Optimized Cardiovascular Disease Detection and Features Extraction Algorithms from ECG Data

By using computer-aided arrhythmia diagnosis tools, electrocardiogram (ECG) signal plays a vital role in lowering the fatality rate associated with cardiovascular diseases (CVDs) and providing information about the patient’s cardiac health to the specialist. Current advancements in deep-learning-based multivariate time series data analysis, such as ECG data classification include LSTM, Bi-LSTM, CNN, with Bi-LSTM, and other sequential networks. However, these networks often struggle to accurately determine the long-range dependencies among data instances, which can result in problems such as vanishing or exploding gradients for longer data sequences. To address these shortcomings of sequential models, a hybrid arrhythmia classification system using recurrence along with a self-attention mechanism is developed. This system utilizes convolutional layers as a part of representation learning, designed to capture the salient features of raw ECG data. Then, the latent embedded layer is fed to a self-attention-assisted transformer encoder model. Because the ECG data are highly influenced by absolute order, position, and proximity of time steps due to interdependent relationships among immediate neighbors, a component of recurrence using Bi-LSTM is added to the encoder model to address this characteristic of the data. The model performance indices such as classification accuracy and F1-score were found to be 99.2%. This indicates that the combination of recurrence along with self-attention-assisted architecture produces improved classification of arrhythmia from raw ECG signal when compared with the state-of-the-art models.

Electrocardiogram (ECG) signals consist of data containing measurements of electrical activity in the heartbeats. These signals include relevant information used to detect abnormalities such as arrhythmia. In this study, a recognition system is proposed for detection and classification of heartbeats in ECG signals. Heartbeats in the ECG data were detected by using the wavelet transform (WT) method and these beats are segmented with determined periods. For obtaining distinctive features from the beats, multi-resolution WT is applied to these segmented signals, and wavelet coefficients are obtained from different frequency levels. Feature vectors are generated on these coefficients by using various statistical methods. The proposed recognition system is trained on feature vectors by using the Online Sequential Extreme Learning Machine (OSELM) classifier during the learning phase to automatically recognize the signals. Five different beat types were obtained from the MIT-BIH arrhythmia dataset. The multi-class dataset that includes five classes and the binary-class dataset that includes two classes were created among these beat types. Performance tests of the proposed wavelet-based-OSELM (W-OSELM) method were realized with these two datasets. The proposed recognition system provided 97.29% correct beat detection rate from raw ECG signals. The classification accuracy is 99.44% for the binary-class dataset and 98.51% for the multi-class dataset. Furthermore, the proposed classifier has shown very fast recognition performance on ECG signals.

Electrocardiogram (ECG) signal quality indices (SQIs) are essential for improving diagnostic accuracy and reliability of ECG analysis systems. In various practical applications, the ECG signals are corrupted by different types of noise. These corrupted ECG signals often provide insufficient and incorrect information regarding a patient’s health. To solve this problem, signal quality measurements should be made before an ECG signal is used for decision-making. This paper investigates the robustness of existing popular statistical signal quality indices (SSQIs): relative power of QRS complex (SQIp), skewness (SQIskew), signal-to-noise ratio (SQIsnr), higher order statistics SQI (SQIhos) and peakedness of kurtosis (SQIkur). We analysed the robustness of these SSQIs against different window sizes across diverse datasets. Results showed that the performance of SSQIs considerably fluctuates against varying datasets, whereas the impact of varying window sizes was minimal. This fluctuation occurred due to the use of a static threshold value for classifying noise-free ECG signals from the raw ECG signals. Another drawback of these SSQIs is the bias towards noise-free ECG signals, that limits their usefulness in clinical settings. In summary, the fixed threshold-based SSQIs cannot be used as a robust noise detection system. In order to solve this fixed threshold problem, other techniques can be developed using adaptive thresholds and machine-learning mechanisms.

This paper presents a novel maximum margin clustering method with immune evolution (IEMMC) for automatic diagnosis of electrocardiogram (ECG) arrhythmias. This diagnostic system consists of signal processing, feature extraction, and the IEMMC algorithm for clustering of ECG arrhythmias. First, raw ECG signal is processed by an adaptive ECG filter based on wavelet transforms, and waveform of the ECG signal is detected; then, features are extracted from ECG signal to cluster different types of arrhythmias by the IEMMC algorithm. Three types of performance evaluation indicators are used to assess the effect of the IEMMC method for ECG arrhythmias, such as sensitivity, specificity, and accuracy. Compared with K-means and iterSVR algorithms, the IEMMC algorithm reflects better performance not only in clustering result but also in terms of global search ability and convergence ability, which proves its effectiveness for the detection of ECG arrhythmias.

