ECG arrhythmia classification using modified visual geometry group network (mVGGNet)

A novel method of swin transformer with time-frequency characteristics for ECG-based arrhythmia detection

Introduction

Arrhythmia is an important indication of underlying cardiovascular diseases (CVD) and is prevalent worldwide. Accurate diagnosis of arrhythmia is crucial for timely and effective treatment. Electrocardiogram (ECG) plays a key role in the diagnosis of arrhythmia. With the continuous development of deep learning and machine learning processes in the clinical field, ECG processing algorithms have significantly advanced the field with timely and accurate diagnosis of arrhythmia.

Methods

In this study, we combined the wavelet time-frequency maps with the novel Swin Transformer deep learning model for the automatic detection of cardiac arrhythmias. In specific practice, we used the MIT-BIH arrhythmia dataset, and to improve the signal quality, we removed the high-frequency noise, artifacts, electromyographic noise and respiratory motion effects in the ECG signals by the wavelet thresholding method; we used the complex Morlet wavelet for the feature extraction, and plotted wavelet time-frequency maps to visualise the time-frequency information of the ECG; we introduced the Swin Transformer model for classification and achieve high classification accuracy of ECG signals through hierarchical construction and self attention mechanism, and combines windowed multi-head self-attention (W-MSA) and shifted window-based multi-head self-attention (SW-MSA) to comprehensively utilise the local and global information.

Results

To enhance the confidence of the experimental results, we evaluated the performance using intra-patient and inter-patient paradigm analyses, and the model classification accuracies reached 99.34% and 98.37%, respectively, which are better than the currently available detection methods.

Discussion

The results reveal that our proposed method is superior to currently available methods for detecting arrhythmia ECG. This provides a new idea for ECG based arrhythmia diagnosis.

ECG-based data-driven solutions for diagnosis and prognosis of cardiovascular diseases: A systematic review

Cardiovascular diseases (CVD) are a leading cause of death globally, and result in significant morbidity and reduced quality of life. The electrocardiogram (ECG) plays a crucial role in CVD diagnosis, prognosis, and prevention; however, different challenges still remain, such as an increasing unmet demand for skilled cardiologists capable of accurately interpreting ECG. This leads to higher workload and potential diagnostic inaccuracies. Data-driven approaches, such as machine learning (ML) and deep learning (DL) have emerged to improve existing computer-assisted solutions and enhance physicians' ECG interpretation of the complex mechanisms underlying CVD. However, many ML and DL models used to detect ECG-based CVD suffer from a lack of explainability, bias, as well as ethical, legal, and societal implications (ELSI). Despite the critical importance of these Trustworthy Artificial Intelligence (AI) aspects, there is a lack of comprehensive literature reviews that examine the current trends in ECG-based solutions for CVD diagnosis or prognosis that use ML and DL models and address the Trustworthy AI requirements. This review aims to bridge this knowledge gap by providing a systematic review to undertake a holistic analysis across multiple dimensions of these data-driven models such as type of CVD addressed, dataset characteristics, data input modalities, ML and DL algorithms (with a focus on DL), and aspects of Trustworthy AI like explainability, bias and ethical considerations. Additionally, within the analyzed dimensions, various challenges are identified. To these, we provide concrete recommendations, equipping other researchers with valuable insights to understand the current state of the field comprehensively.

Evolutionary gravitational neocognitron neural network optimized with marine predators optimization algorithm for MRI brain tumor classification

Magnetic resonance imaging (MRI) is a powerful tool for tumor diagnosis in human brain. Here, the MRI images are considered to detect the brain tumor and classify the regions as meningioma, glioma, pituitary and normal types. Numerous existing methods regarding brain tumor detection were suggested previously, but none of the methods accurately categorizes the brain tumor and consumes more computation period. To address these problems, an Evolutionary Gravitational Neocognitron Neural Network optimized with Marine Predators Algorithm is proposed in this article for MRI Brain Tumor Classification (EGNNN-VGG16-MPA-MRI-BTC). Initially, the brain MRI pictures are collected under Brats MRI image dataset. By using Savitzky-Golay Denoising approach, these images are pre-processed. The features are extracted utilizing visual geometry group network (VGG16). By utilizing VGG16, the features, like Grey level features, Haralick Texture features are extracted. These extracted features are given to EGNNN classifier, which categorizes the brain tumor as glioma, meningioma, pituitary gland and normal. Batch Normalization (BN) layer of EGNNN is eliminated and included with VGG16 layer. Marine Predators Optimization Algorithm (MPA) optimizes the weight parameters of EGNNN. The simulation is activated in MATLAB. Finally, the EGNNN-VGG16-MPA-MRI-BTC method attains 38.98%, 46.74%, 23.27% higher accuracy, 24.24%, 37.82%, 13.92% higher precision, 26.94%, 47.04%, 38.94% higher sensitivity compared with the existing AlexNet-SVM-MRI-BTC, RESNET-SGD-MRI-BTC and MobileNet-V2-MRI-BTC models respectively.

