Reducing false alarm rates for critical arrhythmias using the arterial blood pressure waveform

BackgroundOver the past two decades, high false alarm (FA) rates have remained an important yet unresolved concern in the Intensive Care Unit (ICU). High FA rates lead to desensitization of the attending staff to such warnings, with associated slowing in response times and detrimental decreases in the quality of care for the patient. False arrhythmia alarms are commonly due to single channel ECG artifacts and low voltage signals, and therefore it is likely that the FA rates may be reduced if information from other independent signals is used to form a more robust hypothesis of the alarm’s etiology.MethodsA large multi-parameter ICU database (PhysioNet’s MIMIC II database) was used to investigate the frequency of five categories of false critical (“red” or “life-threatening”) ECG arrhythmia alarms produced by a commercial ICU monitoring system, namely: asystole, extreme bradycardia, extreme tachycardia, ventricular tachycardia and ventricular fibrillation/tachycardia. Non-critical (“yellow”) arrhythmia alarms were not considered in this study. Multiple expert reviews of 5386 critical ECG arrhythmia alarms from a total of 447 adult patient records in the MIMIC II database were made using the associated 41,301 h of simultaneous ECG and arterial blood pressure (ABP) waveforms. An algorithm to suppress false critical ECG arrhythmia alarms using morphological and timing information derived from the ABP signal was then tested.ResultsAn average of 42.7% of the critical ECG arrhythmia alarms were found to be false, with each of the five alarm categories having FA rates between 23.1% and 90.7%. The FA suppression algorithm was able to suppress 59.7% of the false alarms, with FA reduction rates as high as 93.5% for asystole and 81.0% for extreme bradycardia. FA reduction rates were lowest for extreme tachycardia (63.7%) and ventricular-related alarms (58.2% for ventricular fibrillation/tachycardia and 33.0% for ventricular tachycardia). True alarm (TA) reduction rates were all 0%, except for ventricular tachycardia alarms (9.4%).ConclusionsThe FA suppression algorithm reduced the incidence of false critical ECG arrhythmia alarms from 42.7% to 17.2%, where simultaneous ECG and ABP data were available. The present algorithm demonstrated the potential of data fusion to reduce false ECG arrhythmia alarms in a clinical setting, but the non-zero TA reduction rate for ventricular tachycardia indicates the need for further refinement of the suppression strategy. To avoid suppressing any true alarms, the algorithm could be implemented for all alarms except ventricular tachycardia. Under these conditions the FA rate would be reduced from 42.7% to 22.7%. This implementation of the algorithm should be considered for prospective clinical evaluation. The public availability of a real-world ICU database of multi-parameter physiologic waveforms, together with their associated annotated alarms is a new and valuable research resource for algorithm developers.     

A fuzzy clustering neural network architecture for classification of ECG arrhythmias

Accurate and computationally efficient means of classifying electrocardiography (ECG) arrhythmias has been the subject of considerable research effort in recent years. This study presents a comparative study of the classification accuracy of ECG signals using a well-known neural network architecture named multi-layered perceptron (MLP) with backpropagation training algorithm, and a new fuzzy clustering NN architecture (FCNN) for early diagnosis. The ECG signals are taken from MIT-BIH ECG database, which are used to classify 10 different arrhythmias for training. These are normal sinus rhythm, sinus bradycardia, ventricular tachycardia, sinus arrhythmia, atrial premature contraction, paced beat, right bundle branch block, left bundle branch block, atrial fibrillation and atrial flutter. For testing, the proposed structures were trained by backpropagation algorithm. Both of them tested using experimental ECG records of 92 patients (40 male and 52 female, average age is 39.75 +/- 19.06). The test results suggest that a new proposed FCNN architecture can generalize better than ordinary MLP architecture and also learn better and faster. The advantage of proposed structure is a result of decreasing the number of segments by grouping similar segments in training data with fuzzy c-means clustering.     

