An automated patient-specific ECG beat classification using LSTM-based recurrent neural networks

ECG beat classification using particle swarm optimization and radial basis function neural network

State-of-the-art studies on automatic heartbeat classification have made efforts to improve supraventricular ectopic beat (SVEB) detection, but resulted in a low positive predictive value (PPV) of SVEB and poor performance of other categories under the interpatient paradigm. This article proposes a novel algorithm for heartbeat classification by the means of deep learning combined with feature extraction, which enhances the performance and can be applied to an automatic electrocardiogram (ECG) analysis. It is an improved residual attention network (IraNet) that combines attention module, residual inception block, and bidirectional long short-term memory (BiLSTM) layer to process single heartbeat segments directly. A two-phase training method is presented to change the weights in a planned way to deal with the imbalance of distinguishable features. An assistant decision for the deep learning-based model enhances the PPV of SVEB effectively. Under the interpatient paradigm on the Massachusetts Institute of Technology and Beth Israel Hosipital (MIT-BIH) arrhythmia database, the overall accuracy (Acc) of four classes achieves 0.9548. For SVEB class, the PPV is significantly improved to 0.7557 with the sensitivity (Sen) and an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula> score of 0.7392 and 0.7474, respectively. For ventricular ectopic beat (VEB) class, the Sen, PPV, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula> score achieve 0.9575, 0.8500, and 0.9005, respectively, and the numbers are 0.9663, 0.9873, and 0.9767 for normal beat class. For fusion beat class, the numbers are 0.7964, 0.3597, and 0.4954, respectively. The proposed algorithm gets competitive results with the state-of-the-art studies, and there is a notable improvement in the detection of SVEB

Computer-aided detection and diagnosis in ECG signals for heart diseases are gaining increasing attention. However, developing and selecting the highly performing diagnostic model suitable for clinical implications is still challenging. In this paper, we proposed a combined network of convolutional neural network (CNN) and Recurrent Neural Network (RNN), designed for the classification of ECG heart signals for diagnostic purpose. The proposed network consists of 2 convolutional layers with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$5\times 5$ </tex-math></inline-formula> kernels and ReLU activations, followed by 4 residual blocks, 2 bidirectional long short-term memory (biLSTM) layers, as well as 2 fully connected layers. Each residual block involved the structure of a Squeeze-and-Excitation Network (SENet) with lightweight property to recalibrate the feature map of the network. The last dense layer has 5 outputs, equivalent to the classes considered: non-ectopic beats, supraventricular ectopic beats, ventricular ectopic beats, fusion beats, and unknown beats. To train and evaluate the combined CNN and RNN, we transferred the knowledge acquired on beat classification tasks in 2017 PhysioNet/CinC Challenge to that in PhysionNet’s MIT-BIH dataset. The developed network achieved a recognition sensitivity of 95.90%, accuracy = 95.90% and specificity = 96.34% with classification time of single sample = 6.23 s in detecting 5 ECG classes. A comparative analysis proved the high performance of the proposed combined CNN and RNN against previous methods, demonstrating the potential of our proposed network in the analysis of beat patterns. The proposed model can be applied in cloud computing or implemented in mobile devices to evaluate cardiac health with the highest precision.

Convolutional Neural Networks (CNNs) have become a dominant solution for Electrocardiogram (ECG) beat classification, owing to their superior feature extraction capabilities. However, traditional CNN-based accelerators often encounter limitations such as large parameter counts, limited configurability, and inefficient hardware utilization. In this work, we propose a lightweight one-dimensional CNN (1D-CNN) inspired by the InceptionNet architecture, specifically designed for efficient and accurate ECG beat classification. The model integrates customized Inception blocks with parallel convolutional layers of varying kernel sizes to capture multi-scale temporal features. To reduce model complexity and enhance efficiency, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$1 \times 1$</tex> convolutions are used for dimensionality reduction, resulting in a compact network with only 7,740 parameters. Additionally, we present a hardware accelerator that exploits spatial data reuse across multiple processing units and employs dual-port RAM for concurrent data access, improving throughput and memory efficiency. When implemented on hardware with parallel and pipelined execution at 100 MHz, the system achieves a classification accuracy of 99.32%, sensitivity of 98.50%, specificity of 99.58%, and a positive predictive value (PPV) of 98.30% across five ECG classes with the MIT-BIH database, demonstrating its suitability for real-time deployment in resource-constrained environments.

