Accurate detection of atrial fibrillation from 12-lead ECG using deep neural network

Clinician-artificial intelligence collaboration: A win-win solution for efficiency and reliability in atrial fibrillation diagnosis

BACKGROUND

Given the biases and ethical concerns of AI models, the fully automatic diagnosis of diseases in clinical settings is challenging. In contrast, clinician-AI collaboration is considered essential to ensure the validity and reliability of utilizing AI models in clinical practice. However, effective strategies for clinician-AI collaboration remain largely unexplored.

METHODS

This study proposed a three-step general clinician-AI collaboration pipeline aimed at improving disease diagnosis efficiency: first, utilizing large real-world clinical datasets to evaluate and clarify clinicians' diagnostic strengths/weaknesses; second, developing an AI model to complement clinicians' weakness in disease diagnosis; and finally, proposing a clinician-AI collaboration strategy to leverage the strengths of both AI and clinicians. The effectiveness of this pipeline was validated through a study focusing on clinical paroxysmal atrial fibrillation (PAF) detection, utilizing 24-h Holter recordings from over 30,000 patients.

FINDINGS

In PAF detection, clinicians alone required a significant amount of time to identify the data and still overlooked 13.7% of PAF patients but successfully identified all non-atrial fibrillation (AF) patients. Conversely, AI alone rarely missed PAF patients but misidentified 23.3% of non-AF patients as having PAF. After implementing the proposed clinician-AI collaboration strategy, all patients were correctly identified, and clinicians' workload was reduced by 76.7%.

CONCLUSIONS

This study improves both the efficiency and reliability of PAF detection, bridging the gap between AI model development and its clinical application, thereby effectively promoting the application of AI models in clinical AF screening.

FUNDING

This study was supported in part by the National Natural Science Foundation of China.

Integrating deep learning with ECG, heart rate variability and demographic data for improved detection of atrial fibrillation

BACKGROUND

Atrial fibrillation (AF) is a common but often undiagnosed condition, increasing the risk of stroke and heart failure. Early detection is crucial, yet traditional methods struggle with AF's transient nature. This study investigates how augmenting ECG data with heart rate variability (HRV) and demographic data (age and sex) can improve AF detection.

METHODS

We analysed 35 634 12-lead ECG recordings from three public databases (China Physiological Signal Challenge-Extra, PTB-XL and Georgia), each with physician-validated AF labels. A range of convolutional neural network models, including AlexNet, VGG-16, ResNet and transformers, were tested for AF prediction, enriched with HRV and demographic data to explore the effectiveness of the multimodal approach. Each data modality (ECG, HRV and demographic) was assessed for its contribution to model performance using fivefold cross-validation. Performance improvements were evaluated across key metrics, and saliency maps were generated to provide further insights into model behaviour and identify critical features in AF detection.

RESULTS

Integrating HRV and demographic data with ECG substantially improved performance. AlexNet and VGG-16 outperformed more complex models, achieving AUROC of 0.9617 (95% CI 0.95 to 0.97) and 0.9668 (95% CI 0.96 to 0.97), respectively. Adding HRV data showed the most significant improvement in sensitivity, with AlexNet increasing from 0.9117 to 0.9225 and VGG-16 from 0.9216 to 0.9225. Combining both HRV and demographic data led to further improvements, with AlexNet achieving a sensitivity of 0.9225 (up from 0.9192 with HRV) and VGG-16 reaching 0.9113 (up from 0.9097 with HRV). The combination of HRV and demographic data resulted in the highest gains in sensitivity and area under the receiver operating characteristic curve. Saliency maps confirmed the models identified key AF features, such as the absence of the P-wave, validating the multimodal approach.

CONCLUSIONS

AlexNet and VGG-16 excelled in AF detection, with HRV data improving sensitivity, and demographic data providing additional benefits. These results highlight the potential of multimodal approaches, pending further clinical validation.

Deep learning-based analysis of 12-lead electrocardiograms in school-age children: a proof of concept study

Introduction

The diagnostic performance of automated analysis of electrocardiograms for screening children with pediatric heart diseases at risk of sudden cardiac death is unknown. In this study, we aimed to develop and validate a deep learning-based model for automated analysis of ECGs in children.

Methods

Wave data of 12-lead electrocardiograms were transformed into a tensor sizing 2 × 12 × 400 using signal processing methods. A deep learning-based model to classify abnormal electrocardiograms based on age, sex, and the transformed wave data was developed using electrocardiograms performed in patients at the age of 6-18 years during 2003-2006 at a tertiary referral hospital in Japan. Eighty-three percent of the patients were assigned to a training group, and 17% to a test group. The diagnostic performance of the model and a conventional algorithm (ECAPS12C, Nihon Kohden, Japan) for classifying abnormal electrocardiograms were evaluated using the cross-tabulation, McNemar's test, and decision curve analysis.

Results

We included 1,842 ECGs performed in 1,062 patients in this study, and 310 electrocardiograms performed in 177 patients were included in the test group. The specificity of the deep learning-based model for detecting abnormal electrocardiograms was not significantly different from that of the conventional algorithm. For detecting electrocardiograms with ST-T abnormality, complete right bundle branch block, QRS axis abnormality, left ventricular hypertrophy, incomplete right bundle branch block, WPW syndrome, supraventricular tachyarrhythmia, and Brugada-type electrocardiograms, the specificity of the deep learning-based model was higher than that of the conventional algorithm at the same sensitivity.

Conclusions

The present new deep learning-based method of screening for abnormal electrocardiograms in children showed at least a similar diagnostic performance compared to that of a conventional algorithm. Further studies are warranted to develop an automated analysis of electrocardiograms in school-age children.

Recent advances in the tools and techniques for AI-aided diagnosis of atrial fibrillation

Atrial fibrillation (AF) is recognized as a developing global epidemic responsible for a significant burden of morbidity and mortality. To counter this public health crisis, the advancement of artificial intelligence (AI)-aided tools and methodologies for the effective detection and monitoring of AF is becoming increasingly apparent. A unified strategy from the international research community is essential to develop effective intelligent tools and technologies to support the health professionals for effective surveillance and defense against AF. This review delves into the practical implications of AI-aided tools and techniques for AF detection across different clinical settings including screening, diagnosis, and ambulatory monitoring by reviewing the revolutionary research works. The key finding is that the advance in AI and its use for automatic detection of AF has achieved remarkable success, but collaboration between AI and human intelligence is required for trustworthy diagnostic of this life-threatening cardiac condition. Moreover, designing efficient and robust intelligent algorithms for onboard AF detection using portable and implementable computing devices with limited computation power and energy supply is a crucial research problem. As modern wearable devices are equipped with sophisticated embedded sensors, such as optical sensors and accelerometers, hence photoplethysmography and ballistocardiography signals could be explored as an affordable alternative to electrocardiography (ECG) signals for AF detection, particularly for the development of low-cost and miniature screening and monitoring devices.

Detection of atrial fibrillation from pulse waves using convolution neural networks and recurrence-based plots

We propose a classification method for distinguishing atrial fibrillation from sinus rhythm in pulse-wave measurements obtained with a blood pressure monitor. This method combines recurrence-based plots with convolutional neural networks. Moreover, we devised a novel plot, with which our classification achieved specificity of 97.5%, sensitivity of 98.4%, and accuracy of 98.6%. These criteria are higher than previously reported results for measurements obtained with blood pressure monitors and are almost equal to statistical measures for methods based on electrocardiographs and photoplethysmographs.

