Enhancing Heart Disease Diagnosis Using ECG Signal Reconstruction and Deep Transfer Learning Classification with Optional SVM Integration.

A visually interpretable detection method combines 3-D ECG with a multi-VGG neural network for myocardial infarction identification

Effective and powerful methods for denoising real electrocardiogram (ECG) signals are important for wearable sensors and devices. Deep Learning (DL) models have been used extensively in image processing and other domains with great success but only very recently have been used in processing ECG signals. This paper presents several DL models namely Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Restricted Boltzmann Machine (RBM) together with the more conventional filtering methods (low pass filtering, high pass filtering, Notch filtering) and the standard wavelet-based technique for denoising EEG signals. These methods are trained, tested and evaluated on different synthetic and real ECG datasets taken from the MIT PhysioNet database and for different simulation conditions (i.e. various lengths of the ECG signals, single or multiple records). The results show the CNN model is a performant model that can be used for off-line denoising ECG applications where it is satisfactory to train on a clean part of an ECG signal from an ECG record, and then to test on the same ECG signal, which would have some high level of noise added to it. However, for real-time applications or near-real time applications, this task becomes more cumbersome, as the clean part of an ECG signal is very probable to be very limited in size. Therefore the solution put forth in this work is to train a CNN model on 1 second ECG noisy artificial multiple heartbeat data (i.e. ECG at effort), which was generated in a first instance based on few sequences of real signal heartbeat ECG data (i.e. ECG at rest). Afterwards it would be possible to use the trained CNN model in real life situations to denoise the ECG signal.

To develop and evaluate deep learning models for cardiac arrest rhythm classification during cardiopulmonary resuscitation (CPR), we analyzed 508 electrocardiogram (ECG) segments (each 4 s in duration, recorded at 250 Hz) from 131 cardiac arrest patients. Compression-affected segments were recorded during chest compressions, while non-compression segments were extracted during compression pauses or immediately after return of spontaneous circulation (ROSC) declaration. One-dimensional convolutional neural network (1D-CNN) and recurrent neural network (RNN) models were employed for four binary classification tasks: (1) shockable rhythms (VF and pVT) versus non-shockable rhythms (asystole and PEA) in all ECG segments; (2) the same classification in compression-affected ECG segments; (3) pulse-generating rhythms (ROSC rhythm) versus non-pulse-generating rhythms (asystole, PEA, VF and pVT) in all ECG segments; and (4) the same classification in compression-affected ECG segments. The 1D-CNN model consistently outperformed the RNN model across all classification tasks. For shockable versus non-shockable rhythm classification, the 1D-CNN achieved accuracies of 91.3% and 89.8% for all ECG segments and compression-affected ECG segments, respectively, compared to 50.6% and 54.5% for the RNN. In detecting pulse-generating rhythms, the 1D-CNN demonstrated accuracies of 90.9% and 85.7% for all ECG segments and compression-affected ECG segments, respectively, while the RNN achieved 92.2% and 84.4%. The 1D-CNN model demonstrated superior performance in cardiac arrest rhythm classification, maintaining high accuracy even with compression-affected ECG data.

The complexity of the patterns associated with atrial fibrillation (AF) and the high level of noise affecting these patterns have significantly limited the application of current signal processing and shallow machine learning approaches to accurately detect this condition. Deep neural networks have shown to be very powerful to learn the non-linear patterns in various problems such as computer vision tasks. While deep learning approaches have been utilized to learn complex patterns related to the presence of AF in electrocardiogram (ECG) signals, they can considerably benefit from knowing which parts of the signal is more important to focus on during learning. In this paper, we introduce a two-channel deep neural network to more accurately detect the presence of AF in the ECG signals. The first channel takes in an ECG signal and automatically learns where to attend for detection of AF. The second channel simultaneously takes in the same ECG signal to consider all features of the entire signal. Besides improving detection accuracy, this model can guide the physicians via visualization that what parts of the given ECG signal are important to attend while trying to detect atrial fibrillation. The experimental results confirm that the proposed model significantly improves the performance of AF detection on well-known MIT-BIH AF database with 5-s ECG segments (achieved a sensitivity of 99.53%, specificity of 99.26% and accuracy of 99.40%).

