• 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.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.3 no.1
• /
• pp.67-70
• /
• 2005

Pimozide and haloperidol are typical antipsychotics. They share a similarity in pharmacotherapeutic and adverse effect profiles. Cardiovascular effects may be seen as alterations in heart rate, blood pressure, and cardiac conduction. Conduction disturbances may occur ranging from asymptomatic prolongation of the QT interval to fatal ventricular arrhythmia. So in the case of anti psychotics overdose, the patient must be carefully monitored by continuous electrocardiography (ECG). We experienced a 34-year-old woman of schizophrenia with recurrent ventricular tachycardia after pimozide and haloperidol overdose. Initially she was slightly drowsy, however her ECG showed normal sinus rhythm. After 6 hours on emergency department entrance, her ECG monitoring showed ventricular tachycardia and we successfully defibrillated. There were five times events of ventricular arrhythmia during the in-hospital stay. She was discharged 5 days later without any other complications.

• Journal of Yeungnam Medical Science
• /
• v.39 no.2
• /
• pp.172-177
• /
• 2022

Takotsubo or reverse Takotsubo cardiomyopathy is a well-known cardiac complication of subarachnoid hemorrhage (SAH) that shows transient left ventricular wall motion abnormalities with electrocardiogram (ECG) changes. ST change followed by T inversion is a common ECG finding complicated with these disorders, left bundle branch block (LBBB) may be a potential ECG pattern which is seen. In this case, we describe the clinical profile and outcomes of a patient with LBBB and reverse Takotsubo cardiomyopathy after anesthetic induction, which was scheduled as an emergent external ventricular drainage after SAH. This is the first report of an LBBB pattern in reverse Takotsubo cardiomyopathy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.4
• /
• pp.405-413
• /
• 2012

Low misclassification performance is significant with high classification accuracy for a reliable diagnosis of ECG signals, and diagnosing abnormal state as normal state can especially raises a deadly problem to a person in ECG test. In this paper, we propose detection and classification method of abnormal rhythm by rule-based rhythm classification reflecting clinical criteria for disease. Rule-based classification classifies rhythm types using rule-base for feature of rhythm section, and rule-base deduces decision results corresponding to professional materials of clinical and internal fields. Experimental results for the MIT-BIH arrhythmia database show that the applicability of proposed method is confirmed to classify rhythm types for normal sinus, paced, and various abnormal rhythms, especially without misclassification in detection aspect of abnormal rhythm.

• Korean Journal of Clinical Laboratory Science
• /
• v.44 no.3
• /
• pp.136-141
• /
• 2012

The hearts of highly trained athletes show morphologic and electrocardiographic (ECG) changes that suggest the presence of cardiovascular disease, including sinus bradycardia, a striking increase in precordial R-wave or S-wave voltages, ST segment depression, and T-wave inversions. Despite a number of previous observational surveys, the determinants of abnormal ECG patterns in trained athletes remain largely unresolved. In this study, we compared the electrocardiographic characteristics of athletes to determine any sensitive indicators. Comparison between ECG patterns and cardiac physiology was performed in 21 junior athletes and 25 untrained subjects with no signs of cardiac disease. Sinus bradycardia was detected in a subset of athletes but not statistically significant between the athletes ($69.9{\pm}11.1bpm$) and the control ($72.7{\pm}9.9bpm$) group. The mean values of the PR and QTc intervals in the athletes' group were $149.2{\pm}15.4ms$ and $402.3{\pm}28.8ms$, respectively. Also, there were no significantly differences between control group and the athletes' group. In addition, the athletes demonstrated a spectrum of alterations in the 12-lead ECG pattern, including marked increase in precordial R-wave or S-wave voltages ($$SV_1+RV_5{\geq_-}35mm$$, 23.8%), QRS duration ($${\geq_-}90ms$$, 90.5%), suggestive of left ventricular hypertrophy. However, left axis deviation, ST segment depression, and T-wave changes in V5, V6 were not observed in either the athletes or control group. Our findings suggest that sinus bradycardia, precordial R-wave or S-wave voltages, and QRS duration seem to be more sensitively detected in athletes than in control group. Further researches on the electrocardiographic patterns of athletes should be carried out to improve the sensitivity and specificity of diagnostic criteria.

