Heart disease detection using deep learning methods from imbalanced ECG samples

Pre-Processing techniques and artificial intelligence algorithms for electrocardiogram (ECG) signals analysis: A comprehensive review

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.

Echo state networks for the recognition of type 1 Brugada syndrome from conventional 12-LEAD ECG

Artificial Intelligence (AI) applications and Machine Learning (ML) methods have gained much attention in recent years for their ability to automatically detect patterns in data without being explicitly taught rules. Specific features characterise the ECGs of patients with Brugada Syndrome (BrS); however, there is still ambiguity regarding the correct diagnosis of BrS and its differentiation from other pathologies. This work presents an application of Echo State Networks (ESN) in the Recurrent Neural Networks (RNN) class for diagnosing BrS from the ECG time series. 12-lead ECGs were obtained from patients with a definite clinical diagnosis of spontaneous BrS Type 1 pattern (Group A), patients who underwent provocative pharmacological testing to induce BrS type 1 pattern, which resulted in positive (Group B) or negative (Group C), and control subjects (Group D). One extracted beat in the V2 lead was used as input, and the dataset was used to train and evaluate the ESN model using a double cross-validation approach. ESN performance was compared with that of 4 cardiologists trained in electrophysiology. The model performance was assessed in the dataset, with a correct global diagnosis observed in 91.5 % of cases compared to clinicians (88.0 %). High specificity (94.5 %), sensitivity (87.0 %) and AUC (94.7 %) for BrS recognition by ESN were observed in Groups A + B vs. C + D. Our results show that this ML model can discriminate Type 1 BrS ECGs with high accuracy comparable to expert clinicians. Future availability of larger datasets may improve the model performance and increase the potential of the ESN as a clinical support system tool for daily clinical practice.

Classification feasibility test on multi-lead electrocardiography signals generated from single-lead electrocardiography signals

Nowadays, Electrocardiogram (ECG) signals can be measured using wearable devices, such as smart watches. Most wearable devices provide only a few details; however, they have the advantage of recording data in real time. In this study, 12-lead ECG signals were generated from lead I and their feasibility was tested to obtain more details. The 12-lead ECG signals were generated using a U-net-based generative adversarial network (GAN) that was trained on ECG data obtained from the Asan Medical Center. Subsequently, unseen PTB-XL PhysioNet data were used to produce real 12-lead ECG signals for classification. The generated and real 12-lead ECG signals were then compared using a ResNet classification model; and the normal, atrial fibrillation (A-fib), left bundle branch block (LBBB), right bundle branch block (RBBB), left ventricular hypertrophy (LVH), and right ventricular hypertrophy (RVH) were classified. The mean precision, recall, and f1-score for the real 12-lead ECG signals are 0.70, 0.72, and 0.70, and that for the generated 12-lead ECG signals are 0.82, 0.80, and 0.81, respectively. In our study, according to the result generated 12-lead ECG signals performed better than real 12-lead ECG.

Ensemble classifier fostered detection of arrhythmia using ECG data

Electrocardiogram (ECG) is a non-invasive medical tool that divulges the rhythm and function of the human heart. This is broadly employed in heart disease detection including arrhythmia. Arrhythmia is a general term for abnormal heart rhythms that can be identified and classified into many categories. Automatic ECG analysis is provided by arrhythmia categorization in cardiac patient monitoring systems. It aids cardiologists to diagnose the ECG signal. In this work, an Ensemble classifier is proposed for accurate arrhythmia detection using ECG Signal. Input data are taken from the MIT-BIH arrhythmia dataset. Then the input data was pre-processed using Python in Jupyter Notebook which run the code in an isolated manner and was able to keep code, formula, comments, and images. Then, Residual Exemplars Local Binary Pattern is applied for extracting statistical features. The extracted features are given to ensemble classifiers, like Support vector machines (SVM), Naive Bayes (NB), and random forest (RF) for classifying the arrhythmia as normal (N), supraventricular ectopic beat (S), ventricular ectopic beat (V), fusion beat (F), and unknown beat (Q). The proposed AD-Ensemble SVM-NB-RF method is implemented in Python. The proposed AD-Ensemble SVM-NB-RF method is 44.57%, 52.41%, and 29.49% higher accuracy; 2.01%, 3.33%, and 3.19% higher area under the curve (AUC); and 21.52%, 23.05%, and 12.68% better F-Measure compared with existing models, like multi-model depending on the ensemble of deep learning for ECG heartbeats arrhythmia categorization (AD-Ensemble CNN-LSTM-RRHOS), ECG signal categorization utilizing VGGNet: a neural network based classification method (AD-Ensemble CNN-LSTM) and higher performance arrhythmic heartbeat categorization utilizing ensemble learning along PSD based feature extraction method (AD-Ensemble MLP-NB-RF).

