基于双阶段特征提取网络的ECG降噪分类算法

临床采集到的标准12导联心电图常含有噪声,影响了心电信号分类结果的准确度,为此提出了一种基于双阶段特征提取网络的心电图(ECG)降噪分类算法。首先,在空间特征提取阶段,由深度耦合软阈值化去噪方法的残差收缩网络从输入的12导联标准心电信号中提取空间特征;其次,在时间特征提取阶段,由长短期记忆网络与注意力机制结合继续从心电信号中提取时间特征;最后,通过全连接网络层融合提取到的空间特征与时间特征,输出9个类别的概率预测分布。在CPSC2018数据集上与其他同类型先进分类算法进行了对比实验,验证所提算法的效果,实验结果表明:提出的分类算法在对9类ECG信号进行分类时平均F1分数达到0.854,在各项指标上表现更优。此外,实验证明所提算法在含噪数据中的表现也优于其他主流网络,充分证明了所提算法对于含噪心电信号的降噪分类性能,该算法也可应用于其他类似含噪声生理信号的分析和处理。

腔内ECG定位技术联合体外测量法在PICC中的应用

目的:探讨腔内心电图(ECG)定位技术联合体外测量法在经外周静脉穿刺的中心静脉导管(PICC)中的应用。方法:选取2021年1月—2023年1月阜宁县人民医院收治的100例行上肢PICC置管的患者作为研究对象。根据抛币法将其随机分为观察组和对照组,各50例。两组均进行PICC,对照组PICC应用体外测量法,观察组PICC应用腔内ECG定位技术联合体外测量法。比较两组一次性置管情况、导管相关并发症、置管满意度。结果:观察组置管准确率为98.00%,高于对照组的86.00%,置管过深率低于对照组,差异有统计学意义(P<0.05)。两组并发症发生率比较,差异无统计学意义(P>0.05)。观察组总满意度为100%,高于对照组的92.00%,差异有统计学意义(P<0.05)。结论:腔内ECG定位技术联合体外测量法可提高一次置管准确率,提高患者满意率。

Electrocardiographic predictors of cardiovascular events in patients at high cardiovascular risk: a multicenter study

Background There are limited data on the prevalence of electrocardiographic (ECG) abnormalities, and their value for predicting a major adverse cardiovascular event (MACE) in patients at high cardiovascular risk. This study aimed to determine the prevalence of ECG abnormalities in patients at high risk for cardiovascular events, and to identify ECG abnormalities that significantly predict MACE. Methods Patients aged ≥ 45 years with established atherosclerotic disease (EAD) were consecutively enrolled from the outpatient clinics of the six participating hospitals during April 2011 to March 2014. The following data were collected: demographic data, cardiovascular risk factors, history of cardiovascular event, physical examination, ECG and medications. ECG was analyzed using Minnesota Code criteria. MACE included cardiovascular death, non-fatal myocardial infarction, and hospitalization due to unstable angina or heart failure. Results A total of 2009 patients were included, 1048 patients (52.2%) had established EAD, and 961 patients (47.8%) had multiple risk factors (MRF). ECG abnormalities included atrial fibrillation (6.7%), premature ventricular contraction (5.4%), pathological Q-wave (Q/QS)(21.3%), T-wave inversion (20.0%), intraventricular ventricular conduction delay (IVCD)(7.3%), left ventricular hypertrophy (LVH)(12.2%), and AV block (12.5%). MACE occurred in 88 patients (4.4%). Independent predictors of MACE were chronic kidney disease, EAD, and the presence of atrial fibrillation, Q/QS, IVCD or LVH by ECG. Conclusions A high prevalence of ECG abnormalities was found. The prevalence of ECG abnormalities was high even among those with risk factors without documented cardiovascular disease.