• Journal of Veterinary Clinics
• /
• v.15 no.2
• /
• pp.325-330
• /
• 1998

The purpose of this study is to investigate the effect of acupuncture after the induction of acute kidney disease in dogs by ethylene glycol. Twenty four mixed breed, adult cats were used in the experiment. Ethylene glycol was administered orally at 1 ml/kg in 24 cats, and then 6 cats were treated by acupunchuture 6 cats were treated by electroacupuncture, 6 cats were treated by acupuncture and 6 cats were not treated as a control group. Treatment was done once daily far 4 dsys. The acupoint used were Gan-shu and Tai-xi. The effect of acnpuncture was evaluated by clinical symptom, blood chemical values, electrocardiogram (ECG) and histopathologkal findings. After treatement, acupuncture group revealed relatively fast recovery compared with other groups, in clinical symptoms, blood chemical values, ECG waves and histopathological findings. Laserpuncture group revealed secondly fast recovery compared with control group.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.20 no.6
• /
• pp.81-87
• /
• 1983

The body surface ECG(electrocardiogram) is produced by the electric fields caused by the propagation of action potentials within the myocardial cells. The repolarization phase of the action potential is very sensitive to factors of clinical importance. Therefore, in this paper of the inverse electrocardiography, we studied a method of estimating the uniform action potentials during repolarization phase from the body surface ECG using digital signal identification techniques. The estimated action potential of a normal was similar to that of clinical data in the repolarization phase.

• Biomedical Science Letters
• /
• v.21 no.4
• /
• pp.208-217
• /
• 2015

The exact diagnosis of left ventricular hypertrophy (LVH) is very important in the treatment of hypertension. The purpose of our study is to determine the relationship between left ventricular remodeling patterns and electrocardiography (ECG) findings in hypertensive patients. We divided 137 patients into four groups according to left ventricular mass index (LVMI) and the relative wall thickness: normal, concentric remodeling, concentric hypertrophy, eccentric hypertrophy. LVH on the ECG was defined by three ECG criteria: Sokolow-Lyon voltage criteria, Cornell voltage criteria and Romhilt-Estes point score. LVH on the echocardiography was defined by LVMI. The prevalence of ECG LVH was increased in concentric hypertrophy and eccentric hypertrophy group. The QRS voltages by Sokolow-Lyon voltage criteria (r = 0.494, P = 0.002) and Cornell voltage criteria (r = 0.628, P < 0.001), and Romhilt-Estes point score (r = 0.689, P < 0.001) were positively correlated with LVMI. Also, the QRS voltages and point scores were significantly increased in the concentric hypertrophy and eccentric hypertrophy group with increased LVMI. The QRS voltage and Romhilt-Estes point scores were positively correlated with LVMI. The QRS voltages and Romhilt-Estes point scores were also increased in the left ventricular remodeling groups with increased LVMI.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.205-212
• /
• 2023

Among cardiac diseases, arrhythmias can lead to serious complications such as stroke, heart attack, and heart failure if left untreated, so continuous and accurate ECG monitoring is crucial for clinical care. However, the accurate interpretation of electrocardiogram (ECG) data is entirely dependent on medical doctors, which requires additional time and cost. Therefore, this paper proposes an arrhythmia recognition module for the purpose of developing a medical platform through the analysis of abnormal pulse waveforms based on Lifelogs. The proposed method is to convert ECG data into image format instead of time series data, apply visual pattern recognition technology, and then detect arrhythmia using CNN model. In order to validate the arrhythmia classification of the CNN model by image type conversion of ECG data proposed in this paper, the MIT-BIH arrhythmia dataset was used, and the result showed an accuracy of 97%.

• 대한임상약리학회:학술대회논문집
• /
• 2006.11a
• /
• pp.88-88
• /
• 2006