In the detection of arrhythmia using deep learning, most methods train neural networks to categorize input electrocardiogram (ECG) signals into typical arrhythmia signals using annotated training ECG data. Such methods can neither detect unknown arrhythmias nor explain why the signals are considered as arrhythmic. To detect arrhythmia automatically, this study proposes a method that learns normal ECG signals and can explain the assessment for the signals clearly. Our method builds a model of normal ECG signals using a convolutional neural network and long short-term memory. The model inputs normal ECG signals and performs training to predict the succeeding normal ECG signals. If an abnormal ECG signal is provided, the model predicts the succeeding ECG signal far from the actual ECG signal and can assess whether the input is abnormal. This means that our method can judge any arrhythmia because it requires no prior knowledge regarding the annotations. Experimental results confirm that the proposed method can detect arrhythmias appropriately without learning them. Furthermore, we propose a GUI that can display the location where abnormality is suspected to the user.

Background: Psychological stress contributes significantly to the global burden of mental health disorders, yet current diagnostic methods rely heavily on subjective reporting. Physiological biomarkers, particularly electrocardiogram (ECG) signals, offer promise for objective and scalable stress detection. Methods: We present EBAS-D (ECG-Based AI-enabled Stress Detector), a deep learning model that combines traditional ECG morphology (e.g., RR interval, QTc, QRS duration) with novel ventricular efficiency metrics (PFLVEF and VEI_Model2) and heart rate variability (HRV) analysis. Using data from the PhysioNet spider-fear stress dataset, we introduced a morphology-guided label refinement protocol to distinguish genuine no-stress states from post-stress recovery artifacts. A fully connected neural network was trained on 30-beat ECG segments using weighted binary cross-entropy loss to minimize false positives. Results: EBAS-D was evaluated on 31,466 ECG segments, achieving a specificity of 97.7%, positive predictive value of 99.2%, area under the ROC curve of 0.85, and odds ratio of 43.4 for stress classification. Sensitivity was 50.8% under a conservative decision threshold, prioritizing alarm minimization over recall. The model outperformed baseline classifiers and demonstrated significant differentiation between stress and neutral states (p < 0.0001). Conclusions: This study demonstrates the feasibility of high-specificity, ECG-based stress detection using deep learning and morphology-guided label correction. EBAS-D may augment clinical decision-making in emergency departments, psychiatric triage, or telemedicine, where objective stress assessment can support safe and appropriate care. Further validation across diverse populations and real-world settings is warranted to establish its clinical generalizability.

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,

Globally, cardiovascular disease kills more than 500000 people every year, thus becoming the primary reason for death. Nevertheless, cardiovascular health monitoring is essential for accurate analysis and therapy of heart disease. In this work, a novel deep learning-based StrIppeD NAS-Network (SID-NASNet) for arrhythmia categorization into octa-classes with electrocardiogram (ECG) signals is presented. First, the ECG signals are recorded in real time using 12-lead electrodes. Then, the Discrete Wavelet Transform (DWT) is used to denoise the signals to reduce repetition and increase resilience. The noise-free ECG signals are fed into a K-means clustering algorithm to group ECG signal segments into a set number of clusters to identify patterns that may indicate heart abnormalities. Subsequently, the deep learning-based NASNet with Stripped convolutional layers is used to detect ECG irregularities of arrhythmia. Each sample point is examined for its local fractal dimension before extracting the heartbeat waveforms within a predetermined window length. A bio-inspired Dingo Optimization (DO) algorithm is used in the SID-NASNet to normalize the parameters to improve the efficiency of the network with low network complexity. The efficiency of the proposed SID-NASNet is assessed with specificity, accuracy, precision, F1 score and recall based on the MIT-BIH arrhythmia dataset. From the test results, the proposed SID-NASNet achieves an accuracy of 98.22% for effective categorization of ECG signals. The proposed SID-NASNet improves the overall accuracy of 1.24%, 3.76%, 1.87%, and 0.22% better than ECG-NET, Deep Learning (DL)-based GAN, 1D-CNN, and GAN-Long-Short Term Memory (LSTM), respectively.

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.

