Automatic Detection Of Atrial Fibrillation Research Articles

An explainable AI for trustworthy detection of atrial fibrillation on reduced lead ECGs in mobile applications

Abstract Introduction Artificial intelligence (AI), particularly deep learning (DL), has demonstrated high performance in various diagnostic problems, including the detection of paroxysmal atrial fibrillation (AF) from electrocardiograms (ECGs). In mobile applications, these approaches can help to detect AF at an early stage and thus prevent possible secondary diseases. However, due to their black-box nature, DL approaches lack explainability and interpretability. Furthermore, 12-lead ECGs are the clinical standard, but mobile devices usually only provide 1–3 leads, which are similar but not identical to Einthoven leads and differ in morphology. Purpose We apply a recently introduced explainable ECG analysis architecture (xECGArch) to single-lead ECGs to verify its performance in mobile applications. xECGArch can learn rhythmic and morphological characteristics using two parallel convolutional neural networks of different dimensions (Fig. 1). When combined with methods from explainable AI, the classification can be traced back to rhythmic and morphological characteristics. Methods We used a subset of 9 854 ECGs (n(AF) = n(non-AF) = 4 927) from 4 public databases (Chapman-Shaoxing, CPSC2018, Georgia, and PTB-XL). Noise was removed using a cascade of high-pass filtering at 0.3 Hz and discrete wavelet transform. For each lead, we trained xECGArch on single-lead ECGs of 10 s length to classify AF vs. non-AF using 90% of the ECGs with 5-fold cross-validation and tested it on the remaining randomly selected ECGs (n(AF) = 507, n(non-AF) = 479). Consistent data splitting was ensured for all leads. Model explanations were generated using deep Taylor decomposition. Results Both models achieved minimum 91.1% accuracy for each ECG lead (Fig. 1). On lead I, the morphology model outperformed the rhythm model with 92.8% vs. 91.5% accuracy, while the rhythm model slightly outperformed the morphology model on leads II and III with 94.2%–95.0% accuracy vs. 91.1%–94.0%. Both models achieved maximum accuracy of 95.0% (rhythm) and 94.0% (morphology) on lead II. By combining both models, xECGArch reached 93.7%–95.1% accuracy. The model explanations confirm that the rhythm model primarily considers QRS complexes as relevant, while the morphology model focuses on fibrillatory waves (Fig. 1). Conclusions Both rhythm and morphology models achieved reliable results across all leads, competing with the state-of-the-art for automatic AF detection from single-lead ECGs. The combination of both models in xECGArch further increased the accuracy. xECGArch is based on the medical reading of ECGs by considering rhythm and morphology characteristics and is therefore interpretable by design. The model explanations are consistent with the diagnostic criteria for AF (Fibrillatory waves and absolute arrhythmia) across leads. With high accuracy on different single-lead ECGs and improved interpretability, xECGArch provides a trustworthy method for ECG analysis in mobile applications.

Detection model of atrial fibrillation based on multi-branch and multi-scale convolutional networks

Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection and treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor's diagnosis based on electrocardiograms (ECGs), but prolonged analysis of ECG signals is very time-consuming. This paper designs an AF detection model based on the Inception module, constructing multi-branch detection channels to process raw ECG signals, gradient signals, and frequency signals during AF. The model efficiently extracted QRS complex and RR interval features using gradient signals, extracted P-wave and f-wave features using frequency signals, and used raw signals to supplement missing information. The multi-scale convolutional kernels in the Inception module provided various receptive fields and performed comprehensive analysis of the multi-branch results, enabling early AF detection. Compared to current machine learning algorithms that use only RR interval and heart rate variability features, the proposed algorithm additionally employed frequency features, making fuller use of the information within the signals. For deep learning methods using raw and frequency signals, this paper introduced an enhanced method for the QRS complex, allowing the network to extract features more effectively. By using a multi-branch input mode, the model comprehensively considered irregular RR intervals and P-wave and f-wave features in AF. Testing on the MIT-BIH AF database showed that the inter-patient detection accuracy was 96.89%, sensitivity was 97.72%, and specificity was 95.88%. The proposed model demonstrates excellent performance and can achieve automatic AF detection.

