• 한국정보통신학회논문지
• /
• 제14권1호
• /
• pp.16-22
• /
• 2010

심전도 신호 분석 및 부정맥 분류는 환자를 진단하고 치료하는데 중요한 역할을 한다. 부정맥은 맥박이 불규칙한 상태로 심실빈맥(VT)이나 심실세동(VF) 환자에게 심각한 위협이 될 수 있다. 심방조기수축(APC)과 상심실성빈맥(SVT), 심실조기수축(PVC)은 심실빈맥(VT)만큼 치명적이지는 않지만 심장질환을 진단하는데 중요한 부정맥이다. 본 논문은 2~3개의 부정맥 분류만을 고려한 기존의 방법을 극복하고 다양한 부정맥을 분류하기 위한 새로운 방법을 제시한다. 심전도 신호의 특징 추출을 위해서 EMD 방법으로 신호를 분해하여 IMFs를 얻는다. 입력 데이터의 양은 분류기 성능에 영향을 미치므로 신호 데이터의 차원을 감소시키기 위해 Burg 알고리즘을 IMFs에 적용하여 AR 계수를 구하고 여러 개의 이진 분류기를 결합한 다중 클래스 SVM의 입력으로 사용한다. 최적의 SVM 성능 파라미터를 선택하고 부정맥 분류에 적용한 결과 검출의 정확성은 96.8%~99.5%였다. 실험 결과는 제안한 EMD 방법에 의한 전처리 및 특징 추출과 다중 클래스 SVM에 의한 부정맥 분류의 유용성을 보여준다.

• Advances in Traditional Medicine
• /
• 제4권3호
• /
• pp.157-161
• /
• 2004

We showed the effects of the traditional herbal medicine, Jukyeoondam-tang (JO-T, Zhu-ru-Wen-Dan-Tang in Chinese), on ventricular arrhythmia induced by aconitine. Electrophysiological experiments with conventional microelectrode techniques revealed that JO-T potently suppressed the aconitine-induced arrhythmias in ventricular strips of the rat. In the aconitine-induced arrhythmia model of the rat, pretreatment with JO-T $(100\;{\mu}g/ml)$ completely occluded the appearance of ventricular tachyarrhythmia (VT) or ventricular fibrillation (VF) induced by aconitine. Furthermore, the aconitine-induced ventricular arrhythmia was occluded by $Na^+$ channel blocker quinidine but was not occluded by $K^+$ channel blocker glibenclamide $(3\;{\mu}mol/L)\;and\;Ca^{2+}$ channel blocker nifedipine $(10\;{\mu}mol/L)$. We also confirmed the effect of JO-T in the ischemia-reperfusion (I/R)-induced arrhythmia model of the rat. JO-T did not affect the I/R-induced arrhythmias in rats. JO-T may alleviate the risk of ventricular arrhythmias following aconitine. These results suggest that JO-T is a potent antiarrhythmic drug having a$Na^+$ channel-blocking action.

• 한국임상수의학회지
• /
• 제6권2호
• /
• pp.281-290
• /
• 1989

To gain insight into the relationship between the occurrence of occlusive arrhythmia(OA) and the incidence of reperfusion arrhythmia(RA), this study used 25 open-chest dogs anesthetized with halothan, these were ligated between anterior ventricular branch and marginal branch of left circumflex artery for 30 minutes and occlusive arrhythmia were observed during the ligation. After releasing of the ligation, TA were observed during 5 minutes. The results were summerized as follow； 1. Such arrhythmias as ventricular fibrillation(VF), short run type VPC Premature contraction(VPC), Venticular tachycardia(VT), ventricularc and trigeminy VPC(TVPC) were observed during occlusion and reperfusion. 2. The cases occurred VT, SRVPC and TVPC during occlusion necessarily were Incidence of RA. 3. RA never occurred without appearence of occlusive arrhythmias. 4. The occurrence rate of OA showed 55.5% in the incidence group of RA and 24.6％ in the non incidence group of RA. 5. The occurrence rate of VPC during occlusion showed 9.9＋5.85(episode/min) in the incidence group of RA and 4.46＋5.88(episode/min) in the non-incidence group of RA. These results may be estimated that the occurrence of VT, SRVPC and TVPC, and the high occurrence rate of VPC during occlusion can be predicted the incidence.