Deep learning and electrocardiography: systematic review of current techniques in cardiovascular disease diagnosis and management

This paper reviews the recent advancements in the application of deep learning combined with electrocardiography (ECG) within the domain of cardiovascular diseases, systematically examining 198 high-quality publications. Through meticulous categorization and hierarchical segmentation, it provides an exhaustive depiction of the current landscape across various cardiovascular ailments. Our study aspires to furnish interested readers with a comprehensive guide, thereby igniting enthusiasm for further, in-depth exploration and research in this realm.

Deep learning assists early-detection of hypertension-mediated heart change on ECG signals

Arterial hypertension is a major risk factor for cardiovascular diseases. While cardiac ultrasound is a typical way to diagnose hypertension-mediated heart change, it often fails to detect early subtle structural changes. Electrocardiogram(ECG) represents electrical activity of heart muscle, affected by the changes in heart's structure. It is crucial to explore whether ECG can capture slight signals of hypertension-mediated heart change. However, reading ECG records is complex and some signals are too subtle to be captured by cardiologist's visual inspection. In this study, we designed a deep learning model to predict hypertension on ECG signals and then to identify hypertension-associated ECG segments. From The First Affiliated Hospital of Xiamen University, we collected 210,120 10-s 12-lead ECGs using the FX-8322 manufactured by FUKUDA and 812 ECGs using the RAGE-12 manufactured by NALONG. We proposed a deep learning framework, including MML-Net, a multi-branch, multi-scale LSTM neural network to evaluate the potential of ECG signals to detect hypertension, and ECG-XAI, an ECG-oriented wave-alignment AI explanation pipeline to identify hypertension-associated ECG segments. MML-Net achieved an 82% recall and an 87% precision in the testing, and an 80% recall and an 82% precision in the independent testing. In contrast, experienced clinical cardiologists typically attain recall rates ranging from 30 to 50% by visual inspection. The experiments demonstrate that ECG signals are sensitive to slight changes in heart structure caused by hypertension. ECG-XAI detects that R-wave and P-wave are the hypertension-associated ECG segments. The proposed framework has the potential to facilitate early diagnosis of heart change.

Visual interpretation of deep learning model in ECG classification: A comprehensive evaluation of feature attribution methods

Feature attribution methods can visually highlight specific input regions containing influential aspects affecting a deep learning model's prediction. Recently, the use of feature attribution methods in electrocardiogram (ECG) classification has been sharply increasing, as they assist clinicians in understanding the model's decision-making process and assessing the model's reliability. However, a careful study to identify suitable methods for ECG datasets has been lacking, leading researchers to select methods without a thorough understanding of their appropriateness. In this work, we conduct a large-scale assessment by considering eleven popular feature attribution methods across five large ECG datasets using a model based on the ResNet-18 architecture. Our experiments include both automatic evaluations and human evaluations. Annotated datasets were utilized for automatic evaluations and three cardiac experts were involved for human evaluations. We found that Guided Grad-CAM, particularly when its absolute values are utilized, achieves the best performance. When Guided Grad-CAM was utilized as the feature attribution method, cardiac experts confirmed that it can identify diagnostically relevant electrophysiological characteristics, although its effectiveness varied across the 17 different diagnoses that we have investigated.

Risk factors of atrial fibrillation complicated with cognitive impairment and the relationship between cardiac function parameters and the degree of cognitive impairment

OBJECTIVE

To explore the risk factors of Atrial Fibrillation (AF) with Cognitive Impairment (CI) and to analyze the relationship between cardiac function parameters and the degree of CI in patients.

METHODS

120 AF patients were selected, and Montreal Cognitive Assessment (MoCA) was used to distinguish between AF patients with and without CI. Univariate analysis and multivariate Logistic regression analysis were used to evaluate the impact of sociodemographic data, disease-related data, and clinical data on risk factors for AF with CI. Pearson's method was used to analyze the correlation between cardiac function parameters and cognitive function scores in AF patients.

RESULTS

There were 89 patients with CI and 31 patients without CI, and the MoCA scores of patients with CI were lower than those in patients without CI. Age, occupational status, educational level, combined smoking history, drinking history, and heart failure, as well as systolic blood pressure, diastolic blood pressure, total cholesterol, triglyceride, C-reactive protein, free thyroxine, free triiodothyronine, and D-dimer were risk factors for the patient with CI. Left atrial diameter, left ventricular end-diastolic diameter, left ventricular end-systolic diameter, and left atrial maximum volume in patients with CI were higher than those in patients without CI, and left ventricular ejection fraction and peak early diastolic velocity/peak late-diastolic mitral velocity ratio were lower.

CONCLUSION

The cardiac function parameters of patients are closely related to attention, orientation, memory, visuospatial, and executive ability. Cardiac function parameters were closely related to cognitive functions.

Visualized Lead Selection for Arrhythmia Classification Based on a Lead Activation Heatmap Using Multi-Lead ECGs

Visualizing the decision-making process is a key aspect of research regarding explainable arrhythmia recognition. This study proposed a visualized lead selection method to classify arrhythmia for multi-lead ECG signals. The proposed method has several advantages, as it uses a visualized approach to select effective leads, avoiding redundant leads and invalid information. It also captures the temporal dependencies of ECG signals and the complementary information between leads. The method deployed a lead activation heatmap (LA heatmap) based on a lead-wise network to select the proper 5 leads from 12-lead ECG heartbeats extracted from the public 2018 Chinese Physiological Signal Challenge database (CPSC 2018 DB), which were then fed into a ResBiTime network combining bidirectional long short-term memory (Bi-LSTM) networks and residual connections for a classification task of nine heartbeat categories (i.e., N, AF, I-AVB, RBBB, PAC, PVC, STD, LBBB, and STE). The results indicate an average precision of 93.25%, an average recall of 93.03%, an average F1-score of 0.9313, and that the proposed method can effectively extract additional information from ECG heartbeat data.

xECGArch: a trustworthy deep learning architecture for interpretable ECG analysis considering short-term and long-term features

Deep learning-based methods have demonstrated high classification performance in the detection of cardiovascular diseases from electrocardiograms (ECGs). However, their blackbox character and the associated lack of interpretability limit their clinical applicability. To overcome existing limitations, we present a novel deep learning architecture for interpretable ECG analysis (xECGArch). For the first time, short- and long-term features are analyzed by two independent convolutional neural networks (CNNs) and combined into an ensemble, which is extended by methods of explainable artificial intelligence (xAI) to whiten the blackbox. To demonstrate the trustworthiness of xECGArch, perturbation analysis was used to compare 13 different xAI methods. We parameterized xECGArch for atrial fibrillation (AF) detection using four public ECG databases ( n = 9854 ECGs) and achieved an F1 score of 95.43% in AF versus non-AF classification on an unseen ECG test dataset. A systematic comparison of xAI methods showed that deep Taylor decomposition provided the most trustworthy explanations ( + 24 % compared to the second-best approach). xECGArch can account for short- and long-term features corresponding to clinical features of morphology and rhythm, respectively. Further research will focus on the relationship between xECGArch features and clinical features, which may help in medical applications for diagnosis and therapy.