Ensemble Learning-Based Atrial Fibrillation Detection From Single Lead ECG Wave for Wireless Body Sensor Network

With the popularity of wireless techniques and portable devices, continuous and real-time monitoring patient’s health status by collecting physiological signals is becoming more popular. Data mining of electrocardiograph (ECG) attracts widespread attention, where automatic atrial fibrillation (AF) detection has become a hot research field. In this paper, an ensemble learning algorithm is proposed for AF detection from single lead ECG recordings collected by wearable devices. This algorithm includes two modules. First, denoised 1-D time series (ECG), time-frequency spectrum and Poincare plot are used to train three component learners through a parallel style, respectively, and each component learner produces four probability values. Then, all the outputs are combined using a weighted matrix constructed by a Bayesian optimization algorithm, which is capable of producing the final classification result. Quantities of experiments have been implemented, and the results well prove the algorithm’s effectiveness and its advantage over some state-of-the-art counterparts.

An Atrial Fibrillation Classification Method Study Based on BP Neural Network and SVM

Atrial fibrillation is a common arrhythmia, and its diagnosis is interfered by many factors. In order to achieve applicability in diagnosis and improve the level of automatic analysis of atrial fibrillation to the level of experts, the automatic detection of atrial fibrillation is very important. This study proposes an automatic detection algorithm for atrial fibrillation based on BP neural network (back propagation network) and support vector machine (SVM). The electrocardiogram (ECG) segments in the MIT-BIH atrial fibrillation database are divided into 10, 32, 64, and 128 heartbeats, respectively, and the Lorentz value, Shannon entropy, K-S test value and exponential moving average value are calculated. These four characteristic parameters are used as the input of SVM and BP neural network for classification and testing, and the label given by experts in the MIT-BIH atrial fibrillation database is used as the reference output. Among them, the use of atrial fibrillation in the MIT-BIH database, the first 18 cases of data are used as the training set, and the last 7 cases of data are used as the test set. The results show that the accuracy rate of 92% is obtained in the classification of 10 heartbeats, and the accuracy rate of 98% is obtained in the latter three categories. The sensitivity and specificity are both above 97.7%, which has certain applicability. Further validation and improvement in clinical ECG data will be done in next study.

Atrial Fibrillation Detection With an Analog Smartwatch: Prospective Clinical Study and Algorithm Validation.

Atrial fibrillation affects approximately 4% of the world's population and is one of the major causes of stroke, heart failure, sudden death, and cardiovascular morbidity. It can be difficult to diagnose when asymptomatic or in the paroxysmal stage, and its natural history is not well understood. New wearables and connected devices offer an opportunity to improve on this situation. We aimed to validate an algorithm for the automatic detection of atrial fibrillation from a single-lead electrocardiogram taken with a smartwatch. Eligible patients were recruited from 4 sites in Paris, France. Electrocardiograms (12-lead reference and single lead) were captured simultaneously. The electrocardiograms were reviewed by independent, blinded board-certified cardiologists. The sensitivity and specificity of the algorithm to detect atrial fibrillation and normal sinus rhythm were calculated. The quality of single-lead electrocardiograms (visibility and polarity of waves, interval durations, heart rate) was assessed in comparison with the gold standard (12-lead electrocardiogram). A total of 262 patients (atrial fibrillation: n=100, age: mean 74.3 years, SD 12.3; normal sinus rhythm: n=113, age: 61.8 years, SD 14.3; other arrhythmia: n=45, 66.9 years, SD 15.2; unreadable electrocardiograms: n=4) were included in the final analysis; 6.9% (18/262) were classified as Noise by the algorithm. Excluding other arrhythmias and Noise, the sensitivity for atrial fibrillation detection was 0.963 (95% CI lower bound 0.894), and the specificity was 1.000 (95% CI lower bound 0.967). Visibility and polarity accuracies were similar (1-lead electrocardiogram: P waves: 96.9%, QRS complexes: 99.2%, T waves: 91.2%; 12-lead electrocardiogram: P waves: 100%, QRS complexes: 98.8%, T waves: 99.5%). P-wave visibility accuracy was 99% (99/100) for patients with atrial fibrillation and 95.7% (155/162) for patients with normal sinus rhythm, other arrhythmias, and unreadable electrocardiograms. The absolute values of the mean differences in PR duration and QRS width were <3 ms, and more than 97% were <40 ms. The mean difference between the heart rates from the 1-lead electrocardiogram calculated by the algorithm and those calculated by cardiologists was 0.55 bpm. The algorithm demonstrated great diagnostic performance for atrial fibrillation detection. The smartwatch's single-lead electrocardiogram also demonstrated good quality for physician use in daily routine care. ClinicalTrials.gov NCT04351386; http://clinicaltrials.gov/ct2/show/NCT04351386.