基于总体局部均值分解方法的心律失常特征提取与分类

针对心电信号自动分类技术中的特征提取,提出一种新的特征提取方法—总体局部均值分解（ELMD）方法。该方法首先对心电信号加入不同的高斯白噪声,然后进行局部均值分解得到若干乘积函数（PF）分量,求取多次分解后的PF分量均值。多次加入噪声及分量平均的过程可以克服基本局部均值分解方法存在的模态混叠问题。选取较优的前4个PF分量进行特征计算,将得到的特征向量矩阵送入支持向量机对正常心电信号和4种常见的心律失常信号进行分类。从MIT-BIH心律失常数据库的分类结果来看,ELMD总体分类准确率达到99.61%,高于一般方法,证明了ELMD方法的有效性。     

Clinical evaluation of a wireless ECG sensor system for arrhythmia diagnostic purposes

In a clinical study, a novel wireless electrocardiogram (ECG) recorder has been evaluated with regard to its ability to perform arrhythmia diagnostics. As the ECG recorder will detect a “non-standard” ECG signal, it has been necessary to compare those signals to “standard” ECG recording signals in order to evaluate the arrhythmia detection ability of the new system. Simultaneous recording of ECG signals from both the new wireless ECG recorder and a conventional Holter recorder was compared by two independent cardiology specialists with regard to signal quality for performing arrhythmia diagnosis. In addition, calculated R–R intervals from the two systems were correlated. A total number of 16 patients participated in the study. It can be considered that recorded ECG signals obtained from the wireless ECG system had an acceptable quality for arrhythmia diagnosis. Some of the patients used the wireless sensor while doing physical sport activities, and the quality of the recorded ECG signals made it possible to perform arrhythmia diagnostics even under such conditions. Consequently, this makes possible improvements in correlating arrhythmias to physical activities.     

Characterisation of electrocardiogram signals based on blind source separation

Blind source separation assumes that the acquired signal is composed of a weighted sum of a number of basic components corresponding to a number of limited sources. This work poses the problem of ECG signal diagnosis in the form of a blind source separation problem. In particular, a large number of ECG signals undergo two of the most commonly used blind source separation techniques, namely, principal component analysis (PCA) and independent component analysis (ICA), so that the basic components underlying this complex signal can be identified. Given that such techniques are sensitive to signal shift, a simple transformation is used that computes the magnitude of the Fourier transformation of ECG signals. This allows the phase components corresponding to such shifts to be removed. Using the magnitude of the projection of a given ECG signal onto these basic components as features, it was shown that accurate arrhythmia detection and classification were possible. The proposed strategies were applied to a large number of independent 3s intervals of ECG signals consisting of 320 training samples and 160 test samples from the MIT-BIH database. The samples equally represent five different ECG signal types, including normal, ventricular couplet, ventricular tachycardia, ventricular bigeminy and ventricular fibrillation. The intervals analysed were windowed using either a rectangular or a Hamming window. The methods demonstrated a detection rate of sensitivity 98% at specificity of 100% using nearest neighbour classification of features from ICA and a rectangular window. Lower classification rates were obtained using the same classifier with features from either PCA or ICA and a rectangular window. The results demonstrate the potential of the new method for clinical use.     

ECG beat classification using empirical mode decomposition and mixture of features

Computer-aided analysis is useful in predicting arrhythmia conditions of the heart by analysing the recorded ECG signals. In this work, we proposed a method to detect, extract informative features to classify six types of heartbeat of ECG signals obtained from the MIT-BIH Arrhythmia database. The powerful discrete wavelet transform (DWT) is used to eliminate different sources of noises. Empirical mode decomposition (EMD) with adaptive thresholding has been used to detect precise R-peaks and QRS complex. The significant features consists of temporal, morphological and statistical were extracted from the processed ECG signals and combined to form a set of features. This feature set is classified with probabilistic neural network (PNN) and radial basis function neural network (RBF-NN) to recognise the arrhythmia beats. The process achieved better result with sensitivity of 99.96%, and positive predictivity of 99.81 with error rate of 0.23% in detecting the QRS complex. In class-oriented scheme, the arrhythmia conditions are classified with accuracy of 99.54%, 99.89% using PNN and RBF-NN classifier respectively. The obtained result confirms the superiority of the proposed scheme compared to other published results cited in literature.     