In this paper, we present a new system for the classification of electrocardiogram (ECG) beats by using a fast least square support vector machine (LSSVM). Five feature extraction methods are comparatively examined in the 15-dimensional feature space. The dimension of the each feature set is reduced by using dynamic programming based on divergence analysis. After the preprocessing of ECG data, six types of ECG beats obtained from the MIT-BIH database are classified with an accuracy of 95.2% by the proposed fast LSSVM algorithm together with discrete cosine transform. Experimental results show that not only the fast LSSVM is faster than the standard LSSVM algorithm, but also it gives better classification performance than the standard backpropagation multilayer perceptron network.

This study evaluates four databases from PhysioNet: The American Heart Association database (AHADB), Creighton University Ventricular Tachyarrhythmia database (CUDB), MIT-BIH Arrhythmia database (MITDB), and MIT-BIH Noise Stress Test database (NSTDB). The ANSI/AAMI EC57:2012 is used for the evaluation of the algorithms for the supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), atrial fibrillation (AF), and ventricular fibrillation (VF) via the evaluation of the sensitivity, positive predictivity and false positive rate. Sample entropy, fast Fourier transform (FFT), and multilayer perceptron neural network with backpropagation training algorithm are selected for the integrated detection algorithms. For this study, the result for SVEB has some improvements compared to a previous study that also utilized ANSI/AAMI EC57. In further, VEB sensitivity and positive predictivity gross evaluations have greater than 80%, except for the positive predictivity of the NSTDB database. For AF gross evaluation of MITDB database, the results show very good classification, excluding the episode sensitivity. In advanced, for VF gross evaluation, the episode sensitivity and positive predictivity for the AHADB, MITDB, and CUDB, have greater than 80%, except for MITDB episode positive predictivity, which is 75%. The achieved results show that the proposed integrated SVEB, VEB, AF, and VF detection algorithm has an accurate classification according to ANSI/AAMI EC57:2012. In conclusion, the proposed integrated detection algorithm can achieve good accuracy in comparison with other previous studies. Furthermore, more advanced algorithms and hardware devices should be performed in future for arrhythmia detection and evaluation.

The Rhythms of Aging: What New Do We Know from Holter Monitoring?

An electrocardiogram (ECG) records the electrical activity of the heart; it contains rich pathological information on cardiovascular diseases, such as arrhythmia. However, it is difficult to visually analyze ECG signals due to their complexity and nonlinearity. The wavelet scattering transform can generate translation-invariant and deformation-stable representations of ECG signals through cascades of wavelet convolutions with nonlinear modulus and averaging operators. We proposed a novel approach using wavelet scattering transform to automatically classify four categories of arrhythmia ECG heartbeats, namely, nonectopic (N), supraventricular ectopic (S), ventricular ectopic (V), and fusion (F) beats. In this study, the wavelet scattering transform extracted 8 time windows from each ECG heartbeat. Two dimensionality reduction methods, principal component analysis (PCA) and time window selection, were applied on the 8 time windows. These processed features were fed to the neural network (NN), probabilistic neural network (PNN), and k-nearest neighbour (KNN) classifiers for classification. The 4th time window in combination with KNN (k = 4) has achieved the optimal performance with an averaged accuracy, positive predictive value, sensitivity, and specificity of 99.3%, 99.6%, 99.5%, and 98.8%, respectively, using tenfold cross-validation. Thus, our proposed model is capable of highly accurate arrhythmia classification and will provide assistance to physicians in ECG interpretation.

According to the World Health Organization, cardiovascular diseases (CVD) are the main cause of death worldwide. An estimated 17.5 million people died from CVD in 2012, representing 31% of all global deaths. The electrocardiogram (ECG) is a central tool for the pre-diagnosis of heart diseases. Many advances on ECG arrhythmia classification have been developed in the last century; however, there is still research to identify malignant waveforms on ECG beats. The premature ventricular complexes (PVC) are known to be associated with malignant ventricular arrhythmias and in sudden cardiac death (SCD) cases. Detecting this kind of arrhythmia has been crucial in clinical applications. In this work, we extracted 80 different features from 108,653 ECG classified beats of the MIT-BIH database in order to classify the Normal, PVC and other kind of ECG beats. We evaluated three classifier algorithms based on Machine Learning with different parameters and we got a total of 14 models. We used the F1 score and we compared predictive values as a measured of classifier evaluations. Results show that we could have a F1 scores near to the unit, showing the models are higher than 93% of performance.