Local wavelet-based filtering of electromyographic signals to eliminate the electrocardiographic-induced artifacts in patients with spinal cord injury

Surface Electromyography (EMG) is a standard method used in clinical practice and research to assess motor function in order to help with the diagnosis of neuromuscular pathology in human and animal models. EMG recorded from trunk muscles involved in the activity of breathing can be used as a direct measure of respiratory motor function in patients with spinal cord injury (SCI) or other disorders associated with motor control deficits. However, EMG potentials recorded from these muscles are often contaminated with heart-induced electrocardiographic (ECG) signals. Elimination of these artifacts plays a critical role in the precise measure of the respiratory muscle electrical activity. This study was undertaken to find an optimal approach to eliminate the ECG artifacts from EMG recordings. Conventional global filtering can be used to decrease the ECG-induced artifact. However, this method can alter the EMG signal and changes physiologically relevant information. We hypothesize that, unlike global filtering, localized removal of ECG artifacts will not change the original EMG signals. We develop an approach to remove the ECG artifacts without altering the amplitude and frequency components of the EMG signal by using an externally recorded ECG signal as a mask to locate areas of the ECG spikes within EMG data. These segments containing ECG spikes were decomposed into 128 sub-wavelets by a custom-scaled Morlet Wavelet Transform. The ECG-related subwavelets at the ECG spike location were removed and a de-noised EMG signal was reconstructed. Validity of the proposed method was proven using mathematical simulated synthetic signals and EMG obtained from SCI patients. We compare the Rootmean Square Error and the Relative Change in Variance between this method, global, notch and adaptive filters. The results show that the localized wavelet-based filtering has the benefit of not introducing error in the native EMG signal and accurately removing ECG artifacts from EMG signals.

Arterial hypertension and electrocardiographic diagnosis of left ventricular hypertension in the group of geriatric patients with coronary heart disease living in the far north

As a result of research, high prevalence of arterial hypertension has been identified in the group of patients with coronary heart disease aged 60 and older. Most often, occurring form of arterial hypertension among geriatric patients is isolated systolic arterial hypertension (ISAH). The comparison of two ethnic groups of the population has showed higher levels of systolic and diastolic blood pressure (SBP and DBP) in the group of patients of non-indigenous nationality, rather than Yakut patients. Correlation was recorded in the group of non-indigenous patients as they age. Significant increase in the level of SBP was identified in the group of senile and long-livers than in the elderly. Detection of ECG signs of LVH showed the lowest specificity of Cornell voltage criterion comparing to Sokolow-Lyon criterion with its more often occurrence. ECG-signs of left ventricle hypertrophy are significantly more often established by Sokolow-Lyon criterion for men, Cornell voltage—for women. Correlation has been found between the presence of LVH and combination of Cornell voltage criterion with both Gubner-Ungerleider and Sokolow-Lyon criteria.

Validity of electrocardiographic criteria for increased left ventricular mass in young patients in the general population

AIMTo investigate validity of electrocardiographic(ECG)criteria for left ventricular hypertrophy(LVH)in young adults.METHODS Retrospectively,echocardiograms showing LVH and concomitant electrocardiograms were collected in patients 18 to 39 years old.A control group of patients without LVH was collected.Using echocardiogram as the gold standard,electrocardiograms were analyzed using common voltage criteria.RESULTS Study included 100 subjects(52%male,mean age=28±6.8 years,96%Hispanic or African-American)with 50%LVH prevalence.Sensitivity and specificity for SokolowLyon criteria were 24%(95%CI:13.5%-38.4%)and 88%(95%CI:74.9%-95%).For Cornell criteria,sensitivity was 32%(95%CI:19.9%-46.8%)and specificity 98%(95%CI:87.9%-99.8%).For R in a VL criteria,sensitivity was 12%(95%CI:4.9%-25%)and specificity 100%(95%CI:91.1%-100%).CONCLUSION In young adults common ECG voltage criteria have low sensitivities and high specificities similar to other age groups.Low sensitivities preclude these ECG criteria from serving as effective screening tests.

基于单通道ECG信号与INFO-ABCLogitBoost模型的睡眠分期

为了减少对传统多导睡眠图(PSG)系统的依赖,基于单通道心电图(ECG)信号,设计了一种简单高效的睡眠分析算法.采用最大重叠离散小波变换(MODWT)对原始信号进行多分辨分析,再进一步提取峰值信息;根据峰值位置的一阶偏差,提取多维度的心率变异性(HRV)特征.为了进一步筛选与不同睡眠阶段具有强关联性的HRV特征,提出基于ReliefF算法与Gini指数的特征提取方法.在此基础上,采用INFO-ABCLogitBoost方法挖掘HRV与不同睡眠阶段之间的关联性,从而实现睡眠阶段的精细分类.在实际公开数据集上的实验结果表明,所提出的模型在睡眠分期任务中,总体精度为83.67%,准确率为82.59%,Kappa系数为77.94%,F1-Score为82.97%.相比于睡眠分期任务中的常规模型,所提方法展现出更加高效便捷的睡眠质量评估性能,有助于实现家庭或移动医疗场景下的睡眠监测.

