• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.671-681
• /
• 2019

Studies on predicting arrhythmia using machine learning have been actively conducted with increasing number of arrhythmia patients. Existing studies have predicted arrhythmia based on multivariate data of feature variables extracted from RR interval data at a specific time point. In this study, we consider that the pattern of the heart state changes with time can be important information for the arrhythmia prediction. Therefore, we investigate the usefulness of predicting the arrhythmia with multivariate time series data obtained by extracting and accumulating the multivariate vectors of the feature variables at various time points. When considering 1-nearest neighbor classification method and its ensemble for comparison, it is confirmed that the multivariate time series data based method can have better classification performance than the multivariate data based method if we select an appropriate time series distance function.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.62-69
• /
• 2022

An electrocardiogram (ECG) is one of the most important biosignals, and in particular, continuous ECG monitoring is very important in patients with arrhythmia. There are many different types of arrhythmia (sinus node, sinus tachycardia, atrial premature beat (APB), and ventricular fibrillation) depending on the cause, and continuous ECG monitoring during daily life is very important for early diagnosis of arrhythmias and setting treatment directions. The ECG signal of arrhythmia patients is very unstable, and it is difficult to detect the R-peak point, which is a key feature for automatic arrhythmias detection. In this study, we develped a continuous measuring Holter ECG monitoring device and software for analysis and confirmed the utility of R-peak of the ECG signal with MIT-BIH arrhythmia database. In future studies, it needs the validation of algorithms and clinical data for morphological classification and prediction of arrhythmias due to various etiologies.

• Proceeding of EDISON Challenge
• /
• 2017.03a
• /
• pp.708-711
• /
• 2017

전기적 신호의 이상으로 발생하는 심방 부정맥은 심방세동으로 발전하는 대표적 심장 질환이다. 이러한 원인에는 세포 내 이온 채널의 유전적 결함으로 인한 기전이 알려져 있다. 지속적인 연구로 밝혀진 대표적인 유전적 질환 중 하나로서 KCNH2 유전자 돌연변이가 있다. 본 연구에서는 KCNH2 유전자 돌연변이가 심방부정맥을 유발하는 연관성연구를 기반으로 심실에서의 심장 질환 발현 연관성을 확인하고 심실부정맥과 심실세동 가능성을 예측하였다. 이를 위해 Ten tusscher 세포 모델에 KCNH2 유전자의 N588K, L532P 변이를 적용하여 2차원과 3차원 시뮬레이션을 진행하였다. wild-type(WT)과 mutant-type(MT)의 전기전도 패턴을 비교했다. 그 결과 WT의 전도파형이 일찍 자가소멸(self-termination) 되는 것과 대조적으로 MT는 회귀성 파형이 유지되었다(WT : 3.6초간 유지, MT : 지속적). 따라서 본 연구를 통해 KCNH2 유전자 돌연변이가 심실 조직의 취약성 (Action Potential Duration 감소, WT : 270 ms, N588K : 130 ms, L532P : 100 ms)을 증가시켜 부정맥의 요인이 됨을 확인하였다.

• Information and Communications Magazine
• /
• v.30 no.10
• /
• pp.70-78
• /
• 2013

최근 고령화 사회로 진입함에 따라 건강 상태 상시 모니터링에 대한 관심이 높아졌으며, 이에 편승하여 부정맥을 탐지하는 기법에 대한 연구도 활발히 진행되고 있다. 원격심전도 모니터링을 통해 병원 방문 없이도 진료 및 진단이 가능해 질 것으로 예측된다. 이러한 원격심전도 모니터링은 사이버물리시스템의 대표적인 응용사례에 해당된다. 본 고를 통해 우리는 원격심전도 모니터링 응용 사례를 물리시스템과 사이버시스템의 상호작용 관점에서 살펴보고, 이를 통하여 효율적인 시스템 설계 방안에 대하여 논한다.

• Journal of Chest Surgery
• /
• v.30 no.11
• /
• pp.1077-1082
• /
• 1997

To assess the early results, risk factors and optimal timing for coronary artery bypass graft surgery(CABG) after an acute myocardial infarction(AMI), we reviewed our 19 patients who underwent CABG within 30 days after AMI, between June 1994 and October 1996. This study excluded 1 patient whose diagnosis was AMI with ventricular septal rupture. 14 of the patients were male and 5 were female. Their ages ranged from 41 to 77 years(mean age, 60.6$\pm$ 10.4 years), and the amount of time between AMI and CABG ranged from 8 hours to 24 days(mean time, 10.6$\pm$6.4 days). There were 11 anteroseptal infarctions and 8 inferior wall infarctions. 11 patients had trsnsmural infarctions and 8 had subendocardial infarctions. Indications of operations were p imary revascularization and postinfarction angina. Three patients required preoperative intra-aortic balloon pump(IABP) support, and 4 additional patients required IABP to be separated from cardiopulmonary bypass. An average of 3.6 $\pm$ 0.6 vessels per patient were bypassed. The early mortality rate for these 19 patients was 5.3% and late mortality rate was 5.5%, 1-year and 2-year actuarial survival rates were 89.5% Univariate analysis of mortality showed that an ejection fraction less than 30% and intraopretative IABP supports were associated with risk factors(p value=0.018 and 0.015 respectively). Age, sex, time to CABG, emergency operations, types and locations of infarctions were not significant. Although our studies have weak p.oints in that there was only a small number of patients and the lack of long-term results, we could conclude that early myocardial revascularization is relatively safe after AMI for those individuals with an ejection fraction greater than 30%.

