• Journal of Communications and Networks
• /
• v.13 no.2
• /
• pp.113-124
• /
• 2011

Electrocardiography (ECG) is a widely accepted approach for monitoring of cardiac activity and clinical diagnosis of heart diseases. Since cardiologists have been well-trained to accept 12-lead ECG information, a huge number of ECG systems are using such number of electrodes and placement configuration to facilitate fast interpretation. Our goal is to design a wireless ECG system which renders conventional 12-lead ECG information.We propose the three-pad ECG system (W3ECG). W3ECG furthers the pad design idea of the single-pad approach. Signals obtained from these three pads, plus their placement information, make it possible to synthesize conventional 12-lead ECG signals.We provide one example of pad placement and evaluate its performance by examining ECG data of four patients available from online database. Feasibility test of our selected pad placement positions show comparable results with respect to the EASI lead system. Experimental results also exhibit high correlations between synthesized and directly observed 12-lead signals (9 out of 12 cross-correlation coefficients higher than 0.75).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2361-2376
• /
• 2023

The electrocardiogram (ECG) signal is commonly used to screen and diagnose cardiovascular diseases. In recent years, deep neural networks have been regarded as an effective way for automatic ECG disease diagnosis. The convolutional neural network is widely used for ECG signal extraction because it can obtain different levels of information. However, most previous studies adopt single scale convolution filters to extract ECG signal features, ignoring the complementarity between ECG signal features of different scales. In the paper, we propose a dual-scale network with convolution filters of different sizes for 12-lead ECG classification. Our model can extract and fuse ECG signal features of different scales. In addition, different spatial and time periods of the feature map obtained from the 12-lead ECG may have different contributions to ECG classification. Therefore, we add a spatial-temporal attention to each scale sub-network to emphasize the representative local spatial and temporal features. Our approach is evaluated on PTB-XL dataset and achieves 0.9307, 0.8152, and 89.11 on macro-averaged ROC-AUC score, a maximum F1 score, and mean accuracy, respectively. The experiment results have proven that our approach outperforms the baselines.

• The Korean Journal of Emergency Medical Services
• /
• v.25 no.1
• /
• pp.235-241
• /
• 2021

Cardiogenic syncope occurs due to arrhythmia (bradycardia and tachycardia) or decreased cardiac output, and if proper treatment is not provided, it can lead to acute sudden death. A detailed medical history and physical examinations are required to determine the cause of syncope, and clinical approaches, including 12-lead ECG, are important. The 12-lead ECG does not have a chest lead in the posterior wall of the left ventricle; therefore, ECG of the isolated posterior wall myocardial infarction caused by left circumflex artery occlusion is not observed with ST elevation. Therefore, the significantly higher appearance of ST depression and R waves than S waves from V1 to V3 of the chest lead must be interpreted meaningfully. Isolated posterior wall myocardial infarction is small in the area of myocardial necrosis, and tension is increased in the necrotic area due to the contraction of the normal myocardial muscle, which can cause ventricular wall rupture. Therefore, it is necessary to additionally check Beck's triad, such as jugular venous distension and decreased heart sound, in patients with low blood pressure with an isolated posterior wall myocardial infarction on 12-lead ECG in patients with syncope.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.39 no.5
• /
• pp.391-395
• /
• 2015

A 15-Lead ECG has been developed to diagnose posterior wall diseases of the heart that a 12-Lead ECG cannot diagnose. However, 15-Lead ECG data for developing heart-diseases-detecting algorithm are limited, and previous ECG simulators cannot predict the ECG waveform according to the changes in electrode. To solve these problems, the lumped parameter model (LPM), which divides the heart into 15 sections with varying electrical capacitance and electrical resistance. To imitate the electrical conduction in the heart, each node was connected to a current source and delivered the specific current considering the positions and time delay. The purpose of this study is to acquire the waveform that can be used in an ECG by delivering the specific current to LPM.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.508-521
• /
• 2020