Electrocardiogram (ECG) signal processing aims basically 1) at artifact reduction to make the ECG signals cleaner and better interpretable by human or machine observers, 2) at revealing aspects not immediately observable in plain measured ECG signals even after artifact reduction, or 3) at diagnostics decision support and automated ECG signal interpretation, including classification of ECG signals into different classes associated with normal or pathological heart function. Thus, sports related applications aside, body surface ECG signal processing aims at enhancing ECG based diagnostics. In this Chapter, we review and demonstrate a statistical signal processing approach, independent component analysis (ICA), which is inherently very suitable for ECG signal processing regarding the aims 1) and 2) above, and also equally applicable as a component in systems aimed at accomplishing the aim 3). For more on general ECG signal processing, the reader is directed to the textbook written by Sornmo & Laguna (2005), and for a thorough treatment of ICA to the Hyvarinen’s book (Hyvarinen et al., 2001). A concise review on ICA in ECG signal processing has been presented by Castells et al. (2007a). In this Chapter, we describe and illustrate several widely adopted applications of ICA in ECG signal processing, and discuss associated practical aspects, some of which are not generally found in the literature. The treatment of the matter is aimed at conceptual and practical understanding, leaving the mathematical derivations and proofs far mostly for the interested reader to find in the references. ICA (Castells et al., 2007a; Comon, 1994; Hyvarinen et al., 2001; Hyvarinen & Oja, 2000; Naik & Kumar, 2011) is a statistical signal processing method for decomposing a set of signals into a set of mutually independent component signals. In general, in the applications of ICA, including in ECG signal processing, the objective is that the resulting independent component signals are the original source signals. Since ICA operates purely based on the input signals and a few assumptions, ICA belongs to the class of methods called blind source separation methods. For ICA, a source signal is called an independent component (IC). The terms ‘IC’ and ‘source signal’ are here used interchangeably. For ECG, the source signals are the bioelectrical signals generated by the heart, and all the possible artifact signals. Generally, ICA input signals are the observed signals, which may be measurement time series, such as sampled voltage values in time as in the case of ECGs, image pixel values, or basically any sets of values fulfilling the assumptions of ICA. In the sequel, the term

Present paper deals with design and development of digital FIR filters. Heart diseases, which are one of the death reasons, are among the several serious problems in this century and as per the latest survey, 60% of the patients die due to Heart diseases. Electrocardiogram (ECG) signal plays a vital role in the monitoring and diagnosis of the health conditions of human heart. The basic ECG signal has the frequency range from .5Hz to 100Hz. The most significant noises that corrupt ECG signal are power line interference and baseline wanders. It becomes difficult for the Specialist to diagnose the diseases if artifacts are present in the ECG signal. Designing digital filters to reduce these noises is very important in ECG signal processing. In this work a digital FIR filter for reducing 50Hz power line noise in ECG signal is designed and implemented with different windowing methods as of Hamming, Kaiser, and Chebyshev. The work has been done in MATLAB environment. The result obtained for all FIR filters are compared by comparing the waveforms of the original and filtered ECG signals. The filter which gives the best results is the one using Chebyshev Window.

Electrocardiogram (ECG) are the physiological signals and a standard test to measure the heart’s electrical activity that depicts the movement of cardiac muscles. A review study has been conducted on ECG signals analysis with the help of artificial intelligence (AI) methods over the last ten years i.e., 2012–22. Primarily, the method of ECG analysis by software systems was divided into classical signal processing (e.g. spectrograms or filters), machine learning (ML) and deep learning (DL), including recursive models, transformers and hybrid. Secondly, the data sources and benchmark datasets were depicted. Authors grouped resources by ECG acquisition methods into hospital-based portable machines and wearable devices. Authors also included new trends like advanced pre-processing, data augmentation, simulations and agent-based modeling.The study found improvement in ECG examination perfection made each year through ML, DL, hybrid models, and transformers. Convolutional neural networks and hybrid models were more targeted and proved efficient. The transformer model extended the accuracy from 90% to 98%. The Physio-Net library helps acquire ECG signals, including the popular benchmark databases such as MIT-BIH, PTB, and challenging datasets. Similarly, wearable devices have been established as a appropriate option for monitoring patient health without the time and place limitations and are also helpful for AI model calibration with so far accuracy of 82%–83% on Samsung smartwatch. In the pre-processing signals, spectrogram generation through Fourier and wavelet transformations are erected leading approaches promoting on average accuracy of 90%–95%. Likewise, data enhancement using geometrical techniques is well-considered; however, extraction and concatenation-based methods need attention. As the what-if analysis in healthcare or cardiac issues can be performed using a complex simulation, the study reviews agent-based modeling and simulation approaches for cardiovascular risk event assessment.