Gastric volvulus presenting as an acute coronary syndrome with long-lasting electrocardiographic changes

A sixty-one-year-old male,with a medical history of coronary heart disease and myocardial bridge (not confirmed by cardiac catheterization) in the past three years and a 1-h history of sudden onset nausea,retching,diaphoresis,epigastric discomfort without any chest pain.The electrocardiogram revealed ST elevation myocardial infarction (STEMI) changes (Figure 1A).Urgent cardiac catheterization revealed mild myocardial bridge in the middle of the left anterior descending (LAD)(10% systolic compression) and normal left ventricular function without regional wall motion abnormalities.Three high-sensitivity cardiac troponin I (HSTNT) titers done at 4,8 and 20 h from the onset of symptoms were HSTNT =10.5 pg/mL,10.9 pg/mL,25.4 pg/mL (less than 26.2) with CK-MB = 3 pg/mL,18 pg/mL,13 pg/mL (< 25) and the myoglobin levels were = 34.8 pg/mL,39.6 pg/mL,44.5 pg/mL (< 140.1),respectively.

基于深度学习的ECG信号分类与诊断

心电图(ECG)信号描绘了心脏的电活动,提供了有关心脏状态的重要信息。ECG信号分类可用于临床预测、诊断、评估的成果,对于心脏病的自动诊断非常重要。但是基于机器学习的ECG信号分类研究也存在一些如模型复杂度与临床数据实时传输和及时更新等未能解决的问题。因此,笔者首先对近10年来基于机器学习的ECG信号分类从波形形态分类、疾病诊断分类和纯粹的机器学习分类研究进行了回顾与综述,总结出了目前的研究遇到的困境,最后对未来面临的问题进行展望。深入学习模型在现实应用中仍存在一些挑战,未来的研究将进一步探索在芯片中实现机器学习模型的便携性和成本效益的硬件解决方案。此外,机器学习算法应寻求最佳的计算开销平衡,并重视在现实世界环境中的应用。在未来研究中,ECG应多进行临床试验,以评估机器学习模型在处理实际生物医学信号时的有效性和可行性,同时构造性价比高的深度学习模型,以帮助医学专家进行精确和及时的预测和诊断。

A Method for Normal Direction Judge Applied in Electrocardiographic Problem

Boundary Element Method (BEM) is widely used in electrocardiographic (ECG) problem. Formulations of these problems based on mathematical and numerical approximations of the known source in heart and the volume conductor that can transfer voltages on the surface of the body. To analyze the electric potentials on body surface or epicardial surface, a set of discrete equations derived from a boundary integral equations need to be solved. Solving these equations means to get the potential distribution eventually. In the process of solving, transfer matrix of discrete equations has received considerable attention, how to get an appropriate transfer matrix is an important issue. This paper found that the direction of normal vector could affect the results when calculating the transfer matrix and presents a method analogous to Mesh Current Method to deal with this direction problem. Several simulations have been carried out to verify the accurate results with the correct direction of normal vector using new method within a torso model given simultaneous epicardial and body surface potential recordings.