We compared a novel encoding Lempel-Ziv complexity (ELZC) with three common complexity algorithms i.e., approximate entropy (ApEn), sample entropy (SampEn), and classic Lempel-Ziv complexity (CLZC) so as to determine a satisfied complexity and its corresponding quality indices for assessing quality of multi-lead electrocardiogram (ECG). First, we calculated the aforementioned algorithms on six artificial time series in order to compare their performance in terms of discerning randomness and the inherent irregularity within time series. Then, for analyzing sensitivity of the algorithms to content level of different noises within the ECG, we investigated their change trend in five artificial synthetic noisy ECGs containing different noises at several signal noise ratios. Finally, three quality indices based on the ELZC of the multi-lead ECG were proposed to assess the quality of 862 real 12-lead ECGs from the MIT databases. The results showed the ELZC could discern randomness and the inherent irregularity within six artificial time series, and also reflect content level of different noises within five artificial synthetic ECGs. The results indicated the AUCs of three quality indices of the ELZC had statistical significance (>0.500). The ELZC and its corresponding three indices were more suitable for multi-lead ECG quality assessment than the other three algorithms.

• Journal of Biomedical Engineering Research
• /
• v.41 no.2
• /
• pp.107-119
• /
• 2020

The deep neural networks (DNN) that can replicate the behavior of the human expert who recognizes the characteristics of ECG waveform have been developed and studied to analyze ECG. However, although the existing DNNs can not provide the explanations for their decisions, those trials have attempted to determine whether patients have certain diseases or not and those decisions could not be accepted because of the absence of relating theoretical basis. In addition, these DNNs required a lot of training data to obtain sufficient accuracy in spite of the difficulty in the acquisition of relating clinical data. In this study, a small-sized continuous data processing DNN (C-DNN) was suggested to determine the simple characteristics of ECG wave that were not required additional explanations about its decisions and the C-DNN can be easily trained with small training data. Although it can analyze small input data that was selected in narrow region on whole ECG, it can continuously scan all ECG data and find important points such as start and end points of P, QRS and T waves within a short time. The star and end points of ECG waves determined by the C-DNNs were compared with the results performed by human experts to estimate the accuracies of the C-DNNs. The C-DNN has 150 inputs, 51 outputs, two hidden layers and one output layer. To find the start and end points, two C-DNNs were trained through deep learning technology and applied to a parameter acquisition algorithms. 12 lead ECG data measured in four patients and obtained through PhysioNet was processed to make training data by human experts. The accuracy of the C-DNNs were evaluated with extra data that were not used at deep learning by comparing the results between C-DNNs and human experts. The averages of the time differences between the C-DNNs and experts were 0.1 msec and 13.5 msec respectively and those standard deviations were 17.6 msec and 15.7 msec. The final step combining the results of C-DNN through the waveforms of 12 leads was successfully determined all 33 waves without error that the time differences of human experts decision were over 20 msec. The reliable decision of the ECG wave's start and end points benefits the acquisition of accurate ECG parameters such as the wave lengths, amplitudes and intervals of P, QRS and T waves.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.358-359
• /
• 2012

본 연구에서는 범용적인 건강 모니터링에 활용할 수 있는 생체신호인 심전도를 일반 가정 내에서 뿐만 아니라 일상생활 중에서도 실시간으로 편리하게 측정할 수 있도록 초소형 저전력의 착용형 심전도 계측시스템을 구현하였다. 이를 위하여 표준 12-lead법이 아닌 모바일 또는 휴대용 장치에 적합한 2-lead법을 사용하여 심전도 계측부를 구현하였고, 심전도 계측부를 베이스 노드로 하여 심전도 신호를 가정 내 또는 실외에서도 무선으로 전송 할 수 있도록 구현하였다. 먼저 가정 내에서는 저 전력 무선센서노드를 이용하여 심전도 신호를 실시간으로 PC에 전송하여 모니터링이 가능하도록 구현 하였고, 실외에서는 저전력 통신 방식인 Bluetooth 2.0을 사용하여 스마트폰으로 심전도 신호를 실시간으로 전송해 모니터링 할 수 있도록 구현하였다.