Cardiac arrhythmia, one of the primary causes of death, can be diagnosed using the electrocardiogram (ECG), a visual representation of heart activity. Existing methods can annotate ECG signals and achieve satisfactory results. However, they usually require prepossessing the ECG signals by extracting individual heartbeats before being fed into the recognition model. Then, the data is typically processed as a one-dimensional signal that leads to the loss of information. In this context, we propose a Transformer-based Spatial-Temporal Conv-Transformer (STCT) Network that deals with raw ECG data. The STCT considers the raw ECG signal as two-dimensional features by utilising the spatial and temporal information for more accurate identification of irregular heartbeat. Additionally, the model identifies parts of the feature space that are especially relevant and filters out the remainder, ensuring that STCT performance can be enhanced. To demonstrate the effectiveness and efficiency of the proposed method, four separate open ECG datasets, MIT-BIH, EDB, AHA, and NST, were used for the benchmarking. Ultimately, this method achieved 98.96%, 99.29%, 99.88% and 99.13% of accuracy and outperformed the state-of-art methods when compared.KeywordsECGDeep learningRNNCardiac arrhythmia

This paper discusses the circuit comparison of the electrocardiogram (ECG) heart rate detector for wearable biomedical devices. In this work, the QRS complex is used to calculate heart rate, representing the main component of the ECG signal. In order to achieve a high level of accuracy by the detector, the measured ECG signal must be free of noise. Typically, such noise originates from power line interferences and baseline wandering. To eliminate these noises, the ECG signal must be processed using the signal processing method. The ECG detection process can be divided into a preprocessing stage, which eliminates noise from the raw ECG signal, and the feature extraction stage, which extracts the QRS complex for heart rate calculation. Based on our analysis, the trade-off between complexity and accuracy in ECG signal architecture is important when designing a high-efficiency system.

Millions of people around the world are affected by arrhythmias, which are abnormal activities of the functioning of the heart. Most arrhythmias are harmful to the heart and can suddenly become life-threatening. The electrocardiogram (ECG) is an important non-invasive tool in cardiology for the diagnosis of arrhythmias. This work proposes a computer-aided diagnosis (CAD) system to automatically classify different types of arrhythmias from ECG signals. First, the auto-encoder convolutional network (ACN) model is used, which is based on a one-dimensional convolutional neural network (1D-CNN)that automatically learns the best features from the raw ECG signals. After that, the support vector machine (SVM) classifier is applied to the features learned by the ACN model to improve the detection of arrhythmic beats. This classifier detects four different types of arrhythmias, namely the left bundle branch block (LBBB), right bundle branch block (RBBB), paced beat (PB), and premature ventricular contractions (PVC), along with the normal sinus rhythms (NSR). Among these arrhythmias, PVC is particularly a dangerous type of heartbeat in ECG signals. The performance of the model is measured in terms of accuracy, sensitivity, and precision using a tenfold cross-validation strategy on the MIT-BIH arrhythmia database. The obtained overall accuracy of the SVM classifier was 98.84%. The result of this model is portrayed as a better performance than in other literary works. Thus, this approach may also help in further clinical studies of cardiac cases.

A novel P-QRS-T wave localization method in ECG signals based on hybrid neural networks

Electrocardiogram (ECG)-based arrhythmia classification is vital for the early detection and diagnosis of heart diseases. However, raw ECG signals are often noisy, which poses challenges for accurate classification. In this paper, we propose a novel approach that integrates discrete wavelet transform (DWT) for signal denoising with an Attention-Enhanced Convolutional Neural Network-Bidirectional Gated Recurrent Unit (CNN-BiGRU) model for arrhythmia classification. Initially, DWT is applied to the ECG signal to remove noise while preserving important features. To address class imbalance, Borderline-SMOTE is employed to generate synthetic samples for the minority classes. The denoised and balanced signals are then processed through a CNN for feature extraction, followed by a BiGRU to capture temporal dependencies. By incorporating an attention mechanism, the model is able to concentrate on the most critical regions of the ECG signal. The proposed method is evaluated on the MIT-BIH arrhythmia database, achieving an accuracy of 99.22% in classifying five types of arrhythmias, outperforming previous models. This approach provides a promising solution for automatic arrhythmia detection in clinical practice.