结合迁移学习与深度卷积网络的心电分类研究

为解决一维深度卷积网络（1D-DCNN）在心电分类方面存在的多类疾病识别不准、难以提取最佳特征等问题,提出一种结合迁移学习与二维深度卷积网络（2D-DCNN）直接识别心电图像的方法。首先,截取R波前后75 ms内的心电信号,并将一维心电电压信号转化为二维灰度图像信号。接着,构建2D-DCNN对心电节拍样本进行分类训练,权值初始化采用在ImageNet大规模图像数据集上进行预训练的AlexNet参数值。本文提出方法在MIT-BIH心电数据库上进行性能验证,其准确率达到98%,并在不同信噪比下保持较高的准确率,证明了所述模型在心电分类上具有良好的鲁棒性。为了验证2D-DCNN的识别性能,实验部分与采用不同激活函数的1D-DCNN、近些年性能较好的深度学习方法进行比较。量化结果表明,结合迁移学习和2D-DCNN方法,比最优1D-DCNN算法,其准确率提升2%、敏感度提升0.6%、特异性提高4%;在二分类与多分类任务中,均好于现有的其他算法。     

Fragmentation of bandpass-filtered QRS-complex of patients prone to malignant arrhythmia

The structure of high-frequency components of electric and magnetic signals from the heart during the depolarisation phase is investigated. After averaging and broadband filtering with a binomial bandpass filter (37 Hz-90 Hz), the fragmentation of the QRS-complex is quantified. The number of extrema M and a new score value S are calculated from the signals of three electrical leads and one magnetic lead of 23 healthy subjects, 23 patients with coronary heart disease (CHD) without reported event of ventricular tachycardia or fibrillation at the time of measurement, and eight patients with CHD who have suffered from malignant tachycardia. For the parameter M, the sensitivity and specificity for healthy subjects against patients with CHD and ventricular tachycardia for the magnetic lead (the best electric lead) are 100% (75%) and 100% (100%). For the magnetic lead (best electric lead) and parameter S, the sensitivity and specificity are 100% (75%) and 95.6% (100%).     

基于扩展卡尔曼滤波和奇异值分解算法的单通道胎儿心电提取方法

提出一种将扩展卡尔曼滤波(EKF)算法和奇异值分解(SVD)算法相结合的单通道胎儿心电提取方法。首先,建立母体心电的动态模型,利用该模型通过扩展卡尔曼滤波或扩展卡尔曼平滑(EKS),从孕妇的单通道腹部信号中估计出母体心电成分,然后与单通道腹部信号相减得到胎儿心电信号的初步估计,随后再利用奇异值分解算法,对初步估计出的胎儿心电信号进行去噪处理,以期得到高信噪比的胎儿心电信号。另外,针对胎儿心律不齐的情况,在奇异值分解算法中提出一种改进的心电信号重构矩阵构造方法。对合成腹部信号和实际腹部信号(源于DaISy数据库和PhysioNet中的非侵入式胎儿心电数据库,共计49个腹部通道的数据),进行胎儿心电提取实验。结果表明,使用EKF+SVD或EKS+SVD的算法比单独使用EKF或EKS的算法,提取出的胎儿心电信号的信噪比提高约5 dB,胎儿心电提取的准确性分别达95.60%和95.94%。结合EKF和SVD算法的单通道胎儿心电提取方法,可以有效地提高胎儿心电信号的信噪比和提取的准确性,并且适用于母体或胎儿心律不齐的情况。     

基于波形特征和SVM的心电信号自动分类方法研究

目的:提出一种新的基于波形特征和SVM的心电信号自动分类实现方法。方法:定义并提取了基于时域特征、小波域特征和高阶统计量特征等三大类心电特征参数,将一次性直接求解多类模式的SVM方法应用于心电信号分类。结果:通过对心电数据库典型心律失常信号的分类测试,验证了所提出心电信号分类方法的有效性。结论:本方法的实现可以有效提高了分类识别精度和速度。     

A Case of Catecholaminergic Polymorphic Ventricular Tachycardia

Catecholaminergic polymorphic ventricular tachycardia (CPVT) is a familial cardiac arrhythmia that is related to RYR2 or CASQ2 gene mutation. It occurs in patients with structurally normal heart and causes exercise-emotion-triggered syncope and sudden cardiac death. We experienced a case of CPVT in an 11 year-old female patient who was admitted for sudden cardiovascular collapse. The initial electrocardiogram (ECG) on emergency department revealed ventricular fibrillation. After multiple defibrillations, sinus rhythm was restored. However, recurrent ventricular fibrillation occurred during insertion of nasogastric tube without sedation in coronary care unit. On ECG monitoring, bidirectional ventricular tachycardia occurred with sinus tachycardia and then degenerated into ventricular fibrillation. To our knowledge, there has been no previous case report of CPVT triggered by sinus tachycardia in Korea. Therefore, we report the case as well as a review of the literature.     