A Systematic Survey of Data Augmentation of ECG Signals for AI Applications

AI techniques have recently been put under the spotlight for analyzing electrocardiograms (ECGs). However, the performance of AI-based models relies on the accumulation of large-scale labeled datasets, which is challenging. To increase the performance of AI-based models, data augmentation (DA) strategies have been developed recently. The study presented a comprehensive systematic literature review of DA for ECG signals. We conducted a systematic search and categorized the selected documents by AI application, number of leads involved, DA method, classifier, performance improvements after DA, and datasets employed. With such information, this study provided a better understanding of the potential of ECG augmentation in enhancing the performance of AI-based ECG applications. This study adhered to the rigorous PRISMA guidelines for systematic reviews. To ensure comprehensive coverage, publications between 2013 and 2023 were searched across multiple databases, including IEEE Explore, PubMed, and Web of Science. The records were meticulously reviewed to determine their relevance to the study's objective, and those that met the inclusion criteria were selected for further analysis. Consequently, 119 papers were deemed relevant for further review. Overall, this study shed light on the potential of DA to advance the field of ECG diagnosis and monitoring.

Hierarchical deep learning with Generative Adversarial Network for automatic cardiac diagnosis from ECG signals

Cardiac disease is the leading cause of death in the US. Accurate heart disease detection is critical to timely medical treatment to save patients' lives. Routine use of the electrocardiogram (ECG) is the most common method for physicians to assess the cardiac electrical activities and detect possible abnormal conditions. Fully utilizing the ECG data for reliable heart disease detection depends on developing effective analytical models. In this paper, we propose a two-level hierarchical deep learning framework with Generative Adversarial Network (GAN) for ECG signal analysis. The first-level model is composed of a Memory-Augmented Deep AutoEncoder with GAN (MadeGAN), which aims to differentiate abnormal signals from normal ECGs for anomaly detection. The second-level learning aims at robust multi-class classification for different arrhythmia identification, which is achieved by integrating the transfer learning technique to transfer knowledge from the first-level learning with the multi-branching architecture to handle the data-lacking and imbalanced data issues. We evaluate the performance of the proposed framework using real-world ECG data from the MIT-BIH arrhythmia database. Experimental results show that our proposed model outperforms existing methods that are commonly used in current practice.

Towards Automated Optimization of Residual Convolutional Neural Networks for Electrocardiogram Classification

The interpretation of biological data such as the ElectroCardioGram (ECG) signal gives clinical information and helps to assess the heart function. There are distinct ECG patterns associated with a specific class of arrhythmia. The convolutional neural network, inspired by findings in the study of biological vision, is currently one of the most commonly employed deep neural network algorithms for ECG processing. However, deep neural network models require many hyperparameters to tune. Selecting the optimal or the best hyperparameter for the convolutional neural network algorithm is a highly challenging task. Often, we end up tuning the model manually with different possible ranges of values until a best fit model is obtained. Automatic hyperparameters tuning using Bayesian Optimization (BO) and evolutionary algorithms can provide an effective solution to current labour-intensive manual configuration approaches. In this paper, we propose to optimize the Residual one Dimensional Convolutional Neural Network model (R-1D-CNN) at two levels. At the first level, a residual convolutional layer and one-dimensional convolutional neural layers are trained to learn patient-specific ECG features over which multilayer perceptron layers can learn to produce the final class vectors of each input. This level is manual and aims to limit the search space and select the most important hyperparameters to optimize. The second level is automatic and based on our proposed BO-based algorithm. Our optimized proposed architecture (BO-R-1D-CNN) is evaluated on two publicly available ECG datasets. Comparative experimental results demonstrate that our BO-based algorithm achieves an optimal rate of 99.95% for the MIT-BIH database to discriminate between five kinds of heartbeats, including normal heartbeats, left bundle branch block, atrial premature, right bundle branch block, and premature ventricular contraction. Moreover, experiments demonstrate that the proposed architecture fine-tuned with BO achieves a higher accuracy tested on the 10,000 ECG patients dataset compared to the other proposed architectures. Our optimized architecture achieves excellent results compared to previous works on the two benchmark datasets.