Cardiac arrhythmias are significant contributors to global mortality, necessitating precise and timely diagnosis based on electrocardiogram (ECG) signals. This paper introduces an advanced diagnostic system utilizing a deep 1D Convolutional Neural Network (CNN) architecture integrated with the Horse Herd Optimization Algorithm (HOA) for automated feature extraction and classification. The primary objective is to overcome the limitations of manual hyperparameter tuning by using the HOA metaheuristic search capability to optimally tune critical parameters, specifically the Learning Rate and Batch Size. In the proposed framework, raw ECG signals from the standard MIT-BIH Arrhythmia Database are first preprocessed using the discrete wavelet transform with the "db6" mother wavelet to effectively suppress nonstationary noise and baseline wander. The denoised signals are then processed through a sequence of four convolutional blocks, featuring batch normalization and max-pooling, to extract hierarchical morphological features. Experimental results using 5-fold cross-validation demonstrate that the proposed CNN-HOA model achieves a state-of-the-art accuracy of 99.8%, with 99.9% sensitivity and specificity across five Association for the Advancement of Medical Instrumentation beat types: normal (N), supraventricular (S), ventricular (V), fusion (F), and unknown (Q). This study validates that the synergistic integration of modern swarm intelligence algorithms with deep learning provides a robust and highly efficient solution for high-precision medical signal processing and clinical-grade automated diagnosis. Received: 23 October 2025 | Revised: 20 December 2025 | Accepted: 11 February 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The ECG data used to support the findings of this study are available from the MIT-BIH Arrhythmia Database, which is publicly accessible via Figshare at https://doi.org/10.6084/m9.figshare. 845654. Author Contribution Statement Sajjad Mohammed Abdulkareem: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft, Writing – review & editing, Visualization. Seyed Enayatallah Alavi: Conceptualization, Methodology, Resources, Writing – review & editing, Supervision, Project administration.

Continuous blood pressure (BP) monitoring can produce a significant amount of digital data, which increases the chance of early diagnosis and improve the rate of survival for people diagnosed with hypertension and Cardiovascular diseases (CVDs). However, mining and processing this vast amount of data are challenging. This research is aimed to address this challenge by proposing a deep learning technique, convolutional neural network (CNN), to estimate the systolic blood pressure (SBP) using electrocardiogram (ECG) and photoplethysmography (PPG) signals. Two different methods are investigated and compared in this research. In the first method, continuous wavelet transform (CWT) and CNN have been employed to estimate the SBP. For the second method, we used random sampling within the stochastic gradient descent (SGD) optimization of CNN and the raw ECG and PPG signals for training the network. The Medical Information Mart for Intensive Care (MIMIC III) database is used for both methods, which split to two parts, 70% for training our network and the remaining used for testing the performance of the network. Both methods are capable of learning how to extract relevant features from the signals. Therefore, there is no need for engineered feature extraction compared to previous works. Our experimental results show high accuracy for both CNN-based methods which make them promising and reliable architectures for SBP estimation.

Electrocardiogram (ECG) signals are significantly distorted during recording by muscle artifact (MA), causing signal frequency overlap and making it difficult to interpret ECG data correctly. Deep learning (DL) methods for signal processing have shown promising results. However, there is a significant necessity in building proper DL models with appropriate datasets. We propose an enhanced hybrid deep learning framework called HRGB-Net based on residual neural network (ResNet), global channel attention block (GCAB), and bidirectional-long-short-term memory (Bi-LSTM) blocks for filtering the MA noise from ECG by using three distinctive MIT-BIH real-time datasets from the PhysioNet repository by creating suitable datasets for training. We use both raw ECG data and short-time Fourier-transformed (STFT) ECG data for comparative analysis with three neural network models: a convolutional neural Network (CNN), a fully connected neural network (FCNN), and a regression-based LSTM (Reg-LSTM-DNN) model to assess the proposed model. The signal-to-noise ratio (SNR) of noisy ECG signals is varied from - 7dB to 2dB to analyze the mean square error (MSE) and correlation coefficient (CC) performances after the denoising process. Our proposed method utilizes the regression ability to remove MA noise and generate a clean ECG signal with improved values of these signal parameters. The STFT-trained and tested ECG data shows better results than the raw ECG data for efficiently eliminating the MA with a 98.82% correlation coefficient and optimal MSE value of 0.053068. The results prove our proposed HRGB-Net model's remarkable ability to outperform the neural network models and other standard techniques.