Automatic detection of atrial fibrillation and flutter by wave rectification method.

Rapid detection of atrial flutter or fibrillation is needed in intensive care or home ECG monitoring with alarm generation, and in portable monitors with warningfunction, etc. Detection and assessment of these atrial abnormalities is necessary in computerized morphological analysis as well, to decide whether parameter measurements should be rejected, restricted to QRS and/or T wave only, or limited to those leads where atrial flutter orfibrillation waves are less expressed. A method for the detection and measurement of atrial flutter and fibrillation in the T-P segments of the ECG is proposed. An atrial flutter/ fibrillation parameter (AFF) is defined as the mean value of the differentiated filtered and rectified signal in these segments. The AFF has been measured in 329 patients from an annotated atrial flutter-fibrillation database. A threshold of AFF=0.35% with respect to the maximum signal excursion was chosen by a heuristic algorithm, to separate patients with atrial arrhythmia. The accuracy of the method was 91.8 %. The positive and negative detection errors of the AFF classification are discussed.     

Automatic detection of atrial fibrillation and flutter by wave rectification method

Rapid detection of atrial flutter or fibrillation is needed in intensive care or home ECG monitoring with alarm generation, and in portable monitors with warning function, etc. Detection and assessment of these atrial abnormalities is necessary in computerized morphological analysis as well, to decide whether parameter measurements should be rejected, restricted to QRS and/or T wave only, or limited to those leads where atrial flutter or fibrillation waves are less expressed. A method for the detection and measurement of atrial flutter and fibrillation in the T-P segments of the ECG is proposed. An atrial flutter/ fibrillation parameter (AFF) is defined as the mean value of the differentiated filtered and rectified signal in these segments. The AFF has been measured in 329 patients from an annotated atrial flutter-fibrillation database. A threshold of AFF=0.35% with respect to the maximum signal excursion was chosen by a heuristic algorithm, to separate patients with atrial arrhythmia. The accuracy of the method was 91.8%. The positive and negative detection errors of the AFF classification are discussed.     

Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal

OBJECTIVE: This paper presents an effective cardiac arrhythmia classification algorithm using the heart rate variability (HRV) signal. The proposed algorithm is based on the generalized discriminant analysis (GDA) feature reduction scheme and the support vector machine (SVM) classifier. METHODOLOGY: Initially 15 different features are extracted from the input HRV signal by means of linear and nonlinear methods. These features are then reduced to only five features by the GDA technique. This not only reduces the number of the input features but also increases the classification accuracy by selecting most discriminating features. Finally, the SVM combined with the one-against-all strategy is used to classify the HRV signals. RESULTS: The proposed GDA- and SVM-based cardiac arrhythmia classification algorithm is applied to input HRV signals, obtained from the MIT-BIH arrhythmia database, to discriminate six different types of cardiac arrhythmia. In particular, the HRV signals representing the six different types of arrhythmia classes including normal sinus rhythm, premature ventricular contraction, atrial fibrillation, sick sinus syndrome, ventricular fibrillation and 2 degrees heart block are classified with an accuracy of 98.94%, 98.96%, 98.53%, 98.51%, 100% and 100%, respectively, which are better than any other previously reported results. CONCLUSION: An effective cardiac arrhythmia classification algorithm is presented. A main advantage of the proposed algorithm, compared to the approaches which use the ECG signal itself is the fact that it is completely based on the HRV (R-R interval) signal which can be extracted from even a very noisy ECG signal with a relatively high accuracy. Moreover, the usage of the HRV signal leads to an effective reduction of the processing time, which provides an online arrhythmia classification system. A main drawback of the proposed algorithm is however that some arrhythmia types such as left bundle branch block and right bundle branch block beats cannot be detected using only the features extracted from the HRV signal.     