This paper presents a resource-saving system to extract a few important features of electrocardiogram (ECG) signals. In addition, real-time classifiers are proposed as well to classify different types of arrhythmias via these features. The proposed feature extraction system is based on two delta-sigma modulators adopting 250Hz sampling rate and three wave detection algorithms to analyze outputs of the modulators. It extracts essential details of each heartbeat, and the details are encoded into 68 bits data that is only 1.48% of the other comparable methods. To evaluate our classification, we use a novel patient-specific training protocol in conjunction with the MIT-BIH database and the recommendation of the AAMI to train the classifiers. The classifiers are random forests that are designed to recognize two major types of arrhythmias. They are supraventricular ectopic beats (SVEB) and ventricular ectopic beats (VEB). The performance of the arrhythmia classification reaches to the F1 scores of 81.05% for SVEB and 97.07% for VEB, which are also comparable to the state-of-the-art methods. The method provides a reliable and accurate approach to analyze ECG signals. Additionally, it also possesses time-efficient, low-complexity, and low-memory-usage advantages. Benefiting from these advantages, the method can be applied to practical ECG applications, especially wearable healthcare devices and implanted medical devices, for wave detection and arrhythmia classification.

Funding Acknowledgements Type of funding sources: None. Introduction Heart involvement in systemic sclerosis patients is frequent and represents a negative prognostic factor with around 25% of SSc patients dying from cardiovascular related causes. Cardiac arrhythmias represent 6% of the overall causes of death in SSc patients. Not only a plethora of conditions typical of the disease seem to favour the presence of an arrhythmic substrate such as microvascular disease or fibrosis but autoimmunity itself has been recognized as a pathogenic mechanism for cardiac arrhythmias. Purpose The aim of our study was to investigate the incidence of arrhythmias in patients with systemic sclerosis and identify potential predictors. Methods Prospective longitudinal study enrolling all consecutive patients with a diagnosis of SSc and no overt cardiac disease nor pulmonary hypertension. Echocardiographic parameters and GLS were obtained at baseline and at each follow up as well as 12 lead ECG. Presence of atrial fibrillation (AF), atrial tachycardia (AT), ventricular ectopic beats &amp;gt;1000/24 h (VEB), supraventricular ectopic beats (SVEB), bundle branch block (BBB) and atrioventricular block (AVB) was registered. Results 160 patients (144 females, 90%, mean age 59±14 years) were enrolled from June 2016 to December 2021. At enrolment, 11.3% of patients with SSc presented a previous history of supraventricular arrhythmia (5.6% supraventricular ectopic beats, 3.1% atrial fibrillation, 2.5% atrial flutter) and 5.6% a history of ventricular arrhythmia (5.0% ventricular ectopic beats, 0.6% ventricular tachycardia). After a median follow-up of 3.1 years (95% CI 1.4-4.8 years), five patients (3.1%) died of cardiovascular causes, of which three (1.8%) experienced a sudden cardiac death. During the same period, 16 patients (10%) presented a new diagnosis of supraventricular arrythmia (8.7% atrial fibrillation, 1.3% atrial flutter) and two patients (1.2%) a new diagnosis of ventricular tachycardia. PR interval significantly increased during the 3.1-year follow-up (154±27 vs. 178±32 ms; p=0.013), as well as corrected QT interval (420±23 vs. 436±19 ms; p=0.001). New diagnosis of complete right and left bundle branch block was made in 18 (11.2%) and two (1.2%) of all SSc patients. Diagnosis of pulmonary arterial hypertension was associated with a 4-fold and a 10-fold increased risk of supraventricular and ventricular arrhythmias, respectively (Figure 1). A diffuse SSc variant (p=0.049), indexed right (p=0.020) and left atrial volumes (p=0.035), and E/E’ ratios (p=0.016) were all associated with an increased risk of supraventricular arrhythmias. TAPSE (p=0.040), as well as right (p=0.030) global longitudinal strain were associated with an increased risk of ventricular arrhythmias. Conclusions Ssc patients are often by an arrhythmic profile with an increased risk of supraventricular and ventricular events as well as sudden cardiac death. A comprehensive cardiological work up may help in lowering the risk of arrhythmic complications.

The heart is one of the crucial parts of the human being. The graphical recording of the cardiac cycle produced by an Electrocardiograph is called an Electrocardiogram (ECG) signal. To predict the occurrence of an arrhythmia, an electrocardiogram (ECG) is generally used by doctors to identify the condition of the patient. Hence, to accurately detect the abnormalities of the heart in advance and classify those diseases without human involvement many machine learning algorithms are used. The MIT-BIH Arrhythmia database is being used to classify the beat classification performance. This paper presents the hardware implementation of a classifier using an Artificial Neural Network (ANN) to classify four abnormalities (Normal beat, Supraventricular ectopic beat, Ventricular ectopic beat, Fusion beat) of heartbeat with high accuracy. To an appropriate input vector for the classifier, several preprocessing stages have been applied. Discrete Wavelet Transform (DWT) is used to extract the features from the ECG signal. To implement this work, Xilinx Artix-7 NESYS 4 DDR FPGA board is used. This model got 86% testing accuracy in simulation and 85.6% in hardware.