• Journal of Biomedical Engineering Research
• /
• v.20 no.6
• /
• pp.561-571
• /
• 1999

심실세동은 환자의 생명을 위협하는 가장 치명적인 부정맥으로서, 심실세동의 발견즉시 특별한 조치를 취하지 못할 경우 환자는 급사한다. 심실세동을 정지시키는 유일한 방법은 전기적 제세동이며 이는 환자의 심장 부위에 전기적 에너지를 가해 정상 심장 리듬을 되찾도록 하는 방법이다. 심실세동의 발생은 예측할 수 없고, 이를 진단하기 위한 심전도 교육을 모든 의료인에게 할 수 없으므로 심전도를 자동 분석하여 심실세동을 조기에 검출하는 자동 분석장치의 개발은 심실세동에 의한 급사를 줄이는데 매우 중요하다. 본 연구에서는 교차간섭성분의 제거 능력이 뛰어나며 쉽게 구사할 수 있는 Choi-Williams distriguteion (CWD) 방법을 이용하여 급사를 초래할 수 있는 심실세동을 자동 검출하는 알고리즘을 개발하였다. 그리고 개발된 알고리즘의 성능을 검증하기 위하여 본 논문에서는 두 그룹의 심실세동 데이터를 사용하였다. 검출 알고리즘은 심실세동의 시간 및 주파수 특성을 일곱가지 조건들에 대한 만족 여부를 이용하여 심실세동을 판정하였고, 실험의 민감도와 선택도는 각각 92.1%, 97 .2% 이다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.230-234
• /
• 2010

심전도는 가장 일반화되어 있는 생체신호의 하나이다. 심전도를 측정하여 심장병의 유무와 여러 질환들을 예측하고 예방할 수 있다. 심전도 신호를 추출 하는 방법에는 여러 방법이 있는데, 본 논문에서 활용한 두 논문은 계층적인 분류로 HOS, HBF, HMH 세 방법으로 실험을 하였고, 적응가변형 윈도우를 이용한 R파 추출을 실행하였다. 두 논문은 공통적으로 MIT-BIH Arrhythmias Database(MIT-BIT 부정맥 데이터베이스)를 데이터로 실험 하였으며, 알고리즘으로는 SVM, Cross-Validation등을 사용하였다. 마지막으로 두 논문의 실험결과를 바탕으로 정확도를 높일 수 있는 효과적인 알고리즘 연구를 제안하였다.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1163-1185
• /
• 2021

Sudden cardiac death is an unexpected death originating from the heart that occurs within an hour of the onset of symptoms. The main cause of sudden cardiac death is arrhythmia; however, diagnosing underlying structural heart disease significantly contributes to predicting the long-term risk. Cardiovascular CT and MR provide important information for diagnosing and evaluating structural heart disease, enabling the prediction and preparation of the risk of sudden cardiac death. Therefore, we would like to focus on the various structural heart diseases that increase the risk of clinically-important sudden cardiac death and the importance of imaging findings.

• Journal of Chest Surgery
• /
• v.31 no.7
• /
• pp.668-673
• /
• 1998

During the past several years, the maze operation has become the most effective method of treatment for chronic atrial fibrillation. When the maze procedure is done concomittantly with other cardiac operations, surgeons, in their initial experiences, may be concerned about the additional operative risks and uncertainty of the results. We performed the Cox-maze III procedure in six cases of chronic atrial fibrillation associated with mitral, mitral & aortic, or coronary arterial disease. Maze III procedure was done with open mitral commissurotomy(3 cases), mitral valve replacement(1 case), aortic and mitral valve replacement(1 case), and two-vessel coronary bypass graft(1 case). In spite of rather prolonged aortic cross clamp time, cardiac recovery was uneventful in all cases. No cases required reexploration for postoperative bleeding. All patients showed regular sinus rhythms immediate or between 2 and 20 days postoperateratively. Transient postoperative supraventricular arrhythmarias were easily controlled by various antiarrhythmic agents. In follow up evaluations, all cases showed regular sinus rhythm on ECG and the right and left atrial transport function was confirmed by Doppler echocardiography in all except one. Though our experience was limited in case number, the Cox-maze III procedure was effective in controlling the chronic atrial fibrillation without serious additional operative risks.

• The Journal of Engineering Geology
• /
• v.15 no.2 s.42
• /
• pp.213-227
• /
• 2005

This study aims to assess the problems with investigation method and to suggest the complementary solutions by comparing the predicted data from surface investigation with the outcome data from underground cavern. In the study area, one(NE-1) of 6 fracture zones predicted during the surface investigation was only confirmed in underground caverns. Therefore, it is necessary to improve the confidence level for prediction. In this study, the fracture classification criteria was quantitatively suggested on the basis of the BHTV images of NE-1 fracture zone. The major orientation of background fractures in rock mass was changed at the depth of the storage cavern, the length and intensity were decreased. These characteristics result in the deviation of predieted predicted fracture properties and generate the investigation bias depending on the bore hole directions and investigated scales. The evaluation of hydraulic connectivity in the surface investigation stage needs to be analyze by the groundwater pressures and hydrochemical properties from the monitoring bore hole(s) equipped with a double completion or multi-packer system during the test bore hole is pumping or injecting. The hydraulic conductivities in geometric mean measured in the underground caverns are 2-3 times lower than those from the surface and furthermore the horizontal hydraulic conductivity in geometric mean is six times lower than the vertical one. To improve confidence level of the hydraulic conductivity, the orientation of test hole should be considered during the analysis of the hydraulic conductivity and the methodology of hydro-testing and interpretation should be based on the characteristics of rock mass and investigation purposes.