수 있는 병렬 합성곱 신경망 네트워크(Parallel CNN network)모델을 제안하고 다양한 머신러닝 분류기(Classifiers)와 결합한 스태킹 앙상블(Stacking Ensemble) 방법론을 이용하여 이상 호흡음을 높은 정확도로 분류하였다. 본 논문에서 제안한 방법은 96.9%의 정확도로 이상 호흡음을 분류하였으며, 기본모델의 결과 대비 정확도가 약 6.1% 향상되었다.

• Journal of Chest Surgery
• /
• 제13권3호
• /
• pp.174-185
• /
• 1980

It was my great nohour that I can be exposed to such plenty materials of the coronary bypass surgery. Here, I am summarizing the xoronary bypass surgery, clinically. The material is serial 101 patients who underwent coronary bypass surgery between July 17, 1979 to November 30, 1979 in Shadyside Hospital, University of Pittsburgh. 1. Incidence of the Atherosclerosis is frequent in white, male, fiftieth who are living in industrialized country. It has been told the etiologic factor of the atherosclerosis is hereditary, hyperlipidemia, hypertension, smoking, drinking, diabetes, obesity, stress, etc. 2. The main and most frequent complication of the coronary atherosclerosis is angina pectoris. Angina pectoris is the chief cause of coronary bypass surgery and the other causes of coronary bypass surgery are obstruction of the left main coronary artery, unstable angina, papillary muscle disruption or malfunction and ventricular aneurysm complicated by coronary artery disease. 3. The preoperative clinical laboratory examination shows abnormal elevation of plasma lipid in 82 patint, plasma glucose in 40 patient, total CPK-MB in 24 patient stotal LDH in 22 patient out of 101 patient. 4. Abnormal ECG findings in preoperative examine were 29.1% myocardial infarction, 25.8% ischemia and injury, 14.6T conduction defect. 5. Also we had done Echocardiography, Tread Mill Test, Myocardial Scanning, Vectorcardiography and Lung function test to get adjunctive benefit in prediction of prognosis and accurate diagnosis. 6. The frequency of coronary atherosclerosis in main coronary arteries were LAD, RCA and Circumflex in that order. 7. The patients' main complaints which were became as etiologic factor undergoing coronary bypass surgery were angina, dyspnea, diaphoresis, dizziness, nausea and etc. 8. For the coronary bypass surgery, we used cardiopulmonary bypass machine, non-blood, diluting prime, cold cardioplegic solution and moderate cooling for the myocardial protection. 9. We got the grafted veins from Saphenous and Cephalic vein. Reversed and anastomosed between aorta and distal coronary A. using 5-0 and 7-0 prolene continuous suture. Occasionally we used internal mammary A. as an arterial blood source and anastomosed to the distal coronary A. and to side fashion. 10. The average cardiopulmonary bypass time for every graft was 43.9 min. and aortic clamp time was 23 minute. We could Rt. coronary A. bypass surgery only by stand by the cardiopulmonary machine and in the state of pumping heart. 11. Rates by the noumbers of graft were as follow : 21.8% single, 33.7% double, 26.7% triple, 13.9% quadruple, 3% quintuple and 1% was sixtuple graft. 12. combined procedures with coronary bypass surgery were 6% aneurysmectomy, 3% AVR, 1% MVR, 13% pacer implantation and 1% intraaortic ballon setting. 13. We could see the complete abolition of anginal pain after operation in 68% of patient, improvement 25.8%, no change in 3.1%, and there was unknown in 3%. 14. There were 4% immediate postoperative deaths, 13.5% some kinds of heart complication, 51.3% lung complications 33.3% pleural complications as prognosis.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권10호
• /
• pp.6019-6023
• /
• 2013

Lung cancer, one of the leading causes of cancer-related deaths, usually appears as solitary pulmonary nodules (SPNs) which are hard to diagnose using the naked eye. In this paper, curvelet-based textural features and clinical parameters are used with three prediction models [a multilevel model, a least absolute shrinkage and selection operator (LASSO) regression method, and a support vector machine (SVM)] to improve the diagnosis of benign and malignant SPNs. Dimensionality reduction of the original curvelet-based textural features was achieved using principal component analysis. In addition, non-conditional logistical regression was used to find clinical predictors among demographic parameters and morphological features. The results showed that, combined with 11 clinical predictors, the accuracy rates using 12 principal components were higher than those using the original curvelet-based textural features. To evaluate the models, 10-fold cross validation and back substitution were applied. The results obtained, respectively, were 0.8549 and 0.9221 for the LASSO method, 0.9443 and 0.9831 for SVM, and 0.8722 and 0.9722 for the multilevel model. All in all, it was found that using curvelet-based textural features after dimensionality reduction and using clinical predictors, the highest accuracy rate was achieved with SVM. The method may be used as an auxiliary tool to differentiate between benign and malignant SPNs in CT images.