Automatic Detection of Atrial Fibrillation from ECG Signal Using Hybrid Deep Learning Techniques

In cardiac rhythm disorders, atrial fibrillation (AF) is among the most deadly. So, ECG signals play a crucial role in preventing CVD by promptly detecting atrial fibrillation in a patient. Unfortunately, locating trustworthy automatic AF in clinical settings remains difficult. Today, deep learning is a potent tool for complex data analysis since it requires little pre and postprocessing. As a result, several machine learning and deep learning approaches have recently been applied to ECG data to diagnose AF automatically. This study analyses electrocardiogram (ECG) data from the PhysioNet/Computing in Cardiology (CinC) Challenge 2017 to differentiate between atrial fibrillation (AF) and three other rhythms: normal, other, and too noisy for assessment. The ECG data, including AF rhythm, was classified using a novel model based on a combination of traditional machine learning techniques and deep neural networks. To categorize AF rhythms from ECG data, this hybrid model combined a convolutional neural network (Residual Network (ResNet)) with a Bidirectional Long Short Term Memory (BLSTM) network and a Radial Basis Function (RBF) neural network. Both the F1-score and the accuracy of the final hybrid model are relatively high, coming in at 0.80% and 0.85%, respectively.

Classification of Arrhythmia Using Machine Learning Algorithm

Detection of Atrial fibrillation (AF) is more complex as compared to other cardiac diseases. It requires lengthy ECG signals and more time for visual inspection and analysis by the physicians. Automatic detection of AF using an expert system is essential for the investigation of ECG signals. In this study, the Physionet challenge 2017 dataset is used for the detection and classification of AF versus other signals. In this paper, ECG signals are segmented into a sample size of 250 samples for the detection of Wavelet Packet Decomposition (WPD) and approximate entropy (ApEn) features for classification. In addition to WPD and ApEn, statistical features were derived from ECG signals. The Principal Component Analysis (PCA) has been used to reduce the dimensionality of the features based on the rank. Ensemble classifiers such as AdaBoost, XGBoost and Random Forest (RF) are used for classification. The accuracy of 62.91%, 70.33% and 89% for the AdaBoost, XGBoost and Random Forest respectively. We found RF classifier is suitable for classifying AF, normal rhythm and other non-AF related abnormal heart rhythms.

A deep learning refinement strategy based on efficient channel attention for atrial fibrillation and atrial flutter signals identification

Atrial fibrillation (AF) and atrial flutter (AFL) are the most frequent arrhythmias recently. However, given both similar physiological features, visually evaluating electrocardiogram as the most traditional diagnosis scheme is taxing and error-prone. In this work, we specifically design two network modules based on bidirectional long short term memory (BiLSTM) and gate recurrent unit (BiGRU) for automatic AF and AFL detection. Motivated from Efficient Channel Attention network, we aim to reformulate BiLSTM and BiGRU with a feature recalibration approach that enables the model to adaptively focus more on the relevant feature representations and suppress irrelevant parts while appropriately capturing cross-channel interaction for learning effective channel attention. The results lead to consistent performance gains than several published researches with an accuracy of 99.2% and 99.3% across the two publicly available data sets while demonstrating the effectiveness of both modules. In particular, various derivative gradient values of sample ECG segments are visualized to improve interpretability. To our knowledge, this work offers the first empirical investigation of existing BiLSTM and BiGRU refinements for a better performance gain, showing great potential for many computer vision tasks.

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.

Investigation of the Evolution of Wavelet Higher-Order Dynamics in Atrial Fibrillation.

Atrial fibrillation (AF) is the most common cardiac arrhythmia and is associated with significant morbidity and mortality. Owing to the advances in sensor technology and the emergence of wearable devices that enable daily self-monitoring, ECG signal processing methods for the automatic detection of AF are more pertinent than ever. In this paper, we investigate the use of wavelet higher-order statistics (WHOS) for feature extraction and differentiation between normal sinus rhythm and AF. The proposed approach captures the evolution of the WHOS dynamics and quantifies the changes in the time-varying characteristics of the frequency couplings caused by AF. Results obtained from the statistical analysis of a dataset of 5834 single-lead ECG recordings, reveal 46/50 statistically significant features and provide insight into the complexity of the evolution of the ECG non-linearities during AF.

Using Minimum Redundancy Maximum Relevance Algorithm to Select Minimal Sets of Heart Rate Variability Parameters for Atrial Fibrillation Detection.