Contemporary Advances in Cardiac Remote Monitoring: A Comprehensive, Updated Mini-Review

Over the past decade, remote monitoring (RM) has become an increasingly popular way to improve healthcare and health outcomes. Modern cardiac implantable electronic devices (CIEDs) are capable of recording an increasing amount of data related to CIED function, arrhythmias, physiological status and hemodynamic parameters, providing in-depth and updated information on patient cardiovascular function. The extensive use of RM for patients with CIED allows for early diagnosis and rapid assessment of relevant issues, both clinical and technical, as well as replacing outpatient follow-up improving overall management without compromise safety. This approach is recommended by current guidelines for all eligible patients affected by different chronic cardiac conditions including either brady- and tachy-arrhythmias and heart failure. Beyond to clinical advantages, RM has demonstrated cost-effectiveness and is associated with elevated levels of patient satisfaction. Future perspectives include improving security, interoperability and diagnostic power as well as to engage patients with digital health technology. This review aims to update existing data concerning clinical outcomes in patients managed with RM in the wide spectrum of cardiac arrhythmias and Hear Failure (HF), disclosing also about safety, effectiveness, patient satisfaction and cost-saving.

Automated identification of atrial fibrillation from single-lead ECGs using multi-branching ResNet

Introduction: Atrial fibrillation (AF) is the most common cardiac arrhythmia, which is clinically identified with irregular and rapid heartbeat rhythm. AF puts a patient at risk of forming blood clots, which can eventually lead to heart failure, stroke, or even sudden death. Electrocardiography (ECG), which involves acquiring bioelectrical signals from the body surface to reflect heart activity, is a standard procedure for detecting AF. However, the occurrence of AF is often intermittent, costing a significant amount of time and effort from medical doctors to identify AF episodes. Moreover, human error is inevitable, as even experienced medical professionals can overlook or misinterpret subtle signs of AF. As such, it is of critical importance to develop an advanced analytical model that can automatically interpret ECG signals and provide decision support for AF diagnostics. Methods: In this paper, we propose an innovative deep-learning method for automated AF identification using single-lead ECGs. We first extract time-frequency features from ECG signals using continuous wavelet transform (CWT). Second, the convolutional neural networks enhanced with residual learning (ReNet) are employed as the functional approximator to interpret the time-frequency features extracted by CWT. Third, we propose to incorporate a multi-branching structure into the ResNet to address the issue of class imbalance, where normal ECGs significantly outnumber instances of AF in ECG datasets. Results and Discussion: We evaluate the proposed Multi-branching Resnet with CWT (CWT-MB-Resnet) with two ECG datasets, i.e., PhysioNet/CinC challenge 2017 and ECGs obtained from the University of Oklahoma Health Sciences Center (OUHSC). The proposed CWT-MB-Resnet demonstrates robust prediction performance, achieving an F1 score of 0.8865 for the PhysioNet dataset and 0.7369 for the OUHSC dataset. The experimental results signify the model's superior capability in balancing precision and recall, which is a desired attribute for ensuring reliable medical diagnoses.

Non-invasive estimation of atrial fibrillation driver position using long-short term memory neural networks and body surface potentials

BACKGROUND AND OBJECTIVE

Atrial Fibrillation (AF) is a supraventricular tachyarrhythmia that can lead to thromboembolism, hearlt failure, ischemic stroke, and a decreased quality of life. Characterizing the locations where the mechanisms of AF are initialized and maintained is key to accomplishing an effective ablation of the targets, hence restoring sinus rhythm. Many methods have been investigated to locate such targets in a non-invasive way, such as Electrocardiographic Imaging, which enables an on-invasive and panoramic characterization of cardiac electrical activity using recording Body Surface Potentials (BSP) and a torso model of the patient. Nonetheless, this technique entails some major issues stemming from solving the inverse problem, which is known to be severely ill-posed. In this context, many machine learning and deep learning approaches aim to tackle the characterization and classification of AF targets to improve AF diagnosis and treatment.

METHODS

In this work, we propose a method to locate AF drivers as a supervised classification problem. We employed a hybrid form of the convolutional-recurrent network which enables feature extraction and sequential data modeling utilizing labeled realistic computerized AF models. Thus, we used 16 AF electrograms, 1 atrium, and 10 torso geometries to compute the forward problem. Previously, the AF models were labeled by assigning each sample of the signals a region from the atria from 0 (no driver) to 7, according to the spatial location of the AF driver. The resulting 160 BSP signals, which resemble a 64-lead vest recording, are preprocessed and then introduced into the network following a 4-fold cross-validation in batches of 50 samples.

RESULTS

The results show a mean accuracy of 74.75% among the 4 folds, with a better performance in detecting sinus rhythm, and drivers near the left superior pulmonary vein (R1), and right superior pulmonary vein (R3) whose mean sensitivity bounds around 84%-87%. Significantly good results are obtained in mean sensitivity (87%) and specificity (83%) in R1.

CONCLUSIONS

Good results in R1 are highly convenient since AF drivers are commonly found in this area: the left atrial appendage, as suggested in some previous studies. These promising results indicate that using CNN-LSTM networks could lead to new strategies exploiting temporal correlations to address this challenge effectively.

Design and technical validation to generate a synthetic 12-lead electrocardiogram dataset to promote artificial intelligence research

Purpose

The purpose of this study is to construct a synthetic dataset of ECG signal that overcomes the sensitivity of personal information and the complexity of disclosure policies.

Methods

The public dataset was constructed by generating synthetic data based on the deep learning model using a convolution neural network (CNN) and bi-directional long short-term memory (Bi-LSTM), and the effectiveness of the dataset was verified by developing classification models for ECG diagnoses.

Results

The synthetic 12-lead ECG dataset generated consists of a total of 6000 ECGs, with normal and 5 abnormal groups. The synthetic ECG signal has a waveform pattern similar to the original ECG signal, the average RMSE between the two signals is 0.042 µV, and the average cosine similarity is 0.993. In addition, five classification models were developed to verify the effect of the synthetic dataset and showed performance similar to that of the model made with the actual dataset. In particular, even when the real dataset was applied as a test set to the classification model trained with the synthetic dataset, the classification performance of all models showed high accuracy (average accuracy 93.41%).

Conclusion

The synthetic 12-lead ECG dataset was confirmed to perform similarly to the real-world 12-lead ECG in the classification model. This implies that a synthetic dataset can perform similarly to a real dataset in clinical research using AI. The synthetic dataset generation process in this study provides a way to overcome the medical data disclosure challenges constrained by privacy rights, a way to encourage open data policies, and contribute significantly to promoting cardiovascular disease research.

Forecasting imminent atrial fibrillation in long-term electrocardiogram recordings

BACKGROUND

Despite the morbidity associated with acute atrial fibrillation (AF), no models currently exist to forecast its imminent onset. We sought to evaluate the ability of deep learning to forecast the imminent onset of AF with sufficient lead time, which has important implications for inpatient care.

METHODS

We utilized the Physiobank Long-Term AF Database, which contains 24-h, labeled ECG recordings from patients with a history of AF. AF episodes were defined as ≥5 min of sustained AF. Three deep learning models incorporating convolutional and transformer layers were created for forecasting, with two models focusing on the predictive nature of sinus rhythm segments and AF epochs separately preceding an AF episode, and one model utilizing all preceding waveform as input. Cross-validated performance was evaluated using area under time-dependent receiver operating characteristic curves (AUC(t)) at 7.5-, 15-, 30-, and 60-min lead times, precision-recall curves, and imminent AF risk trajectories.

RESULTS

There were 367 AF episodes from 84 ECG recordings. All models showed average risk trajectory divergence of those with an AF episode from those without ∼15 min before the episode. Highest AUC was associated with the sinus rhythm model [AUC = 0.74; 7.5-min lead time], though the model using all preceding waveform data had similar performance and higher AUCs at longer lead times.

CONCLUSIONS

In this proof-of-concept study, we demonstrated the potential utility of neural networks to forecast the onset of AF in long-term ECG recordings with a clinically relevant lead time. External validation in larger cohorts is required before deploying these models clinically.