• 대한약침학회지
• /
• 제19권3호
• /
• pp.197-206
• /
• 2016

Introduction: This study aims to investigate the effects of acupuncture stimulation on the radial artery's pressure pulse wave, along with various hemodynamic parameters, and to explore the possible underlying mechanism of pulse diagnosis in healthy participants in their twenties. Methods and analysis: This study is a prospective, single-arm, exploratory clinical study. A total of 25 healthy participants, without regard to gender, in their twenties will be recruited by physicians. Written informed consent will be obtained from all participants. The participants will receive acupuncture once at ST36 on both sides. The radial arterial pulse waves will be measured on the left arm of the subjects by using an applicable pulse tonometric device (KIOM-PAS). On the right arm (appearing twice), electrocardiogram (ECG), photoplethysmogram (PPG), respiration and cardiac output (CO) signals, will be measured using a physiological data acquisition system (Biopac module), while the velocity of blood flow, and the diameter and the depth of the blood vessel will be measured using an ultrasonogram machine on the right arm (appearing twice). All measurements will be conducted before, during, and after acupuncture. The primary outcome will be the spectral energy at high frequencies above 10 Hz ($SE_{10-30Hz}$) calculated from the KIOM-PAS device signal. Secondary outcomes will be various variables obtained from the KIOM-PAS device, ECG, PPG, impedance cardiography modules, and an ultrasonogram machine. Discussion: The results of this trial will provide information regarding the physiological and the hemodynamic mechanisms underlying acupuncture stimulation and clinical evidence for the influence of acupuncture on the pressure pulse wave in the radial artery. Ethics and dissemination: This study was approved by the Institutional Review Board (IRB) of Kyung Hee University's Oriental Medical Center, Seoul, Korea (KOMCIRB-150818-HR-030). The study findings will be published in peer-reviewed journals and presented at national and international conferences. Trial registration number: This trial was registered with the Clinical Research Information Service (CRIS) at the Korea National Institute of Health (NIH), Republic of Korea (KCT0001663), which is a registry in the World Health Organization's (WHO's) Registry Network.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권6호
• /
• pp.251-256
• /
• 2019

캡슐 내시경은 식도부터 항문까지 소화기관 전체를 한 번에 촬영할 수 있는 의료기기로, 한 번의 검사에서 평균 8~12시간의 길이와 5만장 이상의 프레임으로 구성된 영상을 생성한다. 그러나 생성된 영상에 대한 분석은 전문가에 의해 수작업으로 진행되고 있어서, 질병 영상 진단을 돕기 위한 영상 분석 자동화에 대한 수요가 증가하고 있다. 그 중에서도 본 연구에서는 위장관 내에서 발견될 수 있는 융기성 병변인 폴립 영상 자동 검출에 초점을 맞추었다. 본 연구에서는 멀티 스케일 분석을 통해 폴립 의심 영역을 추출하고, 이것을 원본 영상과 합성하여 폴립 학습을 강화시킬 수 있는 가중치 영상을 생성하는 기법을 제안한다. 수집한 452장의 데이터에 대해 머신 러닝 기법중 하나인 SVM과 RF로 실험한 결과, 원본 영상을 이용한 폴립 검출의 F1점수는 89.3%였지만, 생성된 가중치 영상을 통해 학습한 결과 F1점수가 93.1%로 향상된 것을 확인하였다.

• 한국전자거래학회지
• /
• 제24권1호
• /
• pp.105-120
• /
• 2019

세계보건기구(WHO)를 비롯해 세계 각국의 정부기관은 항생제 오남용에 따른 항생제 내성균 감염에 대해 심각하게 경고하며 이를 예방하기 위한 관리와 감시를 강화하고 있다. 하지만 감염을 확인하기 위한 감염균 배양에 수일의 시간이 소요되면서 격리와 접촉주의를 통한 감염확산 방지 효과가 떨어져 선제적 조치를 위한 신속하고 정확한 예측 및 추정방법이 요구되고 있다. 본 연구는 Electronic Health Records에 포함된 질병 진단내역과 항생제 처방내역을 neural embedding model과 matrix factorization을 통해 embedding 하였고, 이를 활용한 딥러닝 기반분류 예측 모형을 제안하였다. 항생제 내성균 감염의 주요 원인인 질병과 항생제 정보를 embedding하여 환자의 기본정보와 병원이용 정보에 추가했을 때 딥러닝 예측 모형의 f1-score는 0.525에서 0.617로 상승하였고, 딥러닝 모형은 Super Learner와 같은 기존 기계학습 모형보다 더 나은 성능을 보여주었다. 항생제 내성균 감염환자의 특성을 분석한 결과, 감염환자는 동일한 질병을 진단받은 비감염환자에 비교해 J01 계열 항생제 사용이 많았고 WHO 권고기준(DDD)을 크게 벗어나는 오남용 청구사례가 6.3배 이상 높게 나타났으며 항생제 오남용과 항생제 내성균 감염간의 높은 연관성이 발견되었다.