Heart rate is quite regular during sinus (normal) rhythm (SR) originating from the sinus node. In contrast, heart rate is usually irregular during atrial fibrillation (AF). Complete atrioventricular block with an escape rhythm, ventricular pacing, or ventricular tachycardia are the most common exceptions when heart rate may be regular in AF. Heart rate variability (HRV) is the variation in the duration of consecutive cardiac cycles (RR intervals). We investigated the utility of HRV parameters for automated detection of AF with machine learning (ML) classifiers. The minimum redundancy maximum relevance (MRMR) algorithm, one of the most effective algorithms for feature selection, helped select the HRV parameters (including five original), best suited for distinguishing AF from SR in a database of over 53,000 60 s separate electrocardiogram (ECG) segments cut from longer (up to 24 h) ECG recordings. HRV parameters entered the ML-based classifiers as features. Seven different, commonly used classifiers were trained with one to six HRV-based features with the highest scores resulting from the MRMR algorithm and tested using the 5-fold cross-validation and blindfold validation. The best ML classifier in the blindfold validation achieved an accuracy of 97.2% and diagnostic odds ratio of 1566. From all studied HRV features, the top three HRV parameters distinguishing AF from SR were: the percentage of successive RR intervals differing by at least 50 ms (pRR50), the ratio of standard deviations of points along and across the identity line of the Poincare plots, respectively (SD2/SD1), and coefficient of variation—standard deviation of RR intervals divided by their mean duration (CV). The proposed methodology and the presented results of the selection of HRV parameters have the potential to develop practical solutions and devices for automatic AF detection with minimal sets of simple HRV parameters. Using straightforward ML classifiers and the extremely small sets of simple HRV features, always with pRR50 included, the differentiation of AF from sinus rhythms in the 60 s ECGs is very effective.

Automatic Atrial Fibrillation Arrhythmia Detection Using Univariate and Multivariate Data

Atrial fibrillation (AF) is still a major cause of disease morbidity and mortality, making its early diagnosis desirable and urging researchers to develop efficient methods devoted to automatic AF detection. Till now, the analysis of Holter-ECG recordings remains the gold-standard technique to screen AF. This is usually achieved by studying either RR interval time series analysis, P-wave detection or combinations of both morphological characteristics. After extraction and selection of meaningful features, each of the AF detection methods might be conducted through univariate and multivariate data analysis. Many of these automatic techniques have been proposed over the last years. This work presents an overview of research studies of AF detection based on RR interval time series. The aim of this paper is to provide the scientific community and newcomers to the field of AF screening with a resource that presents introductory concepts, clinical features, and a literature review that describes the techniques that are mostly followed when RR interval time series are used for accurate detection of AF.

Continuous mHealth Patch Monitoring for the Algorithm-Based Detection of Atrial Fibrillation: Feasibility and Diagnostic Accuracy Study.

BackgroundThe detection of atrial fibrillation (AF) is a major clinical challenge as AF is often paroxysmal and asymptomatic. Novel mobile health (mHealth) technologies could provide a cost-effective and reliable solution for AF screening. However, many of these techniques have not been clinically validated.ObjectiveThe purpose of this study is to evaluate the feasibility and reliability of artificial intelligence (AI) arrhythmia analysis for AF detection with an mHealth patch device designed for personal well-being.MethodsPatients (N=178) with an AF (n=79, 44%) or sinus rhythm (n=99, 56%) were recruited from the emergency care department. A single-lead, 24-hour, electrocardiogram-based heart rate variability (HRV) measurement was recorded with the mHealth patch device and analyzed with a novel AI arrhythmia analysis software. Simultaneously registered 3-lead electrocardiograms (Holter) served as the gold standard for the final rhythm diagnostics.ResultsOf the HRV data produced by the single-lead mHealth patch, 81.5% (3099/3802 hours) were interpretable, and the subject-based median for interpretable HRV data was 99% (25th percentile=77% and 75th percentile=100%). The AI arrhythmia detection algorithm detected AF correctly in all patients in the AF group and suggested the presence of AF in 5 patients in the control group, resulting in a subject-based AF detection accuracy of 97.2%, a sensitivity of 100%, and a specificity of 94.9%. The time-based AF detection accuracy, sensitivity, and specificity of the AI arrhythmia detection algorithm were 98.7%, 99.6%, and 98.0%, respectively.ConclusionsThe 24-hour HRV monitoring by the mHealth patch device enabled accurate automatic AF detection. Thus, the wearable mHealth patch device with AI arrhythmia analysis is a novel method for AF screening.Trial RegistrationClinicalTrials.gov NCT03507335; https://clinicaltrials.gov/ct2/show/NCT03507335