WavelNet: A novel convolutional neural network architecture for arrhythmia classification from electrocardiograms

BACKGROUND AND OBJECTIVE

Automated detection of arrhythmias from electrocardiograms (ECGs) can be of considerable assistance to medical professionals in providing efficient treatment for patients with cardiovascular diseases. In recent times, convolutional neural network (CNN)-based arrhythmia classification models have been introduced, but their decision-making processes remain unclear and their performances are not reproducible. This paper proposes an accurate, interpretable, and reproducible end-to-end arrhythmia classification model based on a novel CNN architecture named WavelNet, which is interpretable and optimal for dealing with ECGs.

METHODS

Inspired by SincNet, which is capable of band-pass filtering-based spectral analysis, WavelNet was devised to achieve wavelet transform-based spectral analysis. WavelNet was trained using a subject-oriented five-class ECG arrhythmia dataset generated from the MIT-BIH Arrhythmia Database while following a benchmark scheme. By adopting various mother wavelets, multiple WavelNet-based arrhythmia classification models were implemented. To investigate whether our wavelet transform-based approach outperforms original end-to-end and band-pass filtering-based approaches, our proposed models were compared with vanilla CNN- and SincNet-based models. Model implementation and evaluation processes were repeated ten times in a Google Colab Pro+ environment. Furthermore, our most successful model was compared with state-of-the-art arrhythmia classification models for performance evaluation.

RESULTS

The proposed WavelNet-based models showed excellent performance on classifying non-ectopic, supraventricular ectopic, and ventricular ectopic beats because of their ability to perform adaptive spectral analysis while preserving temporal ECG information compared with vanilla CNN- and SincNet-based models. In particular, a Symlet 4 wavelet-adopting WavelNet-based model achieved the best performance with nearly 90% overall accuracy as well as the highest levels of sensitivity in classifying each arrhythmia class: 91.4%, 49.3%, and 91.4% for non-ectopic, supraventricular ectopic, and ventricular ectopic beat classifications, respectively. These results were comparable to those of state-of-the-art models. In addition, the results are reproducible, which differentiates our study from previous studies.

CONCLUSIONS

Our proposed WavelNet-based arrhythmia classification model achieved remarkable performance based on a reasonable decision-making process, in comparison with other models. As its noteworthy performance is clinically reasonable and reproducible, our proposed model can contribute toward implementing a real-world precision healthcare system for patients with cardiovascular diseases.

Deep Learning-Based Data Augmentation and Model Fusion for Automatic Arrhythmia Identification and Classification Algorithms

Automated ECG-based arrhythmia detection is critical for early cardiac disease prevention and diagnosis. Recently, deep learning algorithms have been widely applied for arrhythmia detection with great success. However, the lack of labeled ECG data and low classification accuracy can have a significant impact on the overall effectiveness of a classification algorithm. In order to better apply deep learning methods to arrhythmia classification, in this study, feature extraction and classification strategy based on generative adversarial network data augmentation and model fusion are proposed to address these problems. First, the arrhythmia sparse data is augmented by generative adversarial networks. Then, aiming at the identification of different types of arrhythmias in long-term ECG, a spatial information fusion model based on ResNet and a temporal information fusion model based on BiLSTM are proposed. The model effectively fuses the location information of the nearest neighbors through the local feature extraction part of the generated ECG feature map and obtains the correlation of the global features by autonomous learning in multiple spaces through the BiLSTM network in the part of the global feature extraction. In addition, an attention mechanism is introduced to enhance the features of arrhythmia-type signal segments, and this mechanism can effectively focus on the extraction of key information to form a feature vector for final classification. Finally, it is validated by the enhanced MIT-BIH arrhythmia database. The experimental results demonstrate that the proposed classification technique enhances arrhythmia diagnostic accuracy by 99.4%, and the algorithm has high recognition performance and clinical value.

