Raw Electrocardiogram Signal Research Articles

Precise detection and localization of R-peaks from ECG signals.

Heart rate variability (HRV) is derived from the R-R interval, which depends on the precise localization of R-peaks within an electrocardiogram (ECG) signal. However, current algorithm assessment methods prioritize the R-peak detection's sensitivity rather than the precision of pinpointing the exact R-peak positions. As a result, it is of great value to develop an R-peak detection algorithm with high-precision R-peak localization. This paper introduces a novel R-peak localization algorithm that involves modifications to the well-established Pan-Tompkins (PT) algorithm. The algorithm was implemented as follows. First, the raw ECG signal $ X\left(i\right) $ was band-pass filtered (5-35 Hz) to obtain a preprocessed signal $ Y\left(i\right) $. Second, $ Y\left(i\right) $ was squared to enhance the QRS complex, followed by a 5 Hz low-pass filter to obtain the QRS envelope, which was transformed into a window signal $ W\left(i\right) $ by dynamic threshold with a minimum width of 200 ms to mark the QRS complex. Third, $ Y\left(i\right) $ was used to generate QRS template $ T\left(n\right) $ automatically, and then the R-peak was identified by a template matching process to find the maximum absolute value of all cross-correlation values between $ T\left(n\right) $ and $ Y\left(i\right) $. The proposed algorithm achieved a sensitivity (SE) of 99.78%, a positive prediction value (PPV) of 99.78% and data error rate (DER) of 0.44% in R-peak localization for the MIT-BIH Arrhythmia database. The annotated-detected error (ADE), which represents the error between the annotated R-peak location and the detected R-peak location, was 8.35 ms for the MIT-BIH Arrhythmia database. These results outperformed the results obtained using the classical Pan-Tompkins algorithm which yielded an SE of 98.87%, a PPV of 99.14%, a DER of 1.98% and an ADE of 21.65 ms for the MIT-BIH Arrhythmia database. It can be concluded that the algorithm can precisely detect the location of R-peaks and may have the potential to enhance clinical applications of HRV analysis.

ECG Signals Segmentation Using Deep Spatiotemporal Feature Fusion U-Net for QRS Complexes and R-Peak Detection

To detect and identify QRS complexes and R-peak is one of the crucial steps in the field of electrocardiogram (ECG) signals research, and their detection accuracy directly affects the performance of the subsequent ECG signal processing and analysis. However, the task involving the detection and identification of the ECG features becomes so complex for the traditional threshold-based detection methods. At present, researchers turn to deep learning approaches but little work has been done on the detection of spatiotemporal features of the QRS complexes. In this paper, for better QRS complexes and R-peak detection, we propose a novel method based on the improved U-net model, called ST-Res U-net. This uniquely designed component of the improved U-net model is made up of four levels of ST Block (the block extracting spatial-temporal features) and Res Path (the residual path). The entire framework contains three steps, data preprocessing dealing with denoising of the raw ECG signals, the key component ST-Res U-net dealing with the spatiotemporal feature extraction, and a threshold screening algorithm for locating the R-peaks. Our experiments are purposedly designed to test various combination structures of the ST blocks. The training and testing are from the MIT-BIH arrhythmia database (MITDB) and the CPSC2019 database. We adopt a commonly used set of evaluation criteria with the following experimental results: 99.76% and 90.01% for sensitivity, 99.87% and 93.5% for positive predictivity rate, 99.81% and 91.75% for F1 value, and 0.37% and 15.24% for detection error rate. The former numbers are for MITDB and the latter CPSC2019. Further, we test the proposed method on the PTB-XL database (without labeled R-peak positions) and the method can accurately locate QRS complexes and R-peaks The experimental results demonstrate that the proposed model and method is quite effective for the automatic classification and annotation of ECG signals and thus greatly improves the accuracy of diagnosis of arrhythmia diseases.

Cloud-based healthcare framework for real-time anomaly detection and classification of 1-D ECG signals.

Real-time data collection and pre-processing have enabled the recognition, realization, and prediction of diseases by extracting and analysing the important features of physiological data. In this research, an intelligent end-to-end system for anomaly detection and classification of raw, one-dimensional (1D) electrocardiogram (ECG) signals is given to assess cardiovascular activity automatically. The acquired raw ECG data is pre-processed carefully before storing it in the cloud, and then deeply analyzed for anomaly detection. A deep learning-based auto-encoder(AE) algorithm is applied for the anomaly detection of 1D ECG time-series signals. As a next step, the implemented system identifies it by a multi-label classification algorithm. To improve the classification accuracy and model robustness the improved feature-engineered parameters of the large and diverse datasets have been incorporated. The training has been done using the amazon web service (AWS) machine learning services and cloud-based storage for a unified solution. Multi-class classification of raw ECG signals is challenging due to a large number of possible label combinations and noise susceptibility. To overcome this problem, a performance comparison of a large set of machine algorithms in terms of classification accuracy is presented on an improved feature-engineered dataset. The proposed system reduces the raw signal size up to 95% using wavelet time scattering features to make it less compute-intensive. The results show that among several state-of-the-art techniques, the long short-term memory (LSTM) method has shown 100% classification accuracy, and an F1 score on the three-class test dataset. The ECG signal anomaly detection algorithm shows 98% accuracy using deep LSTM auto-encoders with a reconstructed error threshold of 0.02 in terms of absolute error loss. Our approach provides performance and predictive improvement with an average mean absolute error loss of 0.0072 for normal signals and 0.078 for anomalous signals.