A Residual-Dense-Based Convolutional Neural Network Architecture for Recognition of Cardiac Health Based on ECG Signals

Cardiovascular disorders are often diagnosed using an electrocardiogram (ECG). It is a painless method that mimics the cyclical contraction and relaxation of the heart's muscles. By monitoring the heart's electrical activity, an ECG can be used to identify irregular heartbeats, heart attacks, cardiac illnesses, or enlarged hearts. Numerous studies and analyses of ECG signals to identify cardiac problems have been conducted during the past few years. Although ECG heartbeat classification methods have been presented in the literature, especially for unbalanced datasets, they have not proven to be successful in recognizing some heartbeat categories with high performance. This study uses a convolutional neural network (CNN) model to combine the benefits of dense and residual blocks. The objective is to leverage the benefits of residual and dense connections to enhance information flow, gradient propagation, and feature reuse, ultimately improving the model's performance. This proposed model consists of a series of residual-dense blocks interleaved with optional pooling layers for downsampling. A linear support vector machine (LSVM) classified heartbeats into five classes. This makes it easier to learn and represent features from ECG signals. We first denoised the gathered ECG data to correct issues such as baseline drift, power line interference, and motion noise. The impacts of the class imbalance are then offset by resampling techniques that denoise ECG signals. An RD-CNN algorithm is then used to categorize the ECG data for the various cardiac illnesses using the retrieved characteristics. On two benchmarked datasets, we conducted extensive simulations and assessed several performance measures. On average, we have achieved an accuracy of 98.5%, a sensitivity of 97.6%, a specificity of 96.8%, and an area under the receiver operating curve (AUC) of 0.99. The effectiveness of our suggested method for detecting heart disease from ECG data was compared with several recently presented algorithms. The results demonstrate that our method is lightweight and practical, qualifying it for continuous monitoring applications in clinical settings for automated ECG interpretation to support cardiologists.

A Systematic Review of Machine Learning and IoT Applied to the Prediction and Monitoring of Cardiovascular Diseases

According to the Pan American Health Organization, cardiovascular disease is the leading cause of death worldwide, claiming an estimated 17.9 million lives each year. This paper presents a systematic review to highlight the use of IoT, IoMT, and machine learning to detect, predict, or monitor cardiovascular disease. We had a final sample of 164 high-impact journal papers, focusing on two categories: cardiovascular disease detection using IoT/IoMT technologies and cardiovascular disease using machine learning techniques. For the first category, we found 82 proposals, while for the second, we found 85 proposals. The research highlights list of IoT/IoMT technologies, machine learning techniques, datasets, and the most discussed cardiovascular diseases. Neural networks have been popularly used, achieving an accuracy of over 90%, followed by random forest, XGBoost, k-NN, and SVM. Based on the results, we conclude that IoT/IoMT technologies can predict cardiovascular diseases in real time, ensemble techniques obtained one of the best performances in the accuracy metric, and hypertension and arrhythmia were the most discussed diseases. Finally, we identified the lack of public data as one of the main obstacles for machine learning approaches for cardiovascular disease prediction.

Detection of Atrial Fibrillation based on Feature Fusion using Attention-based BiLSTM

Atrial fibrillation (AF) is a common cardiac arrhythmia, and its early detection is crucial for timely treatment. Conventional methods, such as Electrocardiogram (ECG), can be intrusive and require specialized equipment, whereas Photoplethysmography (PPG) offers a non-invasive alternative. In this study, we present a feature fusion approach for AF detection using attention-based Bidirectional Long Short-Term Memory (BiLSTM) and PPG signals. We extract frequency domain (FD) and time domain (TD) features from PPG signals, combine them with deep learning features generated from an attention-based BiLSTM network, and pass the fusion features through a softmax function. Our approach achieves high accuracy (96.5%) and favorable performance metrics (recall 93.20%, precision 94.50%, and F-score 93.09%), improving AF prediction and diagnosis, and providing support for clinicians in their diagnostic processes.

Electrocardiogram Monitoring Wearable Devices and Artificial-Intelligence-Enabled Diagnostic Capabilities: A Review

Worldwide, population aging and unhealthy lifestyles have increased the incidence of high-risk health conditions such as cardiovascular diseases, sleep apnea, and other conditions. Recently, to facilitate early identification and diagnosis, efforts have been made in the research and development of new wearable devices to make them smaller, more comfortable, more accurate, and increasingly compatible with artificial intelligence technologies. These efforts can pave the way to the longer and continuous health monitoring of different biosignals, including the real-time detection of diseases, thus providing more timely and accurate predictions of health events that can drastically improve the healthcare management of patients. Most recent reviews focus on a specific category of disease, the use of artificial intelligence in 12-lead electrocardiograms, or on wearable technology. However, we present recent advances in the use of electrocardiogram signals acquired with wearable devices or from publicly available databases and the analysis of such signals with artificial intelligence methods to detect and predict diseases. As expected, most of the available research focuses on heart diseases, sleep apnea, and other emerging areas, such as mental stress. From a methodological point of view, although traditional statistical methods and machine learning are still widely used, we observe an increasing use of more advanced deep learning methods, specifically architectures that can handle the complexity of biosignal data. These deep learning methods typically include convolutional and recurrent neural networks. Moreover, when proposing new artificial intelligence methods, we observe that the prevalent choice is to use publicly available databases rather than collecting new data.

Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model

BACKGROUND AND OBJECTIVES

Atrial fibrillation (AF) is one of the most common arrhythmias clinically. Aging tends to increase the risk of AF, which also increases the burden of other comorbidities, including coronary artery disease (CAD), and even heart failure (HF). The precise detection of AF is a challenge due to its intermittence and unpredictability. A method for the accurate detection of AF is still needed.

METHODS

A deep learning model was used to detect atrial fibrillation. Here, a distinction was not made between AF and atrial flutter (AFL), both of which manifest as a similar pattern on an electrocardiogram (ECG). This method not only discriminated AF from normal rhythm of the heart, but also detected its onset and offset. The proposed model involved residual blocks and a Transformer encoder.

RESULTS AND CONCLUSIONS

The data used for training were obtained from the CPSC2021 Challenge, and were collected using dynamic ECG devices. Tests on four public datasets validated the availability of the proposed method. The best performance for AF rhythm testing attained an accuracy of 98.67%, a sensitivity of 87.69%, and a specificity of 98.56%. In onset and offset detection, it obtained a sensitivity of 95.90% and 87.70%, respectively. The algorithm with a low FPR of 0.46% was able to reduce troubling false alarms. The model had a great capability to discriminate AF from normal rhythm and to detect its onset and offset. Noise stress tests were conducted after mixing three types of noise. We visualized the model's features using a heatmap and illustrated its interpretability. The model focused directly on the crucial ECG waveform where showed obvious characteristics of AF.

Automatic screening of patients with atrial fibrillation from 24-h Holter recording using deep learning

Aims

As the demand for atrial fibrillation (AF) screening increases, clinicians spend a significant amount of time identifying AF signals from massive amounts of data obtained during long-term dynamic electrocardiogram (ECG) monitoring. The identification of AF signals is subjective and depends on the experience of clinicians. However, experienced cardiologists are scarce. This study aimed to apply a deep learning-based algorithm to fully automate primary screening of patients with AF using 24-h Holter monitoring.