Deepaware: A hybrid deep learning and context-aware heuristics-based model for atrial fibrillation detection

BackgroundState-of-the-art automatic atrial fibrillation (AF) detection models trained on RR-interval (RRI) features generally produce high performance on standard benchmark electrocardiogram (ECG) AF datasets. These models, however, result in a significantly high false positive rates (FPRs) when applied on ECG data collected under free-living ambulatory conditions and in the presence of non-AF arrhythmias. MethodThis paper proposes DeepAware, a novel hybrid model combining deep learning (DL) and context-aware heuristics (CAH), which reduces the FPR effectively and improves the AF detection performance on participant-operated ambulatory ECG from free-living conditions. It exploits the RRI and P-wave features, as well as the contextual features from the ambulatory ECG. ResultsDeepAware is shown to be very generalizable and superior to the state-of-the-art models when applied on unseen benchmark ECG AF datasets. Most importantly, the model is able to detect AF efficiently when applied on participant-operated ambulatory ECG recordings from free-living conditions and has achieved a sensitivity (Se), specificity (Sp), and accuracy (Acc) of 97.94%, 98.39%, 98.06%, respectively. Results also demonstrate the effect of atrial activity analysis (via P-waves detection) and CAH in reducing the FPR over the RRI features-based AF detection model. ConclusionsThe proposed DeepAware model can substantially reduce the physician’s workload of manually reviewing the false positives (FPs) and facilitate long-term ambulatory monitoring for early detection of AF.

Enhancing the detection of atrial fibrillation from wearable sensors with neural style transfer and convolutional recurrent networks

Electrocardiograms (ECG) provide an effective, non-invasive approach for clinical diagnosis and monitoring treatment in patients with cardiac diseases including the most common cardiac arrhythmia, atrial fibrillation (AF). Portable ECG recording devices including Apple Watch and Kardia devices have been developed for AF detection. However, the efficacy of these smart devices has not been fully validated. We aimed to develop an open-source deep learning framework for automatic AF detection using the largest publicly available single-lead ECG dataset through a mobile Kardia device enhanced with style transfer-driven data augmentation. We developed and validated a 37-layer convolutional recurrent network (CRN) using 5,834 single-lead ECGs with a mean length of 30 seconds from the 2017 PhysioNet Challenge to automatically detect sinus rhythm and AF. To address the challenge of a lack of a large number of AF samples, we proposed a novel style transfer generator that fuses patient-specific clinical ECGs and mathematically modelled ECG features to synthesize realistic ECGs by five-fold. The differences between synthesized and clinical ECGs were analyzed by studying their average ECG morphologies and frequency distributions. Our results indicated the style transfer-driven data augmentation was not classifier-dependent. Validation on 2,917 clinical ECGs showed an F1 score of 96.4%, with the generated ECGs contributing to a 3% improvement in AF detection for the Kardia event recorder. By developing and evaluating our approach on an open-source ECG dataset, we have demonstrated that our framework is both robust and verifiable, and potentially can be used in portable devices for effective AF classification.

Atrial Fibrillation Detection Using a Feedforward Neural Network

PurposeIn this study, we aimed to develop an automatic atrial fibrillation detection technique for the early prediction of atrial fibrillation, that can be used with wearable devices.MethodsAn effective deep learning-based technology is proposed to automatically detect atrial fibrillation. First, novel preprocessing algorithms, wavelet transform and sliding window filtering, are introduced to reduce the noise and outliers, respectively, from ECG signals. Then, a robust R-wave detection algorithm is developed. In addition, we proposed a feedforward neural network to detect atrial fibrillation based on ECG records.ResultsExperiments verified using a tenfold cross-validation strategy showed that the proposed method achieves competitive detection performance, and can be applied to wearable detection devices. The proposed R-wave detection algorithm achieved a detection sensitivity of 99.22%, a positive recognition rate of 98.55%, and a deviance of 2.25% on the MIT-BIH arrhythmia database. The proposed atrial fibrillation detection model achieved an accuracy of 84.00%, a detection sensitivity of 84.26%, a specificity of 93.23%, and an area under the receiver operating curve of 89.40% on a mixed dataset composed of the Challenge2017 database and the MIT-BIH arrhythmia database.ConclusionThe analysis demonstrated that the proposed atrial fibrillation detection method could automatically detect atrial fibrillation with high accuracy and efficiency, could be applied to wearable devices, and has great value in the early detection of atrial fibrillation. We believe that our work will make a valuable contribution to the area of atrial fibrillation.