Electrocardiographic Safety of Daily Hydroxychloroquine 400 mg Plus Azithromycin 250 mg as an Ambulatory Treatment for COVID-19 Patients in Cameroon

Objective: To determine the early electrocardiographic changes in a cohort of ambulatory cameroonian COVID-19 patients treated with hydroxychlo- roquine and Azithromycin. Design: Prospective study. Setting: Treatment centres of the city of Yaounde, Cameroon, from May 7th to 24th 2020. Participants: We enrolled 51 consecutive confirmed COVID-19 on RT-PCR who having mild forms of COVID-19 and treated by hydroxychloroquine 200 mg twice daily during seven #days plus Azithromycin 500 mg the first day and 250 mg the remaining 4 days as per national standard. Main Outcomes Measures: The primary end-point was the change in QTc interval between day 0 (D0), day 3 (D3) and day 7 (D7). Secondary endpoints were changes in all other cardiac electrical conductivity patterns and the occurrence of clinical arrhythmic events during the course of treatment. Results: The population (29 men and 22 women) was aged 39 ± 11 years (range 17 to 61 years). Mean Tisdale score was 3.35 ± 0.48. No significant change from baseline (D0) of QTc was observed at D7 (429 ± 27 ms at D0 versus 396 ± 26 ms at D7;p = 0.27). A reduction of heart rate was observed between the D0 and D7 (75 ± 13 bpm versus 70 ± 13 bpm, p = 0.02) with increased QRS duration between D0 and D7 (95 ± 10 ms versus 102 ± 17 ms, p = 0.004). No symptomatic arrhythmic events occurred during the treatment course. Conclusions: No life-threatening modification of the QT interval was observed in non-severe COVID-19 patients treated ambulatory with hydroxychloroquine and azithromycin. Studies are needed in critical-ill and older patients.

Electrocardiographic Manifestations of Endocrine and Metabolic Disorders

Endocrine dysfunction has an adverse impact on the cardiovascular system that may be due to an endocrine abnormality that leads to electrocardiogram (EKG) changes. The EKG changes due to endocrine disorder can be reversible and irreversible and treating underlying disease can reverse EKG changes in some cases. In this article, we review the electrocardiogram manifestations of various endocrine disorders.

Electrocardiographic Changes in Patients with Type 2 Diabetes Multicenttic Cross Sectional and Descriptive Study in Dakar

Introduction: The resting electrocardiogram is generally called upon in the evaluation of cardiovascular risk in diabetics. Thus we proposed in this work to evaluate electrocardiographic changes in patients with type 2 diabetes. Methods: This was a cross-sectional and descriptive observation that took place from 1 January 2014 to 1 October 2014 in the Internal Medicine/Endocrinology Departments of Pikine National Hospital and Cardiology National Hospital of Grand-Yoff. Results: One hundred (100) patients consisted of 43 male and 57 female diabetics. The sex ration male/female ratio was 0.7. The average age was 58.3 years. Men were twice as likely to be active as women. Rhythm disorders were noted in 20% of patients, 13% of whom were women. Right atrial hypertrophy was found in 11% of patients and left hypertrophy in both men and women (25%). Wolf-Parkinson White syndrome was present in 2% of patients. A complete right bundle block was present in 11% of patients. Primary repolarization disorders were noted in 17% of patients and secondary in 18% of patients, postero-diaphragmatic necrosis in 14% of patients, real posterior necrosis in 2% of patients, extensive anterior necrosis in 15% of patients. The QT interval was lengthened in 21% of patients including 14 women. Left ventricular hypertrophy was present in 33% of patients and right ventricular hypertrophy was found in 10% of patients. The bivariate analysis showed that electrocardiographic abnormalities were more correlated with the association of certain risk factors such as hypertension and dyslipidemia, the feminine gender, but also the poor glycemic balance. On the other hand, physical activity and treatment had a protective effect. Conclusion: The ECG is certainly insufficient for an exhaustive exploration of the heart of the diabetic patient, but still very useful in our conditions of exercise to improve the care of our patients.

Electrocardiographic abnormalities in prevalent infections in tropical regions:A scoping review

Cardiovascular manifestations and electrocardiographic abnormalities have been reported among some prevalent infections in tropical regions,which lead to a great amount of morbidity and mortality.The major infectious diseases include chikungunya,dengue fever,H1N1 influenza,and coronavirus disease-19(COVID-19)in the viral category,leptospirosis,salmonellosis,scrub typhus and tuberculosis in the bacterial category,and malaria in the protozoan parasite category.All these infirmities constitute a foremost infection burden worldwide and have been linked to the various cardiac rhythm aberrancies.So we aimed to identify and compile different studies on these infections and associated acute electrocardiographic(ECG)changes.The search was made in online international libraries like PubMed,Google Scholar,and EMBASE,and 38 most relevant articles,including original research,systematic reviews,and unique case reports were selected.All of them were evaluated thoroughly and information regarding ECG was collected.Myocarditis is the predominant underlying pathology for rhythm disturbance and can be affected either due to the direct pathogenic effect or the abnormal immune system activation.ECG variabilities in some infections like chikungunya,scrub typhus,and leptospirosis are associated with longer hospital stay and poor outcome.Tropical infective diseases are associated with prominent acute cardiac rhythm abnormalities due to myocarditis,which can be identified preliminarily by ECG changes.