• 대한본초학회지
• /
• 제31권2호
• /
• pp.7-12
• /
• 2016

Objectives : Secondary amenorrhoea is the absence of menses for three months in a woman with previously normal menstruation or nine months for women with a history of oligomenorrhoea. It can be caused by stress, extreme weight loss, and excessive exercise. The purpose of this study was to report the clinical effects of herbal medicine on secondary amenorrhoea.Methods : We employed oriental medical treatments; herbal - medication (Hyunburikyungtang gamibang), acupuncture and moxibustion. We treated the patients one or two times a month with oriental therapy method. They took medicine three times a day after a meal. During taking medicine, we let the patients avoid fatty food, flour based food and alcohol. We evaluated the status of the patient, on the basis of the state of menstration and F2 level of Yangdorak. Because we diagnosed the condition of patients with the pattern of liver depression and qi stagnation, so F2 level of Yangdorak was an important point of the diagnosis. Yangdorak machine was Tormeter Iw - zen at Towatech Co.,Ltd.Results : After taking treatment - several times acupuncture and moxibustion during some period and taking herbal-medicine, they had menstrain naturally without taking any hormone drug. Also the amount of menstration has gradually increased. The F2 level of Yangdorak returned to normal range. The feeling of cold on hands, feet and lower abdomen was much improved.Conclusions : Herbal medicine (Hyunburikyungtang gamibang) with oriental medical treatments, acupuncture and moxibustion was effective in the treatment of secondary amenorrhoea.

• Parasites, Hosts and Diseases
• /
• 제47권3호
• /
• pp.235-241
• /
• 2009

The aim of this study was to estimate the benefit from repeated examinations in the diagnosis of enterobiasis in nursery school groups, and to test the effectiveness of individual-based risk predictions using different methods. A total of 604 children were examined using double, and 96 using triple, anal swab examinations. The questionnaires for parents, structured observations, and interviews with supervisors were used to identify factors of possible infection risk. In order to model the risk of enterobiasis at individual level, a similarity-based machine learning and prediction software Constud was compared with data mining methods in the Statistica 8 Data Miner software package. Prevalence according to a single examination was 22.5%; the increase as a result of double examinations was 8.2%. Single swabs resulted in an estimated prevalence of 20.1% among children examined 3 times; double swabs increased this by 10.1%, and triple swabs by 7.3%. Random forest classification, boosting classification trees, and Constud correctly predicted about 2/3 of the results of the second examination. Constud estimated a mean prevalence of 31.5% in groups. Constud was able to yield the highest overall fit of individual-based predictions while boosting classification tree and random forest models were more effective in recognizing Enterobius positive persons. As a rule, the actual prevalence of enterobiasis is higher than indicated by a single examination. We suggest using either the values of the mean increase in prevalence after double examinations compared to single examinations or group estimations deduced from individual-level modelled risk predictions.

• 대한세포병리학회지
• /
• 제9권2호
• /
• pp.129-137
• /
• 1998

Although the success of the Papanicolaou test as a screening tool of cervical cancer is evident, there still exists $2{\sim}5%$ of discrepancy rate by both human and machine. To improve the qualilty of cervico-vaginal cytology, the authors compared cervicovaginal smear with cervical biopsy diagnoses, and analysed the causes of discrepancies. Among 30,922 cervicovaginal smears from June 1996 to April 1997 at our hospital, there were 271 cases of cervicovaginal smear with subsequent cervical punch or LEEP cone biopsies within several months. The biopsies and smears from a total of 98 discordant cases were reviewed. The discrepancy was attributed to sampling errors in 43 cases(43.9%), and to cytologic diagnosis in 49 cases(50.0%). Among these, 43 cases were interpretative errors(categories A;19, B;16 and C;8) whereas six cases were screening errors(categories B:2 and C:4). Among cervical biopsy cases, errors were present in four. As for 10% random rescreening, cytotechnologists reviewed 3,196 of 30,922 smears during the same period, There were 43 cases of screening error(categories A;27, B;16). Cytologic/histologic correlation was superior to 10% random rescreening of negative cases. The most effective method for quality improvement in cervicovaginal cytology was to implement both quality control(rescreening) and qualify assurance(cytologic/histologic correlation) programs.