• 한국응급구조학회지
• /
• 제9권1호
• /
• pp.25-32
• /
• 2005

Purpose: There has been an increase in the number of prehospital cardiac arrests due to increases in both cardiovascular diseases and the average age of the population, We performed this study to identify the proper resuscitation technique and AED to be used to increase the survival rate in prehospital cardiac arrest. Methods: We studied 57 victims with prehospilal cardiac arrest by EMT's Reports form January to December, 2004. Results: Fifty-seven of 92 victims were trasported with ECG in prehospital cardiac arrest. Ventricular fibrillation(VF)/ ventricular tachycardia was 56.2%, asystole was 33,3%, and pulseless electrical activity(PEA.) was 10.5% in initial rhythm analysis, There weren't attempt CPR in 14.0%. Twenty of the 32(62.5%) were shocked by AED for the adequacy method. There were no statistical differences the transportation time. Conclusion: With the increase in cardiovascular disease and old age, the number out-of-hospital cardiac arrests has risen accordingly. However, there were lack of CPR by bystander, defibrillation, advanced cardiac life support(ACLS) in prehospital stage. To improve the adequancy of basic life support and to increase the performance of ACLS, especially AED, we must create challenges to develop new protocols in prehospital care.

• 대한의용생체공학회:의공학회지
• /
• 제28권4호
• /
• pp.556-568
• /
• 2007

Unsatisfied results of return of spontaneous circulation (ROSC) estimates were caused by the fact that the predictability of the predictors was insufficient. This unmet estimate of the predictors may be affected by transitional events due to behaviors which occur during cardiopulmonary resuscitation (CPR). We thus hypothesized that the discrepancy of ROSC estimates found in statistical characteristics due to transitional CPR events, may affect the performance of the predictors, and that the performance of the classifier dichotomizing between ROSC and No-ROSC might be different during CPR. In a canine model (n=18) of prolonged ventricular fibrillation (VF), standard CPR was provided with administration of two doses of epinephrine 0 min or 3 min later of the onset of CPR. For the analysis of the likelihood of a successful defibrillation during CPR, Support Vector Classification was adopted to evaluate statistical peculiarity combining time and frequency based predictors: median frequency, frequency band-limited power spectrum, mean segment amplitude, and zero crossing rates. The worst predictable period showed below about 1 min after the onset of CPR, and the best predictable period could be observed from about 1.5 min later of the administering epinephrine through 2.0-2.2 min. As hypothesized, the discrepancy of statistical characteristics of the predictors was reflected in the differences of the classification performance during CPR. These results represent a major improvement in defibrillation prediction can be achieved by a specific timing of the analysis, as a change in CPR transition.

• 전자공학회논문지SC
• /
• 제44권5호
• /
• pp.45-54
• /
• 2007

시/주파수 분석은 생체 신호 처리에서 널리 사용되어왔다. 전기 생리학적 신호로부터 중요한 특징들을 추출함으로써 이 방법들은 특정 질병의 임상 병리학적 기전 해석이 가능하다. 하지만 이 방법은 신호가 안정하다는 가정 아래 적용되었으며 불안정한 시스템에서의 적용은 제한이 되어 있다. 본 연구에서는 비선형적이고 비정상적인 심실세동 심전도 파형의 분석을 위해 Hilbert-Huang 변환을 사용한 새로운 신호처리 방법을 제안하였다. Hilbert-Huang 변환은 경험모드분리법(EMD)과 힐버트 변환으로 크게 두 가지로 구성된다. Hilbert-Huang 변환은 EMD를 사용하여 각각의 특성을 지니고 있는 독립적인 내부모드함수들로 나누어지며, 힐버트 변환에 의해 순간 주파수와 크기를 구할 수 있게 된다. 이런 특성으로 신호의 국부적인 작용에 대하여 정확하게 설명할 수 있게 된다. 본 연구에서는 Hilbert-Huang 변환을 기반으로 심실세동 심전도 파형으로부터 두 종류의 파라미터(EMD-IF, EMD-FFT)를 추출하고 서포트 벡터 머신(Support Vector Machine)을 이용하여 소생성공 및 실패 여부 예측에 관하여 연구하였다. 평균적으로 민감도와 특이도는 각각 87.57%와 76.92%로 나타났다. Hilbert-Huang 변환은 더욱 정확하게 심실세동에서의 소생성공 예측을 가능하게 하였다.

• International Journal of Control, Automation, and Systems
• /
• 제3권4호
• /
• pp.571-579
• /
• 2005

In this paper, we proposed an algorithm for arrhythmia classification, which is associated with the reduction of feature dimensions by linear discriminant analysis (LDA) and a support vector machine (SVM) based classifier. Seventeen original input features were extracted from preprocessed signals by wavelet transform, and attempts were then made to reduce these to 4 features, the linear combination of original features, by LDA. The performance of the SVM classifier with reduced features by LDA showed higher than with that by principal component analysis (PCA) and even with original features. For a cross-validation procedure, this SVM classifier was compared with Multilayer Perceptrons (MLP) and Fuzzy Inference System (FIS) classifiers. When all classifiers used the same reduced features, the overall performance of the SVM classifier was comprehensively superior to all others. Especially, the accuracy of discrimination of normal sinus rhythm (NSR), arterial premature contraction (APC), supraventricular tachycardia (SVT), premature ventricular contraction (PVC), ventricular tachycardia (VT) and ventricular fibrillation (VF) were $99.307\%,\;99.274\%,\;99.854\%,\;98.344\%,\;99.441\%\;and\;99.883\%$, respectively. And, even with smaller learning data, the SVM classifier offered better performance than the MLP classifier.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권4호
• /
• pp.274-283
• /
• 2005