Heart disease is still a heavy hitter on the list of leading causes of death around the globe, so getting ahead of the game with early and accurate predictions is crucial for effective treatment. Traditional diagnostic systems often put all their eggs in one basket, relying solely on clinical data or electrocardiogram (ECG) signals. This one-track approach can really throw a wrench in the works, limiting their predictive power. To tackle this head-on, we suggest a Hybrid Deep Learning Framework for Heart Disease Prediction Using Multi-Modal Clinical and ECG Data, which weaves together cutting-edge neural architectures, attention mechanisms, and ensemble strategies to boost performance and clarity.The framework gets the ball rolling by preprocessing UCI Cleveland clinical features with a bit of normalization and encoding, while ECG signals are put through the wringer with noise removal, segmentation, and scaling. Clinical data are shaped using machine learning classifiers and ANN, while ECG features are pulled together with CNN, BiLSTM, and Transformer layers to snag local, temporal, and contextual insights. A Graph Neural Network (GNN) weaves together the threads of clinical and ECG features, while a cross-attention fusion module dances to the rhythm of dynamically aligning and prioritizing the key features from both modalities. Predictions are cooked up using a stacked ensemble classifier, and model interpretability is kept in the clear through SHAP values, attention heatmaps, and graph attention visualization.The experimental evaluation reveals that the proposed method takes the cake, leaving the baseline models in the dust. Our framework hit the nail on the head with a whopping 94.8% accuracy, 93.5% precision, 95.1% recall, and 94.3% F1-score, leaving traditional machine learning in the dust at a mere 86.5%, and unimodal deep learning methods like CNN-BiLSTM and Transformer trailing behind at 89.7% and 90.4%, respectively. Talk about raising the bar!To wrap it all up, the suggested hybrid method hits the nail on the head by blending structured clinical data with ECG signals, providing top-notch predictive accuracy and clarity that’s second to none. This positions it as a strong contender for practical clinical decision support and the early detection of cardiovascular disease. Keywords: Heart Disease Prediction, Hybrid Deep Learning, Multi-Modal Fusion, ECG Signals, Cross-Attention, Graph Neural Network, Explainable AI,

Applications based on electrocardiogram (ECG) signal feature extraction and classification are of major importance to the autodiagnosis of heart diseases. Most studies on ECG classification methods have targeted only 1- or 2-lead ECG signals. This limitation results from the unavailability of real clinical 12-lead ECG data, which would help train the classification models. In this study, we propose a new tensor-based scheme, which is motivated by the lack of effective feature extraction methods for direct tensor data input. In this scheme, an ECG signal is represented by third-order tensors in the spatial-spectral-temporal domain after using short-time Fourier transform on the raw ECG data. To overcome the limitations of tensor rank one discriminant analysis (TR1DA) inherited from linear discriminant analysis, we introduced a generalized tensor rank one discriminant analysis (GTR1DA). This approach involves considering the distribution of the data points near the classification boundary to calculate better projection tensors. The experimental results showed that the proposed method achieves greater classification accuracy than other vector- and tensor-based methods. Finally, GTR1DA features a better convergence property than the original TR1DA.

Research has been conducted to support an automatic diagnosis system that will relieve clinicians of their weary work by detecting epileptic seizures. In this paper, we suggest a novel method to automatically identify epilepsy crises based on electroencephalogram (EEG) and electrocardiogram (ECG) signals. The work to detect epileptic seizures from EEG and ECG signals is carried out in three stages. In the first stage, simultaneous EEG and ECG recordings captured from 24 channels are segmented into 10-second periods (where 23 are the EEG signals and one is the ECG signal). In the second stage, the extraction of the parameters of each channel from the time domain and, finally, the classification of the EEG and ECG signals into epileptic seizure and normal have been done using ANN. Experiment analysis shows that using the ECG signal as extra information has a high capacity for classification.