应用目标检测网络自动检测ECG信号所含噪声

现阶段的心电（ECG）信号去噪网络多通过滤波器滤除噪声,但是通常噪声滤除不彻底,从而造成ECG信号失真。基于此,本研究将目标检测网络用于ECG信号中的噪声检测,首先从MIT-BIT心律不齐数据库中筛选无噪声ECG记录,加入两种来自于MIT-BIH噪声压力测试数据库中的真实噪声,生成4个不同信噪比的含噪信号并构成训练及测试数据集。然后针对ECG信号的特殊性,对YOLOv3网络结构进行修改,设计YOLO-ECG目标检测网络,使用迁移学习策略训练目标检测网络。实验结果表明,本研究提出的网络在ECG信号中噪声检测时的F1值达0.955 8,具有良好的检测效果。     

An arrhythmia classification system based on the RR-interval signal

OBJECTIVE: This paper proposes a knowledge-based method for arrhythmic beat classification and arrhythmic episode detection and classification using only the RR-interval signal extracted from ECG recordings. METHODOLOGY: A three RR-interval sliding window is used in arrhythmic beat classification algorithm. Classification is performed for four categories of beats: normal, premature ventricular contractions, ventricular flutter/fibrillation and 2 degrees heart block. The beat classification is used as input of a knowledge-based deterministic automaton to achieve arrhythmic episode detection and classification. Six rhythm types are classified: ventricular bigeminy, ventricular trigeminy, ventricular couplet, ventricular tachycardia, ventricular flutter/fibrillation and 2 degrees heart block. RESULTS: The method is evaluated by using the MIT-BIH arrhythmia database. The achieved scores indicate high performance: 98% accuracy for arrhythmic beat classification and 94% accuracy for arrhythmic episode detection and classification. CONCLUSION: The proposed method is advantageous because it uses only the RR-interval signal for arrhythmia beat and episode classification and the results compare well with more complex methods.     

Antiarrhythmic efficacy of amiodarone in recurrent ventricular tachycardia evaluated by multiple electrophysiological and ambulatory ECG recordings

Thirty-three patients with recurrent drug-refractory ventricular tachycardia were treated with oral amiodarone during an average period of 6.1 months. In-hospital monitoring for two weeks or more, electrophysiological tests and ambulatory ECG were used to evaluate the results. Twenty patients are still using the drug with complete control of the arrhythmia. Eleven have failed the drug, ten due to recurrence of documented ventricular tachycardia. Only three patients failed after the first month of therapy. Two patients died, one suddenly. The drug was discontinued in a further two patients due to side-effects. Other side-effects were tolerable or manageable by dose adjustments alone. Five patients showed evidence of inadequate arrhythmia control between days 15 and 32 of therapy but subsequently responded to the drug for 4-9 months, giving further support to the concept that in some patients at least 30 days of therapy is necessary for the full effect of the drug to appear. In 16 of the 20 patients tested by arrhythmia induction study while on the drug, ventricular tachycardia could still be induced. Seven (44%) of these eventually failed the drug. Arrhythmia recurred in one of those four in whom tachycardia could not be induced. Amiodarone is a valuable drug in the management of recurrent ventricular tachycardia, refractory to other antiarrhythmic drugs.     

Autocorrelation function analysis of ECG signals in 20 rabbits

In this experiment, we measured ECG signals of lead I, respectively, during normal and arrhythmia after 20 rabbits were anaesthetized. These signals were recorded, then the information was put into a computer and it analyzed Autocorrelation (AC) Function, and Power Spectrum. The results make us know: (1) periodicity corresponding relationship of ECG in normal rabbits can derive reflects from changes of ECG AC function changes of ECG signals in arrhythmia rabbits can derive relatively sensitive reflection from changes of ECG function (attenuating area S and the value of k) in normal rabbits. (2) The Autocorrelation Function of Electrocardio change but ECG in the normal. All these provide another useful method for the diagnosis of arrhythmia.     

基于自适应学习的心律失常心拍分类方法

心律失常是因心脏疾病引起的心电活动中的异常症状,早期心室收缩（PVC）是由异位心跳引起的常见心律失常形式。通过心电图（ECG）信号检测PVC对于预测可能的心力衰竭具有重要意义。本文提出一种面向PVC心拍分类的心电信号分类算法,重点研究基于自适应学习的PVC异常心拍分类特征提取模型,通过计算心拍关联后验概率,结合领域专家标注信息训练分类器,提高整体分类效果。实验采用MIT-BIH心律失常数据库的ECG数据,研究结果表明所提方法针对非线性流形结构数据,能够有效提升小样本心拍自适应分类器的准确性。