Methods and results

A deep learning model was developed to automatically detect AF episodes using RR intervals and was trained and evaluated on 23 621 (2297 AF and 21 324 non-AF) 24-h Holter recordings from 23 452 patients. Based on the AF episode detection results, patients with AF were automatically identified using the criterion of at least one AF episode lasting 6 min or longer. Performance was assessed on an independent real-world hospital-scenario test set (19 227 recordings) and a community-scenario test set (1299 recordings). For the two test sets, the model obtained high performance for the identification of patients with AF (sensitivity: 0.995 and 1.000; specificity: 0.985 and 0.997, respectively). Moreover, it obtained good and consistent performance (sensitivity: 1.000; specificity: 0.972) for an external public data set.

Conclusion

Using the criterion of at least one AF episode of 6 min or longer, the deep learning model can fully automatically screen patients for AF with high accuracy from long-term Holter monitoring data. This method may serve as a powerful and cost-effective tool for primary screening for AF.

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.

Fuzz-ClustNet: Coupled fuzzy clustering and deep neural networks for Arrhythmia detection from ECG signals

Electrocardiogram (ECG) is a widely used technique to diagnose cardiovascular diseases. It is a non-invasive technique that represents the cyclic contraction and relaxation of heart muscles. ECG can be used to detect abnormal heart motions, heart attacks, heart diseases, or enlarged hearts by measuring the heart's electrical activity. Over the past few years, various works have been done in the field of studying and analyzing the ECG signals to detect heart diseases. In this work, we propose a deep learning and fuzzy clustering (Fuzz-ClustNet) based approach for Arrhythmia detection from ECG signals. We started by denoising the collected ECG signals to remove errors like baseline drift, power line interference, motion noise, etc. The denoised ECG signals are then segmented to have an increased focus on the ECG signals. We then perform data augmentation on the segmented images to counter the effects of the class imbalance. The augmented images are then passed through a CNN feature extractor. The extracted features are then passed to a fuzzy clustering algorithm to classify the ECG signals for their respective cardio diseases. We ran intensive simulations on two benchmarked datasets and evaluated various performance metrics. The performance of our proposed algorithm was compared with several recently proposed algorithms for heart disease detection from ECG signals. The obtained results demonstrate the efficacy of our proposed approach as compared to other contemporary algorithms.

Comparison of ANN and ANFIS Models for AF Diagnosis Using RR Irregularities

Classification of normal sinus rhythm (NSR), paroxysmal atrial fibrillation (PAF), and persistent atrial fibrillation (AF) is crucial in order to diagnose and effectively plan treatment for patients. Current classification models were primarily developed by electrocardiogram (ECG) signal databases, which may be unsuitable for local patients. Therefore, this research collected ECG signals from 60 local Thai patients (age 52.53 ± 23.92) to create a classification model. The coefficient of variance (CV), the median absolute deviation (MAD), and the root mean square of the successive differences (RMSSD) are ordinary feature variables of RR irregularities used by existing models. The square of average variation (SAV) is a newly proposed feature that extracts from the irregularity of RR intervals. All variables were found to be statistically different using ANOVA tests and Tukey’s method with a p-value less than 0.05. The methods of artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) were also tested and compared to find the best classification model. Finally, SAV showed the best performance using the ANFIS model with trapezoidal membership function, having the highest system accuracy (ACC) at 89.33%, sensitivity (SE), specificity (SP), and positive predictivity (PPR) for NSR at 100.00%, 94.00%, and 89.29%, PAF at 88.00%, 90.57%, and 81.48%, and AF at 80.00%, 96.00%, and 90.91%, respectively.

Multiple high-regional-incidence cardiac disease diagnosis with deep learning and its potential to elevate cardiologist performance

Currently, due to lack of large-scale datasets containing multiple arrhythmias and acute coronary syndrome-related diseases, AI-aided diagnosis for cardiac diseases is limited in clinical scenarios. Whether AI-based ECG diagnosis can assist cardiologists to improve performance has not been reported. We constructed a large-scale dataset containing multiple high-regional-incidence arrhythmias and ACS-related diseases, including 162,622 12-lead ECGs collected between January 2018 and March 2021. We presented a deep learning model for clinical ECG diagnosis of multiple cardiac diseases. Results show that our model for diagnosing 15 cardiac abnormalities achieved 88.216% accuracy, and its average AUC ROC score reached 0.961. On the board-certified re-annotated dataset, its performance surpasses that of cardiologists in non-reference group. Moreover, with aid of labels given by our model, accuracy and efficiency for cardiologist increased by 13.5% and 69.9% than non-reference group. Our approach provides solutions for AI-aided diagnosis systems of cardiac diseases in applications.

Automated diagnosis of atrial fibrillation using ECG component-aware transformer

Atrial fibrillation (AF) is the most common sustained arrhythmia worldwide and imposes a substantial economic burden on the public healthcare system due to its high morbidity and mortality. Early detection of AF is crucial in providing timely treatment and preventing complications such as stroke and other thromboembolism. For AF diagnosis, the 12-lead electrocardiogram (ECG) has been established as the gold standard. However, it requires the clinical experiences of cardiologists and may be vulnerable to inter-observer variability. Although automated AF diagnostic techniques based on deep neural networks (DNN) have been proposed, most studies were conducted using small-scale datasets, resulting in the over-fitting problem. Furthermore, they have not fully exploited ECG components such as P-wave, QRS-complex, and T-wave contrary to the approach adopted by cardiologists who interpret ECG by considering its components. To overcome these limitations, this study presents the component-aware transformer (CAT), which segments the ECG waveform into each component, vectorizes them with length and types information into one vector, and used it as the input of the transformer. We conducted extensive experiments to evaluate the CAT using a large-scale dataset called Shaoxing Hospital Zhejiang University School of Medicine database (AF: 1,780 cases, non-AF: 8,866 cases). The quantitative evaluations demonstrate that the CAT outperforms the conventional deep learning techniques on both single- and 12-lead ECG signals. Moreover, the CAT trained on single-lead ECG is comparable to that of a 12-lead analysis, while conventional methods degraded significantly in performance. Consequently, the CAT is applicable to various single-channel signals such as airway pressure, photoplethysmogram, and blood pressure.

A systematic review and Meta-data analysis on the applications of Deep Learning in Electrocardiogram

The success of deep learning over the traditional machine learning techniques in handling artificial intelligence application tasks such as image processing, computer vision, object detection, speech recognition, medical imaging and so on, has made deep learning the buzz word that dominates Artificial Intelligence applications. From the last decade, the applications of deep learning in physiological signals such as electrocardiogram (ECG) have attracted a good number of research. However, previous surveys have not been able to provide a systematic comprehensive review including biometric ECG based systems of the applications of deep learning in ECG with respect to domain of applications. To address this gap, we conducted a systematic literature review on the applications of deep learning in ECG including biometric ECG based systems. The study analyzed systematically, 150 primary studies with evidence of the application of deep learning in ECG. The study shows that the applications of deep learning in ECG have been applied in different domains. We presented a new taxonomy of the domains of application of the deep learning in ECG. The paper also presented discussions on biometric ECG based systems and meta-data analysis of the studies based on the domain, area, task, deep learning models, dataset sources and preprocessing methods. Challenges and potential research opportunities were highlighted to enable novel research. We believe that this study will be useful to both new researchers and expert researchers who are seeking to add knowledge to the already existing body of knowledge in ECG signal processing using deep learning algorithm.

Supplementary information

The online version contains supplementary material available at 10.1007/s12652-022-03868-z.