• The Korean Journal of Emergency Medical Services
• /
• v.25 no.1
• /
• pp.243-249
• /
• 2021

A decrease in coronary blood flow leads to an imbalance between the supply of oxygen to the myocardium and its demand, and reversible or irreversible damage to the myocardium could occur depending on the severity of the resultant ischemia and the duration of the imbalance. This imbalance results in a cascade of ischemic reactions in the following order: metabolic abnormalities, diastolic dysfunction, systolic dysfunction, and electrocardiogram changes. Variant angina is caused by the closure of the coronary artery due to reversible coronary artery spasm, resulting in myocardial ischemia and subsequent chest pain as a clinical symptom. Variant angina may be observed as ST segment elevation in electrocardiogram measured when present in chest pain. However, 12-lead electrocardiogram performed after the patient's chest pain resolves does not help in the diagnosis. Since the duration of chest pain appears to be <15 minutes, it is important to perform the 12-lead electrocardiogram when clinical symptoms are present. If nitroglycerin is administered without performing 12-lead electrocardiogram by 119 pre-hospital paramedics, the chest pain would be resolved, making it impossible to identify changes in the ST segment. Before administration of nitroglycerin, changes in the ST segment must be recorded by performing 12-lead electrocardiogram.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.12
• /
• pp.1690-1698
• /
• 2018

Recent advances in ICT technology have transformed many of our daily lives and attracted a lot of attention to personal health. Heart beat measurement that reflects cardiac activities has been used in various fields such as exercise evaluation and psychological state evaluation for a long time, but its utilization method is limited due to its differentiation from clinical electrocardiogram. Therefore, in this study, we could observe the change of the measured signal according to the change of the distance and the position of the measuring electrodes which are non-standard electrode configuration. Based on the electric dipole model of the heart, correlation with clinical electrocardiogram could be confirmed by synthesizing multiple surface potentials measured with a shorter electrode distance than standard one. From the electromagnetic point of view, the distance between the measuring electrodes corresponds to the distance that the electric potential by the cardiac electric dipole moves, and the electric potential measured at the body surface is proportional to the moving distance of the electric potential. Therefore, it is preferable to make the distance between electrodes as long as possible, and to position the measuring electrode close to the ventricle rather than the atrium. In addition, it was found that standard electrocardiographic waveforms could be synthesized by using arithmetic sum of multiple measuring electrodes due to the relationship of electrical dipole vectors, which is obtained by dividing and positioning a plurality of measuring electrodes on a reference electrode line, such as Lead-I, Lead-II direction. Also, we obtained a significant Pearson correlation coefficient ($r=0.9113{\pm}0.0169$) as a result of synthetic experiments on four subjects.

• Childhood Kidney Diseases
• /
• v.27 no.2
• /
• pp.105-110
• /
• 2023

Purpose: To analyze electrocardiograms (ECGs) of patients with a salt-losing tubulopathy (SLT) and to determine the frequency and risk factors for long QT and arrhythmia. Methods: A total of 203 patients aged <19 years with SLT, specifically Bartter syndrome and Gitelman syndrome, who had a 12-lead ECG were included in this retrospective study. We analyzed the presence of an arrhythmia or prolonged corrected QT (QTc) on ECGs obtained for these patients. Demographic and laboratory data were compared between patients with abnormal and normal ECG findings. Results: Out of the 203 SLT patients, 38 (18.7%) underwent electrocardiography and 10 (40.0%) of 25 patients with inherited SLT had abnormal ECG findings, including prolonged QTc and arrhythmias. The abnormal ECG group had significantly lower serum potassium levels than the normal group (median [interquartile range]: 2.50 mmol/L [2.20-2.83] vs. 2.90 mmol/L [2.70-3.30], P=0.036), whereas other serum chemistry values did not show significant differences. The cutoff level for a significant difference in QTc interval was serum potassium level <2.50 mmol/L. One cardiac event occurred in a 13-year-old boy, who developed paroxysmal supraventricular tachycardia and underwent cardiac ablation. No sudden cardiac deaths occurred in this cohort. Conclusions: The incidence of ECG abnormalities in patients with inherited SLT was 40.0%, whereas the ECG screening rate was relatively low (18.7%). Therefore, we recommend ECG screening in patients with inherited SLT, especially in those with serum potassium level <2.50 mmol/L.