Coronary Perfusion Pressure(CPP) is known for the most important parameter related to the Return of Spontaneous Circulation (ROSC), however, clinically measuring CPP is difficult either invasive or non-invaisive method. En this paper, we analyze the correlation between the extracted parameter from VF ECG wave and the CPP with the statistical method, and predict CPP value using the extracted parameters within significance level. the extracted parameters are median frequency(MF), peak frequency(PF), average segment amplitude(ASA), MSA(maximum segment amplitude), Two parameters, MF, and ASA are selected in order to predict CPP value with general regression neural network, and then we evaluated the agreement statistics between the simulated CPP and the measured CPP. In conclusion, the mean and variance of the difference between the simulated CPP and the measured CPP are 8.9716±1.3526 mmHg, and standard deviation 6.4815 mmHg with one hundred-times training and test results. the simulated CPP and the measured CPP are agreed with the overall accuracy $90.68\%$ and kappa coefficient $81.14\%$ as a discriminant parameter of ROSC.

• 한국지능시스템학회논문지
• /
• 제21권6호
• /
• pp.730-736
• /
• 2011

본 연구는 순차적인 시계열 자료들에서 가장 최근의 추세가 반영될 수 있는 패턴분류 모델을 설계하였다. 의사결정을 지원하는 데이터마이닝 패턴분류 모델을 설계할 때 통계 기법과 인공지능 기법을 융합한 모델들이 기존의 모델보다 우수함을 입증하였다. 특히 퍼지이론과 융합된 패턴분류 모델들의 적중률이 상대적으로 더 향상되었다. 예를 들어, 통계적 이론을 기반으로 한 SVM모델과 퍼지소속함수와의 결합, 혹은 신경망과 FCM을 결합한 모델들의 성능이 우수하였다. 실험에서 사용한 패턴분류 모델들은 BPN, PNN, FNN, FCM, SVM, FSVM, Decision Tree, Time Series Analysis, Regression Analysis 등이다. 그리고 데이터베이스는 시계열 속성을 지닌 금융시장의 경제지표 DB(한국, KOSPI200 데이터베이스)와 병원 응급실의 부정맥환자에 대한 심전도 DB(미국 MIT-BIH 데이터베이스)들을 사용하였다.

• 한국응급구조학회지
• /
• 제8권1호
• /
• pp.149-160
• /
• 2004

Background : To save out-of-hospital cardiac arrest cases is a major concern for Korea. Cardiac arrest is a very common problem, with > 18,000 cases dying each year in Korea. Overall, survival to hospital discharge remains poor. Resuscitation has become an important multidisciplinary branch of medicine, demanding a spectrum of skills and attracting a plethora of specialities and organizations. Since the "Utstein Style" was advocated in 1991, many reports about out-of-hospital cardiac arrest have been published based on this guideline. These differences prevent valid inter-hospital and international comparisons. However, we do not know the true effectiveness of resuscitation. There are no guideline for reviewing, reporting, conducting research on resuscitation in Korea. This study evaluated the out-of-hospital factor associated with survival discharge of out-of-hospital cardiac arrest, was especially to provide basic data for the unified reporting guideline of resuscitation in Korea. Methods : From January 1990 to July 2004, we collected data about out-of-hospital cardiac arrest at Wonju Christian Hospital(WCH-CAD), Ewha Women University Mokdong Hospital(Ewha-CAD), I used same record form based on the "Utstein Style". The "Utstein Style" is internationally recommended guidelines for reporting outcome data from resuscitation events. Results : Resuscitation was performed in 1443 out-of-hospital cardiac arrest patients at 2 hospitals. Five hundred eighty(40.25%) patients recovered the spontaneous circulation at least once and One hundred sixty eight(11.66%) patients discharged alive. Initial EKG showed Ventricular Tachycardia/Ventricular Fibrillation in One hundred thirty five(9.33%) patients, asystole in one thousand nine(69.73%) patients and other rhythms in one hundred thirty nine(20.94%) patients. Among one hundred two cardiogenic cardiac arrest patients, two(2.0%) patients was discharged alive. Conclusion : Overall survival rate of out-of-hospital cardiac arrest patients was 11.66% which was poorer than that of the western country. The proportion of the cardiogenic cause was 33.38% which was only half of the western country. VT/VF is relatively not common ac a initial EKG rhythm. These differences might be to due difference in the prevalence pattern of out-of-hospital cardiac arrest as well as prematurity of the EMSS. It is needed that the best survival can be achieved if all following links have been optimized : rapid access, early CPR, early defibrillation, early ACLS.