Comparison of the Performance of Three Commonly Used Electrocardiographic Indexes for the Diagnosis of Left Ventricular Hypertrophy in Black Hypertensive Patients with Reduced Kidney Function Managed at a Tertiary Healthcare Hospital: A Post-Hoc Analysis

Background: Reduced kidney function in blacks is associated with an increased frequency of left ventricular hypertrophy. Given the unavailability of echocardiography in most developing countries, the diagnostic performance of current ECG indexes needs to be evaluated. Objective: To compare the diagnostic performance of 3 commonly used ECG indexes (Sokolow-Lyon, Cornell voltage and Cornell product) in black hypertensive patients. Methods: Electrocardiography and echocardiography estimated left ventricular mass of 155 consecutive hypertensive patients who participated from January 2012 to January 2013 to an echocardiographic cross-sectional study of left ventricular structure was analyzed to compare Cornell voltage and Cornell product indexes with Sokolow-Lyon voltage index as a reference. Reduced kidney function was defined as eGFR 2. ROC curves in relation to LVH diagnosis were used to estimate the sensitivities and specificities of each index. P Results: The sensitivity and specificity were 43% and 85%, 23% and 77% and 26% and 77% for Sokolow-Lyon, Cornell voltage and Cornell product indexes, respectively. However, Sokolow-Lyon index (AUC;95% CI: 0.64;0.50 - 0.78) showed better performance than Cornell voltage (0.42;0.25 - 0.59) and Cornell product (0.43;0.28 - 0.59). Sokolow-Lyon index cut-point ≥ 37 mm corresponded to the highest Youden index (39.4% of sensitivity and 92.3% of specificity). Conclusion: Although the overall performance of the 3 ECG indexes versus echocardiography was low, Sokolow-Lyon index performed better than the two other indexes in diagnosing LVH.

Emotion Detection Using ECG Signals and a Lightweight CNN Model

Emotion recognition is a growing field that has numerous applications in smart healthcare systems and Human-Computer Interaction(HCI).However,physical methods of emotion recognition such as facial expressions,voice,and text data,do not always indicate true emotions,as users can falsify them.Among the physiological methods of emotion detection,Electrocardiogram(ECG)is a reliable and efficient way of detecting emotions.ECG-enabled smart bands have proven effective in collecting emotional data in uncontrolled environments.Researchers use deep machine learning techniques for emotion recognition using ECG signals,but there is a need to develop efficient models by tuning the hyperparameters.Furthermore,most researchers focus on detecting emotions in individual settings,but there is a need to extend this research to group settings aswell since most of the emotions are experienced in groups.In this study,we have developed a novel lightweight one dimensional(1D)Convolutional Neural Network(CNN)model by reducing the number of convolution,max pooling,and classification layers.This optimization has led to more efficient emotion classification using ECG.We tested the proposed model’s performance using ECG data from the AMIGOS(A Dataset for Affect,Personality and Mood Research on Individuals andGroups)dataset for both individual and group settings.The results showed that themodel achieved an accuracy of 82.21%and 85.62%for valence and arousal classification,respectively,in individual settings.In group settings,the accuracy was even higher,at 99.56%and 99.68%for valence and arousal classification,respectively.By reducing the number of layers,the lightweight CNNmodel can process data more quickly and with less complexity in the hardware,making it suitable for the implementation on the mobile phone devices to detect emotions with improved accuracy and speed.