This paper investigates the application of the newly proposed Kronecker-based method for the reconstruction of compressively sensed electrocardiogram (ECG) signals. By applying the Kronecker-based method, ECG signal acquisition is done in smaller lengths. Collection of smaller length of ECG signals leads to fewer arithmetic operations during the compression phase. Instead of recovering individually in smaller lengths, recovery is done over several concatenated segments. This newly proposed recovery method improves the quality of the reconstructed signal when compared to the traditional recovery done without concatenation. Two random measurement matrices, namely the Gaussian and the Bernoulli matrices, are considered as sensing matrices in this study and the methodology is evaluated using 10 ECG signals acquired from the MIT arrhythmia database. The random Bernoulli matrix is found to provide better quality of recovered compressed ECG signal even with the traditional compressive recovery techniques. Recovery by the newly proposed Kroneckerbased method results in higher SNR in all the ECG signals when the compression ratio (CR) is 25% or 50% and when the CR is 75%, improvement is observed in majority of the ECG signals. Lower CRs provide better reconstruction than higher CRs. The Kronecker-based recovery method may be useful for wearable ECG devices.

<title>Abstract</title> Electrocardiogram (ECG) signals are critical to identify various cardiac abnormalities. However, the accuracy of ECG-based clinical interpretations can be significantly compromised due to contamination from various artifacts. Traditional ECG denoising methods often struggle to maintain the balance between noise suppression and preservation of essential ECG characteristics. This study presents, for the first time, a deep learning (DL)-based autoencoder (AE) for robust ECG denoising and artifact cancellation and automated ECG diagnosis and classification. Unlike traditional methods, AEs are designed to learn efficient data representations, making them well-suited for distinguishing between clean signals and noise without extensive computational demands. The proposed approach leverages the PTB Diagnostic ECG Database (PTBdb) and introduces various types of noise derived from the MIT-BIH Noise Stress Test Database, including muscle artifacts (MA), electrode motion artifacts (EM), baseline wander (BW), and their combinations. The proposed AE model is trained to eliminate these noise components effectively while preserving the critical morphological features of the ECG signals. To assess the performance of the introduced method, comprehensive experiments are performed to compare clean, noisy, and AE denoised ECG signals. The AE's performance is further benchmarked against classical denoising techniques, assessing key metrics such as signal to noise ratio (SNR), mean square error (MSE), root mean square error (RMSE) and a percent root-mean square difference (PRD). The results elucidate that the introduced AE-based denoising framework not only outperforms conventional techniques in noise suppression but also enhances the reliability of ECG signal interpretation, making it an effective solution for implementation in clinical settings.

Anomaly detection is one of the basic issues in data processing that addresses different problems in healthcare sensory data. Technology has made it easier to collect large and highly variant time series data; however, complex predictive analysis models are required to ensure consistency and reliability. With the rise in the size and dimensionality of collected data, deep learning techniques, such as autoencoder (AE), recurrent neural networks (RNN), and long short-term memory (LSTM), have gained more attention and are recognized as state-of-the-art anomaly detection techniques. Recently, developments in transformer-based architecture have been proposed as an improved attention-based knowledge representation scheme. We present an unsupervised transformer-based method to evaluate and detect anomalies in electrocardiogram (ECG) signals. The model architecture comprises two parts: an embedding layer and a standard transformer encoder. We introduce, implement, test, and validate our model in two well-known datasets: ECG5000 and MIT-BIH Arrhythmia. Anomalies are detected based on loss function results between real and predicted ECG time series sequences. We found that the use of a transformer encoder as an alternative model for anomaly detection enables better performance in ECG time series data. The suggested model has a remarkable ability to detect anomalies in ECG signal and outperforms deep learning approaches found in the literature on both datasets. In the ECG5000 dataset, the model can detect anomalies with 99% accuracy, 99% F1-score, 99% AUC score, 98.1% recall, and 100% precision. In the MIT-BIH Arrhythmia dataset, the model achieved an accuracy of 89.5%, F1 score of 92.3%, AUC score of 93%, recall of 98.2%, and precision of 87.1%.