Biometric Recognition: A Systematic Review on Electrocardiogram Data Acquisition Methods

In the last decades, researchers have shown the potential of using Electrocardiogram (ECG) as a biometric trait due to its uniqueness and hidden nature. However, despite the great number of approaches found in the literature, no agreement exists on the most appropriate methodology. This paper presents a systematic review of data acquisition methods, aiming to understand the impact of some variables from the data acquisition protocol of an ECG signal in the biometric identification process. We searched for papers on the subject using Scopus, defining several keywords and restrictions, and found a total of 121 papers. Data acquisition hardware and methods vary widely throughout the literature. We reviewed the intrusiveness of acquisitions, the number of leads used, and the duration of acquisitions. Moreover, by analyzing the literature, we can conclude that the preferable solutions include: (1) the use of off-the-person acquisitions as they bring ECG biometrics closer to viable, unconstrained applications; (2) the use of a one-lead setup; and (3) short-term acquisitions as they required fewer numbers of contact points, making the data acquisition of benefit to user acceptance and allow faster acquisitions, resulting in a user-friendly biometric system. Thus, this paper reviews data acquisition methods, summarizes multiple perspectives, and highlights existing challenges and problems. In contrast, most reviews on ECG-based biometrics focus on feature extraction and classification methods.

Explainable machine learning framework for predicting long-term cardiovascular disease risk among adolescents

Although cardiovascular disease (CVD) is the leading cause of death worldwide, over 80% of it is preventable through early intervention and lifestyle changes. Most cases of CVD are detected in adulthood, but the risk factors leading to CVD begin at a younger age. This research is the first to develop an explainable machine learning (ML)-based framework for long-term CVD risk prediction (low vs. high) among adolescents. This study uses longitudinal data from a nationally representative sample of individuals who participated in the Add Health study. A total of 14,083 participants who completed relevant survey questionnaires and health tests from adolescence to young adulthood were chosen. Four ML classifiers [decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), and deep neural networks (DNN)] and 36 adolescent predictors are used to predict adulthood CVD risk. While all ML models demonstrated good prediction capability, XGBoost achieved the best performance (AUC-ROC: 84.5% and AUC-PR: 96.9% on testing data). Besides, critical predictors of long-term CVD risk and its impact on risk prediction are obtained using an explainable technique for interpreting ML predictions. The results suggest that ML can be employed to detect adulthood CVD very early in life, and such an approach may facilitate primordial prevention and personalized intervention.

Machine learning based regional epidemic transmission risks precaution in digital society

The contact and interaction of human is considered to be one of the important factors affecting the epidemic transmission, and it is critical to model the heterogeneity of individual activities in epidemiological risk assessment. In digital society, massive data makes it possible to implement this idea on large scale. Here, we use the mobile phone signaling to track the users' trajectories and construct contact network to describe the topology of daily contact between individuals dynamically. We show the spatiotemporal contact features of about 7.5 million mobile phone users during the outbreak of COVID-19 in Shanghai, China. Furthermore, the individual feature matrix extracted from contact network enables us to carry out the extreme event learning and predict the regional transmission risk, which can be further decomposed into the risk due to the inflow of people from epidemic hot zones and the risk due to people close contacts within the observing area. This method is much more flexible and adaptive, and can be taken as one of the epidemic precautions before the large-scale outbreak with high efficiency and low cost.