Deep Learning-Based ECG Classification for Arterial Fibrillation Detection

The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant interest.Accurate and timely diagnosis increases the patient’s chances of recovery.However,issues like overfitting and inconsistent accuracy across datasets remain challenges.In a quest to address these challenges,a study presents two prominent deep learning architectures,ResNet-50 and DenseNet-121,to evaluate their effectiveness in AFib detection.The aim was to create a robust detection mechanism that consistently performs well.Metrics such as loss,accuracy,precision,sensitivity,and Area Under the Curve(AUC)were utilized for evaluation.The findings revealed that ResNet-50 surpassed DenseNet-121 in all evaluated categories.It demonstrated lower loss rate 0.0315 and 0.0305 superior accuracy of 98.77%and 98.88%,precision of 98.78%and 98.89%and sensitivity of 98.76%and 98.86%for training and validation,hinting at its advanced capability for AFib detection.These insights offer a substantial contribution to the existing literature on deep learning applications for AFib detection from ECG signals.The comparative performance data assists future researchers in selecting suitable deep-learning architectures for AFib detection.Moreover,the outcomes of this study are anticipated to stimulate the development of more advanced and efficient ECG-based AFib detection methodologies,for more accurate and early detection of AFib,thereby fostering improved patient care and outcomes.

Efficient ECG classification based on Chi-square distance for arrhythmia detection

This study introduces a new classifier tailored to address the limitations inherent in conventional classifiers such as K-nearest neighbor(KNN),random forest(RF),decision tree(DT),and support vector machine(SVM)for arrhythmia detection.The proposed classifier leverages the Chi-square distance as a primary metric,providing a specialized and original approach for precise arrhythmia detection.To optimize feature selection and refine the classifier’s performance,particle swarm optimization(PSO)is integrated with the Chi-square distance as a fitness function.This synergistic integration enhances the classifier’s capabilities,resulting in a substantial improvement in accuracy for arrhythmia detection.Experimental results demonstrate the efficacy of the proposed method,achieving a noteworthy accuracy rate of 98% with PSO,higher than 89% achieved without any previous optimization.The classifier outperforms machine learning(ML)and deep learning(DL)techniques,underscoring its reliability and superiority in the realm of arrhythmia classification.The promising results render it an effective method to support both academic and medical communities,offering an advanced and precise solution for arrhythmia detection in electrocardiogram(ECG)data.

以BP神经网络为工具的短时ECG信号情感分类

针对目前生理信号情感识别领域采用的生理信号种类太多或使用的生信号长度较长的问题,本文使用BP神经网络对单一、短时ECG信号进行情感识别分类,并对识别时间进行了估计。通过诱发被试喜、怒、哀、惧和平静5种基本情感状态,采集到ECG生理信号,处理后利用神经网络建立模型。实验结果表明,本文方法得到的情感分类的平均识别率为89.14%,且生理信号进行特征提取和识别分类的时间总和小于0.15s,有效地降低了对生理信号种类和窗口长度的依赖。

THE PREDICTIVE VALUE OF ELECTROCARDIOGRAPHIC S_ⅠQ_ⅢT_Ⅲ PATTERN IN ACUTE PULMONARY EMBOLISM

Objective:To evaluate the predictive value of electrocardiographic SⅠQⅢTⅢ pattern in patients with acute pulmonary embolism . Method: ECG was analyzed retrospectively in 102 patients with acute pulmonary embolism confirmed by spiral CT scan and Compared the clinical data between SⅠQⅢTⅢ positive and negative group. Result: In 102 patients 29 cases have positive SⅠQⅢTⅢ , positive rate was 28.4%. In SⅠQⅢTⅢ positive group and SⅠQⅢTⅢ negative group, 41.4% vs 69.9% have vulnerable diagnosis before admitted, respectively(P < 0.05),as well as the massive PE 48.3% vs 23.3% (P < 0.05),mortality rate 24.1% vs 10.9(P < 0.05),bilateral PE 86.3% vs 65.8%(P < 0.05) and right side PE 10.3% vs 31.5%(P < 0.05).Conclusion : positive Electrocardiographic SⅠQⅢTⅢ could not be served as the basic diagnosis criteria for acute PE . positive SⅠQⅢTⅢ ECG could decrease the misdiagnosis of acute PE, indicate higher possibility of bilateral and massive acute PE.