Semi-supervised learning for automatic atrial fibrillation detection in 24-hour Holter monitoring

Paroxysmal atrial fibrillation (AF) is generally diagnosed by long-term dynamic electrocardiogram (ECG) monitoring. Identifying AF episodes from long-term ECG data can place a heavy burden on clinicians. Many machine-learning-based automatic AF detection methods have been proposed to solve this issue. However, these methods require numerous annotated data to train the model, and the annotation of AF in long-term ECG is extremely time-consuming. Reducing the demand for labeled data can effectively improve the clinical practicability of automatic AF detection methods. In this study, we developed a novel semi-supervised learning method that generated modified low-entropy labels of unlabeled samples for training a deep learning model to automatically detect paroxysmal AF in 24 h Holter monitoring data. Our method employed a 1D CNN-LSTM neural network with RR intervals as input and used few labeled training data with numerous unlabeled data for training the neural network. This method was evaluated using a 24 h Holter monitoring dataset collected from 1000 paroxysmal AF patients. Using labeled samples from only 10 patients for model training, our method achieved a sensitivity of 97.8%, specificity of 97.9%, and accuracy of 97.9% in five-fold cross-validation. Compared to the supervised learning method with complete labeled samples, the detection accuracy of our method was only 0.5% lower, while the workload of data annotation was significantly reduced by more than 98%. In general, this is the first study to apply semi-supervised learning techniques for automatic AF detection using ECG. Our method can effectively reduce the demand for AF data annotations and can improve the clinical practicability of automatic AF detection.

State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint)

Background

Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals.

Objective

This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications.

Methods

The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches.

Results

We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models.

Conclusions

We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.

Artificial intelligence for the detection, prediction, and management of atrial fibrillation

The present article reviews the state of the art of machine learning algorithms for the detection, prediction, and management of atrial fibrillation (AF), as well as of the development and evaluation of artificial intelligence (AI) in cardiology and beyond. Today, AI detects AF with a high accuracy using 12-lead or single-lead electrocardiograms or photoplethysmography. The prediction of paroxysmal or future AF currently operates at a level of precision that is too low for clinical use. Further studies are needed to determine whether patient selection for interventions may be possible with machine learning.

Efficient on-site confirmatory testing for atrial fibrillation with derived 12-lead ECG in a wireless body area network

Smartphones that can support and assist the screening of various cardiovascular diseases are gaining popularity in recent years. The timely detection, diagnosis, and treatment of atrial fibrillation (AF) are critical, especially for those who are at risk of stroke. AF detection via screening with wearable devices should always be confirmed by a standard 12-lead electrocardiogram (ECG). However, the inability to perform on-site AF confirmatory testing results in increased patient anxiety, followed by unnecessary diagnostic procedures and treatments. Also, the delay in confirmation procedure may conclude the condition as non-AF while it was indeed present at the time of screening. To overcome these challenges, we propose an efficient on-site confirmatory testing for AF with 12-lead ECG derived from the reduced lead set (RLS) in a wireless body area network (WBAN) environment. The reduction in the number of leads enhances the comfort level of patients as well as minimizes the hurdles associated with continuous telemonitoring applications such as data transmission, storage, and bandwidth of the overall system. The proposed method is characterized by segment-wise regression and a lead selection algorithm, facilitating improved P-wave reconstruction. Further, an efficient AF detection algorithm is proposed by incorporating a novel three-level P-wave evidence score with an RR irregularity evidence score. The proposed on-site AF confirmation test reduces false positives and false negatives by 88% and 53% respectively, compared to single lead screening. In addition, the proposed lead derivation method improves accuracy, F 1 -score, and Matthews correlation coefficient (MCC) for the on-site AF detection compared to existing related methods.

Fully Elman Neural Network: A Novel Deep Recurrent Neural Network Optimized by an Improved Harris Hawks Algorithm for Classification of Pulmonary Arterial Wedge Pressure

Heart failure (HF) is one of the most prevalent life-threatening cardiovascular diseases in which 6.5 million people are suffering in the USA and more than 23 million worldwide. Mechanical circulatory support of HF patients can be achieved by implanting a left ventricular assist device (LVAD) into HF patients as a bridge to transplant, recovery or destination therapy and can be controlled by measurement of normal and abnormal pulmonary arterial wedge pressure (PAWP). While there are no commercial long-term implantable pressure sensors to measure PAWP, real-time non-invasive estimation of abnormal and normal PAWP becomes vital. In this work, first an improved Harris Hawks optimizer algorithm called HHO+ is presented and tested on 24 unimodal and multimodal benchmark functions. Second, a novel fully Elman neural network (FENN) is proposed to improve the classification performance. Finally, four novel 18-layer deep learning methods of convolutional neural networks (CNNs) with multi-layer perceptron (CNN-MLP), CNN with Elman neural networks (CNN-ENN), CNN with fully Elman neural networks (CNN-FENN), and CNN with fully Elman neural networks optimized by HHO+ algorithm (CNN-FENN-HHO+) for classification of abnormal and normal PAWP using estimated HVAD pump flow were developed and compared. The estimated pump flow was derived by a non-invasive method embedded into the commercial HVAD controller. The proposed methods are evaluated on an imbalanced clinical dataset using 5-fold cross-validation. The proposed CNN-FENN-HHO+ method outperforms the proposed CNN-MLP, CNN-ENN and CNN-FENN methods and improved the classification performance metrics across 5-fold cross-validation with an average sensitivity of 79%, accuracy of 78% and specificity of 76%. The proposed methods can reduce the likelihood of hazardous events like pulmonary congestion and ventricular suction for HF patients and notify identified abnormal cases to the hospital, clinician and cardiologist for emergency action, which can diminish the mortality rate of patients with HF.

Review of Deep Learning-Based Atrial Fibrillation Detection Studies

Atrial fibrillation (AF) is a common arrhythmia that can lead to stroke, heart failure, and premature death. Manual screening of AF on electrocardiography (ECG) is time-consuming and prone to errors. To overcome these limitations, computer-aided diagnosis systems are developed using artificial intelligence techniques for automated detection of AF. Various machine learning and deep learning (DL) techniques have been developed for the automated detection of AF. In this review, we focused on the automated AF detection models developed using DL techniques. Twenty-four relevant articles published in international journals were reviewed. DL models based on deep neural network, convolutional neural network (CNN), recurrent neural network, long short-term memory, and hybrid structures were discussed. Our analysis showed that the majority of the studies used CNN models, which yielded the highest detection performance using ECG and heart rate variability signals. Details of the ECG databases used in the studies, performance metrics of the various models deployed, associated advantages and limitations, as well as proposed future work were summarized and discussed. This review paper serves as a useful resource for the researchers interested in developing innovative computer-assisted ECG-based DL approaches for AF detection.

Considerations on Performance Evaluation of Atrial Fibrillation Detectors

OBJECTIVE

A large number of atrial fibrillation (AF) detectors have been published in recent years, signifying that the comparison of detector performance plays a central role, though not always consistent. The aim of this study is to shed needed light on aspects crucial to the evaluation of detection performance.

METHODS

Three types of AF detector, using either information on rhythm, rhythm and morphology, or segments of ECG samples, are implemented and studied on both real and simulated ECG signals. The properties of different performance measures are investigated, for example, in relation to dataset imbalance.

RESULTS

The results show that performance can differ considerably depending on the way detector output is compared to database annotations, i.e., beat-to-beat, segment-to-segment, or episode-to-episode comparison. Moreover, depending on the type of detector, the results substantiate that physiological and technical factors, e.g., changes in ECG morphology, rate of atrial premature beats, and noise level, can have a considerable influence on performance.