A Robust Framework Combining Image Processing and Deep Learning Hybrid Model to Classify Cardiovascular Diseases Using a Limited Number of Paper-Based Complex ECG Images

Heart disease can be life-threatening if not detected and treated at an early stage. The electrocardiogram (ECG) plays a vital role in classifying cardiovascular diseases, and often physicians and medical researchers examine paper-based ECG images for cardiac diagnosis. An automated heart disease prediction system might help to classify heart diseases accurately at an early stage. This study aims to classify cardiac diseases into five classes with paper-based ECG images using a deep learning approach with the highest possible accuracy and the lowest possible time complexity. This research consists of two approaches. In the first approach, five deep learning models, InceptionV3, ResNet50, MobileNetV2, VGG19, and DenseNet201, are employed. In the second approach, an integrated deep learning model (InRes-106) is introduced, combining InceptionV3 and ResNet50. This model is developed as a deep convolutional neural network capable of extracting hidden and high-level features from images. An ablation study is conducted on the proposed model altering several components and hyperparameters, improving the performance even further. Before training the model, several image pre-processing techniques are employed to remove artifacts and enhance the image quality. Our proposed hybrid InRes-106 model performed best with a testing accuracy of 98.34%. The InceptionV3 model acquired a testing accuracy of 90.56%, the ResNet50 89.63%, the DenseNet201 88.94%, the VGG19 87.87%, and the MobileNetV2 achieved 80.56% testing accuracy. The model is trained with a k-fold cross-validation technique with different k values to evaluate the robustness further. Although the dataset contains a limited number of complex ECG images, our proposed approach, based on various image pre-processing techniques, model fine-tuning, and ablation studies, can effectively diagnose cardiac diseases.

Imbalanced ECG signal-based heart disease classification using ensemble machine learning technique

The machine learning (ML)-based classification models are widely utilized for the automated detection of heart diseases (HDs) using various physiological signals such as electrocardiogram (ECG), magnetocardiography (MCG), heart sound (HS), and impedance cardiography (ICG) signals. However, ECG-based HD identification is the most common one used by clinicians. In the current investigation, the ECG records or subjects have been sampled and are used as inputs to the classification model to distinguish between normal and abnormal patients. The study has employed an imbalanced number of ECG samples for training the various classification models. Few ML methods such as support vector machine (SVM), logistic regression (LR), and adaptive boosting (AdaBoost) which have been rarely used for HD detection have been selected. The performance of the developed model has been evaluated in terms of accuracy, F1-score, and area under curve (AUC) values using ECG signals of subjects given in publicly available (PTB-ECG, MIT-BIH) datasets. Ranking of the models has been assigned based on these performance metrics and it is found that the AdaBoost and LR classifiers stand in first and second positions. These two models have been ensembled based on the majority voting principle and the performance measure of this ensemble model has also been determined. It is, in general, observed that the proposed ensemble model demonstrates the best HD detection performance of 0.946, 0.949, and 0.951 for the PTB-ECG dataset and 0.921, 0.926, and 0.950 for the MIT-BIH dataset in terms of accuracy, F1-score, and AUC, respectively. The proposed methodology can also be employed for the classification of HD using ICG, MCG, and HS signals as inputs. Further, the proposed methodology can also be applied to the detection of other diseases.

Heart disease detection based on internet of things data using linear quadratic discriminant analysis and a deep graph convolutional neural network

Heart disease is an emerging health issue in the medical field, according to WHO every year around 10 billion people are affected with heart abnormalities. Arteries in the heart generate oxygenated blood to all body parts, however sometimes blood vessels become clogged or restrained due to cardiac issues. Past heart diagnosis applications are outdated and suffer from poor performance. Therefore, an intelligent heart disease diagnosis application design is required. In this research work, internet of things (IoT) sensor data with a deep learning-based heart diagnosis application is designed. The heart disease IoT sensor data is collected from the University of California Irvine machine learning repository free open-source dataset which is useful for training the deep graph convolutional network (DG_ConvoNet) deep learning network. The testing data has been collected from the Cleveland Clinic Foundation; it is a collection of 350 real-time clinical instances from heart patients through IoT sensors. The K-means technique is employed to remove noise in sensor data and clustered the unstructured data. The features are extracted to employ Linear Quadratic Discriminant Analysis. DG_ConvoNet is a deep learning process to classify and predict heart diseases. The diagnostic application achieves an accuracy of 96%, sensitivity of 80%, specificity of 73%, precision of 90%, F-Score of 79%, and area under the ROC curve of 75% implementing the proposed model.