A deep dynamic neural network model and its application for ECG classification

The electrocardiogram (ECG) signal is a kind of time-varying signal, which has the characteristics and difficulties of variability, instability, and noise. Aiming at that, this paper put forward a novel 13-layer deep dynamic neural network model (DDNN) for the ECG signal learning and classification. The proposed DDNN model is a dynamic hybrid deep learning model. It includes a wavelet block, a convolutional block, a recurrent block, and a classification block, which combines the learning property and classification mechanism of convolutional neural network for the large-scale data sets, the learning and memory ability of Long Short-Term Memory (LSTM) for time series, and the noise reduction and processing ability of wavelet basis for the signals to meet the requirement of the learning and classification of ECG signal characteristics. Sufficient experimental results show that the proposed model is feasible and effective in the electrocardiogram signal pattern classification.

Classification of arrhythmia’s ECG signal using cascade transparent classifier

Arrhythmia is an abnormality often encountered in patients with cardiac problems. The presence of arrhythmia can be detected by an electrocardiogram (ECG) test. Automatic observation based on machine learning has been developed for long time. Unfortunately, only few of them have capability of explaining the knowledge inside themselves. Thus, transparency is important to improve human understanding of knowledge. To achieve this goal, a method based on cascaded transparent classifier is proposed. Firstly, ECG signals were separated and every single signal was extracted using feature extraction method. Several of extracted feature’s attributes were selected, and the final step was classifying data using cascade classifier which consists of decision tree and the rule based classifier. Classification performance was evaluated with publicly available dataset, the MIT-BIH Physionet Dataset. The methods were tested using 10-fold cross validation. The average of both accuracy and number of rules generated was considered. The best result using rule-based classifier achieves the accuracy and the number of rules 92.40% and 40, respectively. And the best result using cascade classifier achieves the accuracy and the number of rules 92.84% and 80, respectively. As a conclusion, transparent classifier shows a competitive performance with reasonable accuracy compared with previous research and promising in addressing the need for interpretability model.

Application of Internet of Things on the Healthcare Field Using Convolutional Neural Network Processing

Population at risk can benefit greatly from remote health monitoring because it allows for early detection and treatment. Because of recent advances in Internet-of-Things (IoT) paradigms, such monitoring systems are now available everywhere. Due to the essential nature of the patients being monitored, these systems demand a high level of quality in aspects such as availability and accuracy. In health applications, where a lot of data are accessible, deep learning algorithms have the potential to perform well. In this paper, we develop a deep learning architecture called the convolutional neural network (CNN), which we examine in this study to see if it can be implemented. The study uses the IoT system with a centralised cloud server, where it is considered as an ideal input data acquisition module. The study uses cloud computing resources by distributing CNN operations to the servers with outsourced fitness functions to be performed at the edge. The results of the simulation show that the proposed method achieves a higher rate of classifying the input instances from the data acquisition tools than other methods. From the results, it is seen that the proposed CNN achieves an average accurate rate of 99.6% on training datasets and 86.3% on testing datasets.

O-WCNN: an optimized integration of spatial and spectral feature map for arrhythmia classification

The regular monitoring and accurate diagnosis of arrhythmia are critically important, leading to a reduction in mortality rate due to cardiovascular diseases (CVD) such as heart stroke or cardiac arrest. This paper proposes a novel convolutional neural network (CNN) model for arrhythmia classification. The proposed model offers the following improvements compared with traditional CNN models. Firstly, the multi-channel model can concatenate spectral and spatial feature maps. Secondly, the structural unit is composed of a depthwise separable convolution layer followed by activation and batch normalization layers. The structural unit offers effective utilization of network parameters. Also, the optimization of hyperparameters is done using Hyperopt library, based on Sequential Model-Based Global Optimization algorithm (SMBO). These improvements make the network more efficient and accurate for arrhythmia classification. The proposed model is evaluated using tenfold cross-validation following both subject-oriented inter-patient and class-oriented intra-patient evaluation protocols. Our model achieved 99.48% and 99.46% accuracy in VEB (ventricular ectopic beat) and SVEB (supraventricular ectopic beat) class classification, respectively. The model is compared with state-of-the-art models and has shown significant performance improvement.

An IoT and Fog Computing-Based Monitoring System for Cardiovascular Patients with Automatic ECG Classification Using Deep Neural Networks

Telemedicine and all types of monitoring systems have proven to be a useful and low-cost tool with a high level of applicability in cardiology. The objective of this work is to present an IoT-based monitoring system for cardiovascular patients. The system sends the ECG signal to a Fog layer service by using the LoRa communication protocol. Also, it includes an AI algorithm based on deep learning for the detection of Atrial Fibrillation and other heart rhythms. The automatic detection of arrhythmias can be complementary to the diagnosis made by the physician, achieving a better clinical vision that improves therapeutic decision making. The performance of the proposed system is evaluated on a dataset of 8.528 short single-lead ECG records using two merge MobileNet networks that classify data with an accuracy of 90% for atrial fibrillation.