CONCLUSION

The present study demonstrates overall strengths and weaknesses of different types of detector, highlights challenges in AF detection, and proposes five recommendations on how to handle data and characterize performance.

Global hybrid multi-scale convolutional network for accurate and robust detection of atrial fibrillation using single-lead ECG recordings

BACKGROUND AND OBJECTIVE

Atrial fibrillation (AF) is the most common persistent cardiac arrhythmia in clinical practice, and its accurate screening is of great significance to avoid cardiovascular diseases (CVDs). Electrocardiogram (ECG) is considered to be the most commonly used technique for detecting AF abnormalities. However, previous ECG-based deep learning algorithms did not take into account the complementary nature of inter-layer information, which may lead to insufficient AF screening. This study reports the first attempt to use hybrid multi-scale information in a global space for accurate and robust AF detection.

METHODS

We propose a novel deep learning classification method, namely, global hybrid multi-scale convolutional neural network (i.e., GH-MS-CNN), to implement binary classification for AF detection. Unlike previous deep learning methods in AF detection, an ingenious hybrid multi-scale convolution (HMSC) module, for the advantage of automatically aggregating different types of complementary inter-layer multi-scale features in the global space, is introduced into all dense blocks of the GH-MS-CNN model to implement sufficient feature extraction, and achieve much better overall classification performance.

RESULTS

The proposed GH-MS-CNN method has been fully validated on the CPSC 2018 database and tested on the independent PhysioNet 2017 database. The experimental results show that the global and hybrid multi-scale information has tremendous advantages over local and single-type multi-scale information in AF screening. Furthermore, the proposed GH-MS-CNN method outperforms the state-of-the-art methods and achieves the best classification performance with an accuracy of 0.9984, a precision of 0.9989, a sensitivity of 0.9965, a specificity of 0.9998 and an F1 score of 0.9954. In addition, the proposed method has achieved comparable and considerable generalization capability on the PhysioNet 2017 database.

CONCLUSIONS

The proposed GH-MS-CNN method has promising capabilities and great advantages in accurate and robust AF detection. It is assumed that this research has made significant improvements in AF screening and has great potential for long-term monitoring of wearable devices.

Automatic Detection of Short-Term Atrial Fibrillation Segments Based on Frequency Slice Wavelet Transform and Machine Learning Techniques

Atrial fibrillation (AF) is the most frequently encountered cardiac arrhythmia and is often associated with other cardiovascular and cerebrovascular diseases, such as ischemic heart disease, chronic heart failure, and stroke. Automatic detection of AF by analyzing electrocardiogram (ECG) signals has an important application value. Using the contaminated and actual ECG signals, it is not enough to only analyze the atrial activity of disappeared P wave and appeared F wave in the TQ segment. Moreover, the best analysis method is to combine nonlinear features analyzing ventricular activity based on the detection of R peak. In this paper, to utilize the information of the P-QRS-T waveform generated by atrial and ventricular activity, frequency slice wavelet transform (FSWT) is adopted to conduct time-frequency analysis on short-term ECG segments from the MIT-BIH Atrial Fibrillation Database. The two-dimensional time-frequency matrices are obtained. Furthermore, an average sliding window is used to convert the two-dimensional time-frequency matrices to the one-dimensional feature vectors, which are classified using five machine learning (ML) techniques. The experimental results show that the classification performance of the Gaussian-kernel support vector machine (GKSVM) based on the Bayesian optimizer is better. The accuracy of the training set and validation set are 100% and 93.4%. The accuracy, sensitivity, and specificity of the test set without training are 98.15%, 96.43%, and 100%, respectively. Compared with previous research results, our proposed FSWT-GKSVM model shows stability and robustness, and it could achieve the purpose of automatic detection of AF.

A Classification and Prediction Hybrid Model Construction with the IQPSO-SVM Algorithm for Atrial Fibrillation Arrhythmia

Atrial fibrillation (AF) is the most common cardiovascular disease (CVD), and most existing algorithms are usually designed for the diagnosis (i.e., feature classification) or prediction of AF. Artificial intelligence (AI) algorithms integrate the diagnosis of AF electrocardiogram (ECG) and predict the possibility that AF will occur in the future. In this paper, we utilized the MIT-BIH AF Database (AFDB), which is composed of data from normal people and patients with AF and onset characteristics, and the AFPDB database (i.e., PAF Prediction Challenge Database), which consists of data from patients with Paroxysmal AF (PAF; the records contain the ECG preceding an episode of PAF), and subjects who do not have documented AF. We extracted the respective characteristics of the databases and used them in modeling diagnosis and prediction. In the aspect of model construction, we regarded diagnosis and prediction as two classification problems, adopted the traditional support vector machine (SVM) algorithm, and combined them. The improved quantum particle swarm optimization support vector machine (IQPSO-SVM) algorithm was used to speed the training time. During the verification process, the clinical FZU-FPH database created by Fuzhou University and Fujian Provincial Hospital was used for hybrid model testing. The data were obtained from the Holter monitor of the hospital and encrypted. We proposed an algorithm for transforming the PDF ECG waveform images of hospital examination reports into digital data. For the diagnosis model and prediction model trained using the training set of the AFDB and AFPDB databases, the sensitivity, specificity, and accuracy measures were 99.2% and 99.2%, 99.2% and 93.3%, and 91.7% and 92.5% for the test set of the AFDB and AFPDB databases, respectively. Moreover, the sensitivity, specificity, and accuracy were 94.2%, 79.7%, and 87.0%, respectively, when tested using the FZU-FPH database with 138 samples of the ECG composed of two labels. The composite classification and prediction model using a new water-fall ensemble method had a total accuracy of approximately 91% for the test set of the FZU-FPH database with 80 samples with 120 segments of ECG with three labels.

AFibNet: an implementation of atrial fibrillation detection with convolutional neural network

Background

Generalization model capacity of deep learning (DL) approach for atrial fibrillation (AF) detection remains lacking. It can be seen from previous researches, the DL model formation used only a single frequency sampling of the specific device. Besides, each electrocardiogram (ECG) acquisition dataset produces a different length and sampling frequency to ensure sufficient precision of the R–R intervals to determine the heart rate variability (HRV). An accurate HRV is the gold standard for predicting the AF condition; therefore, a current challenge is to determine whether a DL approach can be used to analyze raw ECG data in a broad range of devices. This paper demonstrates powerful results for end-to-end implementation of AF detection based on a convolutional neural network (AFibNet). The method used a single learning system without considering the variety of signal lengths and frequency samplings. For implementation, the AFibNet is processed with a computational cloud-based DL approach. This study utilized a one-dimension convolutional neural networks (1D-CNNs) model for 11,842 subjects. It was trained and validated with 8232 records based on three datasets and tested with 3610 records based on eight datasets. The predicted results, when compared with the diagnosis results indicated by human practitioners, showed a 99.80% accuracy, sensitivity, and specificity.

Result

Meanwhile, when tested using unseen data, the AF detection reaches 98.94% accuracy, 98.97% sensitivity, and 98.97% specificity at a sample period of 0.02 seconds using the DL Cloud System. To improve the confidence of the AFibNet model, it also validated with 18 arrhythmias condition defined as Non-AF-class. Thus, the data is increased from 11,842 to 26,349 instances for three-class, i.e., Normal sinus (N), AF and Non-AF. The result found 96.36% accuracy, 93.65% sensitivity, and 96.92% specificity.

Conclusion

These findings demonstrate that the proposed approach can use unknown data to derive feature maps and reliably detect the AF periods. We have found that our cloud-DL system is suitable for practical deployment

The application of deep learning in electrocardiogram: Where we came from and where we should go?