An automated heart disease prediction approach using linearly support vector regression and stacked linear swarm optimization

In today’s world, mining and learning applications play an essential role in healthcare sectors and intend to transform all the data into an understandable form. However, the healthcare sectors require an automated disease prediction system for better medical analysis and emphasize better prediction accuracy for evaluation purposes. In this paper, a new automated prediction model based on Linearly Support Vector Regression and Stacked Linear Swarm Optimization (LSVR-SLSO) has been proposed to predict heart disease accurately. Primarily, the features are analyzed in a linear and non-linear manner using LSVR feature learning approaches. The extracted features are then fed into the SLSO model in order to extract the global optimal solutions. These global solutions will reduce the data dimensionality and computational complexity during the evaluation phase. Moreover, the optimal solution facilitates the proposed model to predict heart disease appropriately. The simulation can be carried out through the MATLAB environment by utilizing a publicly available benchmark heart disease dataset. The performance results evident that the proposed LSVR-SLSO model can efficiently predict heart disease with superior accuracy of 98%, precision of 98.76%, and recall of 99.7% when compared with conventional approaches. The better performance of the proposed model will pave the way to act as an effective clinical decision support tool for physicians during an emergency.

A multi-variate heart disease optimization and recognition framework

Cardiovascular diseases (CVD) are the most widely spread diseases all over the world among the common chronic diseases. CVD represents one of the main causes of morbidity and mortality. Therefore, it is vital to accurately detect the existence of heart diseases to help to save the patient life and prescribe a suitable treatment. The current evolution in artificial intelligence plays an important role in helping physicians diagnose different diseases. In the present work, a hybrid framework for the detection of heart diseases using medical voice records is suggested. A framework that consists of four layers, namely “Segmentation” Layer, “Features Extraction” Layer, “Learning and Optimization” Layer, and “Export and Statistics” Layer is proposed. In the first layer, a novel segmentation technique based on the segmentation of variable durations and directions (i.e., forward and backward) is suggested. Using the proposed technique, 11 datasets with 14,416 numerical features are generated. The second layer is responsible for feature extraction. Numerical and graphical features are extracted from the resulting datasets. In the third layer, numerical features are passed to 5 different Machine Learning (ML) algorithms, while graphical features are passed to 8 different Convolutional Neural Networks (CNN) with transfer learning to select the most suitable configurations. Grid Search and Aquila Optimizer (AO) are used to optimize the hyperparameters of ML and CNN configurations, respectively. In the last layer, the output of the proposed hybrid framework is validated using different performance metrics. The best-reported metrics are (1) 100% accuracy using ML algorithms including Extra Tree Classifier (ETC) and Random Forest Classifier (RFC) and (2) 99.17% accuracy using CNN.

Deep Learning-Based Heart Sound Analysis for Left Ventricular Diastolic Dysfunction Diagnosis

The aggravation of left ventricular diastolic dysfunction (LVDD) could lead to ventricular remodeling, wall stiffness, reduced compliance, and progression to heart failure with a preserved ejection fraction. A non-invasive method based on convolutional neural networks (CNN) and heart sounds (HS) is presented for the early diagnosis of LVDD in this paper. A deep convolutional generative adversarial networks (DCGAN) model-based data augmentation (DA) method was proposed to expand a HS database of LVDD for model training. Firstly, the preprocessing of HS signals was performed using the improved wavelet denoising method. Secondly, the logistic regression based hidden semi-Markov model was utilized to segment HS signals, which were subsequently converted into spectrograms for DA using the short-time Fourier transform (STFT). Finally, the proposed method was compared with VGG-16, VGG-19, ResNet-18, ResNet-50, DenseNet-121, and AlexNet in terms of performance for LVDD diagnosis. The result shows that the proposed method has a reasonable performance with an accuracy of 0.987, a sensitivity of 0.986, and a specificity of 0.988, which proves the effectiveness of HS analysis for the early diagnosis of LVDD and demonstrates that the DCGAN-based DA method could effectively augment HS data.