Objective. The arrhythmia identification method based on the U-net has the potential for fast application. The RR-intervals have been proven to improve the performance of single-heartbeat identification methods. However, because both the heartbeats number and location in the input of the U-net are unfixed, the approach based on the U-net cannot use RR-intervals directly. To solve this problem, we proposed a novel method. The proposed method also can identify heartbeats of four classes, including non-ectopic (N), supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), and fusion beat (F). Approach. Our method consists of the pre-processing and the two-stage identification framework. In the pre-processing part, we filtered input signals with a band-pass filter and created the auxiliary waveforms by RR-intervals. In the first stage of the framework, we designed a network to handle input signals and auxiliary waveforms. We proposed a masking operation to separate the input signal into two signals according to the result of the network. The first signal contains heartbeats of SVEB and VEB. The second signal includes heartbeats of N and F. The second stage consists of two networks and can further identify the heartbeats of SVEB, VEB, N, and F from these two signals. Main result. We validated our method on the MIT-BIH arrhythmia database with the inter-patient model. For classes N, SVEB, VEB, and F, our approach achieved F1 scores of 98.26, 68.61, 95.99, and 47.75, respectively. Significance. Our method not only can effectively utilize RR intervals but also can identify multiple arrhythmias.

The diagnosis of electrocardiogram (ECG) is extremely onerous and inefficient, so it is necessary to use a computer-aided diagnosis of ECG signals. However, it is still a challenging problem to design high-accuracy ECG algorithms suitable for the medical field. In this paper, a classification method is proposed to classify ECG signals. Firstly, wavelet transform is used to denoise the original data, and data enhancement technology is used to overcome the problem of an unbalanced dataset. Secondly, an integrated convolutional neural network (CNN) and gated recurrent unit (GRU) classifier is proposed. The proposed network consists of a convolution layer, followed by 6 local feature extraction modules (LFEM), a GRU, and a Dense layer and a Softmax layer. Finally, the processed data were input into the CNN-GRU network into five categories: nonectopic beats, supraventricular ectopic beats, ventricular ectopic beats, fusion beats, and unknown beats. The MIT-BIH arrhythmia database was used to evaluate the approach, and the average sensitivity, accuracy, and F1-score of the network for 5 types of ECG were 99.33%, 99.61%, and 99.42%. The evaluation criteria of the proposed method are superior to other state-of-the-art methods, and this model can be applied to wearable devices to achieve high-precision monitoring of ECG.

Цель – определить частоту отдельных видов аритмий и нарушений проводимости сердца в российской популяции больных системной склеродермией (ССД) по данным стандартной и суточной электрокардиографии (ЭКГ) и оценить корреляции этих изменений с клиническими параметрами заболевания. Материал и методы. В исследование были включены 80 больных ССД и 60 сопоставимых с ними по полу и возрасту условно здоровых лиц, составивших контрольную группу. Всем участникам исследования проводили стандартную ЭКГ в покое и суточное холтеровское мониторирование (ХМ) ЭКГ. Результаты. При стандартной ЭКГ у больных ССД нарушения ритма определялись в 14 (17,5%) случаях, в том числе синусовая аритмия – у 2 больных и экстрасистолия – у 13 (16%). Частота наджелудочковой и желудочковой экстрасистолии составила 5 (6%) и 7 (9%) случаев соответственно; в 1 наблюдении отмечалось сочетание наджелудочковых и желудочковых экстрасистол. У 9 (11%) больных ССД выявлялись ЭКГ-признаки очагового фиброза миокарда различной локализации. ХМ ЭКГ показало высокую частоту наджелудочковых и желудочковых экстрасистол, которые выявлялись у 40 и 65% больных ССД соответственно. Частота и выраженность аритмий сердца у больных ССД была достоверно больше, чем в контрольной группе. У 36% больных отмечаются потенциально опасные в отношении раз- вития злокачественной аритмии и внезапной сердечной смерти желудочковые экстрасистолы высокой градации. Заключение. Нарушения ритма и проводимости сердца развиваются у большинства больных ССД. Стандартная ЭКГ не отражает истинную частоту аритмий сердца у больных ССД. Суточное ХМ ЭКГ является обязательным методом обследования больных ССД и контроля эффективности лечения.