Electrocardiogram (ECG) is a commonly-used, non-invasive examination recording cardiac voltage versus time traces over a period. Deep learning technology, a robust artificial intelligence algorithm, can imitate the data processing patterns of the human brain, and it has experienced remarkable success in disease screening, diagnosis, and prediction. Compared with traditional machine learning, deep learning algorithms possess more powerful learning capabilities and can automatically extract features without extensive data pre-processing or hand-crafted feature extraction, which makes it a suitable tool to analyze complex structures of high-dimensional data. With the advances in computing power and digitized data availability, deep learning provides us an opportunity to improve ECG data interpretation with higher efficacy and accuracy and, more importantly, expand the original functions of ECG. The application of deep learning has led us to stand at the edge of ECG innovation and will potentially change the current clinical monitoring and management strategies. In this review, we introduce deep learning technology and summarize its advantages compared with traditional machine learning algorithms. Moreover, we provide an overview on the current application of deep learning in ECGs, with a focus on arrhythmia (especially atrial fibrillation during normal sinus rhythm), cardiac dysfunction, electrolyte imbalance, and sleep apnea. Last but not least, we discuss the current challenges and prospect directions for the following studies.

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

There has been an exponential growth of artificial intelligence (AI) and machine learning (ML) publications aimed at advancing our understanding of atrial fibrillation (AF), which has been mainly driven by the confluence of two factors: the advances in deep neural networks (DeepNNs) and the availability of large, open access databases. It is observed that most of the attention has centred on applying ML for dvsetecting AF, particularly using electrocardiograms (ECGs) as the main data modality. Nearly a third of them used DeepNNs to minimize or eliminate the need for transforming the ECGs to extract features prior to ML modelling; however, we did not observe a significant advantage in following this approach. We also found a fraction of studies using other data modalities, and others centred in aims, such as risk prediction, AF management, and others. From the clinical perspective, AI/ML can help expand the utility of AF detection and risk prediction, especially for patients with additional comorbidities. The use of AI/ML for detection and risk prediction into applications and smart mobile health (mHealth) technology would enable ‘real time’ dynamic assessments. AI/ML could also adapt to treatment changes over time, as well as incident risk factors. Incorporation of a dynamic AI/ML model into mHealth technology would facilitate ‘real time’ assessment of stroke risk, facilitating mitigation of modifiable risk factors (e.g. blood pressure control). Overall, this would lead to an improvement in clinical care for patients with AF.

Clinical Application of Machine Learning-Based Artificial Intelligence in the Diagnosis, Prediction, and Classification of Cardiovascular Diseases

With the rapid development of artificial intelligence (AI) and machine learning (ML), as well as the arrival of the big data era, technological innovations have occurred in the field of cardiovascular medicine. First, the diagnosis of cardiovascular diseases (CVDs) is highly dependent on assistive examinations, the interpretation of which is time consuming and often limited by the knowledge level and clinical experience of doctors; however, AI could be used to automatically interpret the images obtained in auxiliary examinations. Second, some of the predictions of the incidence and prognosis of CVDs are limited in clinical practice by the use of traditional prediction models, but there may be occasions when AI-based prediction models perform well by using ML algorithms. Third, AI has been used to assist precise classification of CVDs by integrating a variety of medical data from patients, which helps better characterize the subgroups of heterogeneous diseases. To help clinicians better understand the applications of AI in CVDs, this review summarizes studies relating to AI-based diagnosis, prediction, and classification of CVDs. Finally, we discuss the challenges of applying AI to cardiovascular medicine.

Deep learning and the electrocardiogram: review of the current state-of-the-art

In the recent decade, deep learning, a subset of artificial intelligence and machine learning, has been used to identify patterns in big healthcare datasets for disease phenotyping, event predictions, and complex decision making. Public datasets for electrocardiograms (ECGs) have existed since the 1980s and have been used for very specific tasks in cardiology, such as arrhythmia, ischemia, and cardiomyopathy detection. Recently, private institutions have begun curating large ECG databases that are orders of magnitude larger than the public databases for ingestion by deep learning models. These efforts have demonstrated not only improved performance and generalizability in these aforementioned tasks but also application to novel clinical scenarios. This review focuses on orienting the clinician towards fundamental tenets of deep learning, state-of-the-art prior to its use for ECG analysis, and current applications of deep learning on ECGs, as well as their limitations and future areas of improvement.

Intelligent Diagnosis Method Based on 2DECG Model

Electrophysiological signals can effectively reflect various physiological states of human body, and provide favorable basis for medical diagnosis. However, the correct analysis of electrophysiological signals requires professional medical diagnosis experience. With the rapid development of artificial intelligence, intelligent diagnosis methods based on deep learning are gradually applied in the medical field in order to reduce the dependence of diagnosis results on medical experience. Deep learning has made remarkable achievements in the field of image processing, through which deeper information can be extracted than through time-series signals. Therefore, this paper proposes a method of 2DECG diagnosis based on Faster R-CNN (Faster Region-based Convolutional Neural Network). First, the time-series ECG signal is transformed into two-dimensional curve. Then, the Faster R-CNN model based on beat is obtained by using dataset training. Finally, three kinds of ECG diseases are diagnosed by the Faster R-CNN model. The test results show that compared with the effect of one-dimensional CNN, the method proposed in this paper has high diagnosis accuracy and can help doctors to diagnose diseases more intuitively.

Characterization of atrial arrhythmias in body surface potential mapping: A computational study

PURPOSE

Atrial tachycardia (AT), flutter (AFL) and fibrillation (AF) are very common cardiac arrhythmias and are driven by localized sources that can be ablation targets. Non-invasive body surface potential mapping (BSPM) can be useful for early diagnosis and ablation planning. We aimed to characterize and differentiate the arrhythmic mechanisms behind AT, AFL and AF from the BSPM perspective using basic features reflecting their electrophysiology.

METHODS

19 simulations of 567-lead BSPMs were used to obtain dominant frequency (DF) maps and estimate the atrial driving frequencies using the highest DF (HDF). Regions with |DF-HDF|≤1Hz were segmented and characterized (size, area); the spatial distribution of the differences |DF-atrialHDFestimate| was qualitatively analyzed. Phase singularity points (SPs) were detected on maps generated with Hilbert transform after band-pass filtering around the HDF (±1Hz). Connected SPs along time (filaments) and their histogram (heatmaps) were used for rotational activity characterization (duration, spatiotemporal stability). Results were reproduced in clinical layouts (252 to 12 leads) and with different rotations and translations of the atria within the torso, and compared with the original 567-lead outcomes using structural similarity index (SSIM) between maps, sensitivity and precision in SP detection and direct feature comparison. Random forest and least-square based algorithms were used to classify the arrhythmias and their mechanisms' location, respectively, based on the obtained features.

RESULTS

Frequency and phase analyses revealed distinct behavior between arrhythmias. AT and AFL presented uniform DF maps with low variance, while AF maps were more heterogeneous. Lower differences from the atrial HDF regions correlated with the driver location. Rotational activity was most stable in AFL, followed by AT and AF. Features were robust to lower spatial resolution layouts and modifications in the atrial geometry; DF and heatmaps presented decreasing SSIM along the layouts. The classification of the arrhythmias and their mechanisms' location achieved balanced accuracy of 72.0% and 73.9%, respectively.

CONCLUSION

Non-invasive characterization of AT, AFL and AF based on realistic models highlights intrinsic differences between the arrhythmias, enhancing the BSPM utility as an auxiliary clinical tool.