Automatic Detection of Atrial Fibrillation from Single-Lead ECG Using Deep Learning of the Cardiac Cycle.

Objective and Impact Statement. Atrial fibrillation (AF) is a serious medical condition that requires effective and timely treatment to prevent stroke. We explore deep neural networks (DNNs) for learning cardiac cycles and reliably detecting AF from single-lead electrocardiogram (ECG) signals. Introduction. Electrocardiograms are widely used for diagnosis of various cardiac dysfunctions including AF. The huge amount of collected ECGs and recent algorithmic advances to process time-series data with DNNs substantially improve the accuracy of the AF diagnosis. DNNs, however, are often designed as general purpose black-box models and lack interpretability of their decisions. Methods. We design a three-step pipeline for AF detection from ECGs. First, a recording is split into a sequence of individual heartbeats based on R-peak detection. Individual heartbeats are then encoded using a DNN that extracts interpretable features of a heartbeat by disentangling the duration of a heartbeat from its shape. Second, the sequence of heartbeat codes is passed to a DNN to combine a signal-level representation capturing heart rhythm. Third, the signal representations are passed to a DNN for detecting AF. Results. Our approach demonstrates a superior performance to existing ECG analysis methods on AF detection. Additionally, the method provides interpretations of the features extracted from heartbeats by DNNs and enables cardiologists to study ECGs in terms of the shapes of individual heartbeats and rhythm of the whole signals. Conclusion. By considering ECGs on two levels and employing DNNs for modelling of cardiac cycles, this work presents a method for reliable detection of AF from single-lead ECGs.

Diagnostic Accuracy and Usability of the ECG247 Smart Heart Sensor Compared to Conventional Holter Technology.

Background Heart rhythm disorders, especially atrial fibrillation (AF), are increasing global health challenges. Conventional diagnostic tools for assessment of rhythm disorders suffer from limited availability, limited test duration time, and usability challenges. There is also a need for out-of-hospital investigation of arrhythmias. Therefore, the Norwegian ECG247 Smart Heart Sensor has been developed to simplify the assessment of heart rhythm disorders. The current study aimed to evaluate the diagnostic accuracy and usability of the ECG247 Smart Heart Sensor compared to conventional Holter monitors. Methods Parallel tests with ECG247 Smart Heart Sensor and a Holter monitor were performed in 151 consecutive patients referred for out-of-hospital long-term ECG recording at Sorlandet Hospital Arendal, Norway. All ECG data were automatically analysed by both systems and evaluated by hospital physicians. Participants were asked to complete a questionnaire scoring usability parameters after the test. Results A total of 150 patients (62% men, age 54 (±17) years) completed the study. The ECG quality from both monitors was considered satisfactory for rhythm analysis in all patients. AF was identified in 9 (6%) patients during the period with parallel tests. The diagnostic accuracy for automatic AF detection was 95% (95% CI 91–98) for the ECG247 Smart Heart Sensor and 81% (95% CI 74–87) for the Holter system. The proportion of false-positive AF was 4% in tests analysed by the ECG247 algorithm and 16% in tests analysed by the Holter algorithm. Other arrhythmias were absent/rare. The system usability score was significantly better for ECG247 Smart Heart Sensor compared to traditional Holter technology (score 87.4 vs. 67.5, p < 0.001). Conclusions The ECG247 Smart Heart Sensor showed at least comparable diagnostic accuracy for AF and improved usability compared to conventional Holter technology. ECG247 allows for prolonged monitoring and may improve detection of AF. This trial is registered with https://clinicaltrials.gov/ct2/show/NCT04700865.

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.

An effective feature extraction method based on GDS for atrial fibrillation detection

Atrial fibrillation (AF) is a common and extremely harmful arrhythmia disease. Automatic detection of AF based on ECG helps accurate and timely detection of the condition. However, the existing AF detection methods are mostly based on complex signal transformation or precise waveform localization. This is a big challenge for complex, variable, and susceptible ECG signals. Therefore, we propose a simple feature extraction method based on gradient set (GDS) for AF detection. The method first calculates the GDS of the ECG segment and then calculates the statistical distribution feature and the information quantity feature of the GDS as the input of the classifier. Experiments on four databases include 146 subjects show that the feature extraction method for detecting AF proposed in this paper has the characteristics of simple calculation, noise tolerance, and high adaptability to all kinds of classifiers, and got the best performance on the DNN classifier we designed. Therefore, it is a good choice for feature extraction in AF detection.