A stacked ensemble model for automatic stroke prediction using only raw electrocardiogram

Stroke is one of the main causes of death and disability in elderly people worldwide. Early diagnosis of this disease is desirable. An electrocardiogram (ECG) signal is a powerful tool in the diagnosis of stroke. Many recent studies are using ECG signals in the diagnosis of stroke. This study is done with the aim to develop an efficient classification model which can be used in the diagnosis of stroke disease using ECG features. This study uses ECG data collected from 71 different subjects of which 35 were stroke patients and 36 were normal patients. This study proposes a stacked ensemble model which is built by stacking three different convolutional neural networks (CNN) models. The raw ECG signals are used as input to the model for training and testing. The result shows that the proposed model is capable of predicting stroke with an accuracy of 99.7%. F1-score, precision and recall are 99.69%, 99.67% and 99.71% respectively. Hence, this study reports that with the proposed model, ECG can be used as an aid in the diagnosis of stroke disease with high efficiency.

A robust multiple heartbeats classification with weight-based loss based on convolutional neural network and bidirectional long short-term memory.

Background: Analysis of electrocardiogram (ECG) provides a straightforward and non-invasive approach for cardiologists to diagnose and classify the nature and severity of variant cardiac diseases including cardiac arrhythmia. However, the interpretation and analysis of ECG are highly working-load demanding, and the subjective may lead to false diagnoses and heartbeats classification. In recent years, many deep learning works showed an excellent role in accurate heartbeats classification. However, the imbalance of heartbeat classes is universal in most of the available ECG databases since abnormal heartbeats are always relatively rare in real life scenarios. In addition, many existing approaches achieved prominent results by removing noise and extracting features in data preprocessing, which relies heavily on powerful computers. It is a pressing need to develop efficient and automatic light weighted algorithms for accurate heartbeats classification that can be used in portable ECG sensors. Objective: This study aims at developing a robust and efficient deep learning method, which can be embedded into wearable or portable ECG monitors for classifying heartbeats. Methods: We proposed a novel and light weighted deep learning architecture with weight-based loss based on a convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM) that can automatically identify five types of ECG heartbeats according to the AAMI EC57 standard. It was also true that the raw ECG signals were simply segmented without noise removal and other feature extraction processing. Moreover, to tackle the challenge of classification bias due to imbalanced ECG datasets for different types of arrhythmias, we introduced a weight-based loss function to reduce the influence of over-weighted categories in the ECG dataset. For avoiding the influence of the division of validation dataset, k-fold method was adopted to improve the reliability of the model. Results: The proposed algorithm is trained and tested on MIT-BIH Arrhythmia Database, and achieves an average of 99.33% accuracy, 93.67% sensitivity, 99.18% specificity, 89.85% positive prediction, and 91.65% F1 score.

Heart Disease Prediction using Machine Learning

The correct prediction of cardiovascular disease can prevent life threats, and incorrect prediction can prove to be fatal at the same time. Heart disease, also known as cardiovascular disease is one of the complex diseases and globally many people suffered from this disease. It is one of the major causes of mortality worldwide, can be mitigated by early heart disease diagnosis. However, the mortality rate can be drastically controlled if the disease is detected at early stage and preventive measures are adopted as soon as possible. In the modern world, there are some revolutionary advancements within the field of medical science and research and this can be no totally different for ECG. Electrocardiogram (ECG) gives useful information about morphological and functional details of heart which is used to predict various cardiac diseases. In this article, we proposed an efficient and accurate system to diagnosis heart disease which is based on machine learning techniques. Raw ECG signal contains useful features which can be used to detect different heart diseases. The various ECG parameters like heart rate, age, sex, cholesterol level, blood pressure, ST interval of ECG signal are used for analysis. Several machine learning (ML) algorithms have been used for cardiovascular disease prediction. Machine Learning is employed across several ranges around the world. The healthcare business isn't any exclusion.

Fog-Enabled IoT Framework for Heart Disease Diagnosis Systems

IoT technology has been recently adopted in healthcare systems to quickly detect abnormalities from patients, diagnose diseases and provide supports in time, even remotely. In the field of heart disease, timely diagnosis and prediction help to save people. This paper proposes a fog-based IoT approach to collect and analyze electrocardiogram (ECG) signals from patients to detect abnormalities or heart attacks with a short response time so that appropriate treatments can be provided. Commonly, ECG signals are transmitted to an eco-expert system deployed on the cloud to perform preliminary automatic diagnosis using a knowledge base built from medical experts. Although such an eco-expert system assists patients and supports physicians in performing treatment for their patients, there are several open technical challenges. First, noise in raw ECG signals makes the data imprecise and reduces the prediction accuracy. Second, involving data mining and machine learning on the cloud poses a significant latency since a huge amount of data needs to be transferred in the network. This paper proposes a novel framework that can provide the integrity of the ECG data by removing noise and then extract relevant knowledge for heart disease diagnosis at the network edge based on data mining techniques. Practical experiments demonstrate that the proposed framework not only guarantees the integrity of the data but also enhances the accuracy of the real-time detection compared with previous works.

Heartprint: A Dataset of Multisession ECG Signal with Long Interval Captured from Fingers for Biometric Recognition

The electrocardiogram (ECG) signal produced by the human heart is an emerging biometric modality that can play an important role in the future generation’s identity recognition with the support of machine learning techniques. One of the major obstacles in the progress of this modality is the lack of public datasets with a long interval between sessions of data acquisition to verify the uniqueness and permanence of the biometric signature of the heart of a subject. To address this issue, we put forward Heartprint, a large biometric database of multisession ECG signals comprising 1539 records captured from the fingers of 199 healthy subjects. The capturing time for each record was 15 s, and recordings were made in resting and reading conditions. They were collected in multiple sessions over ten years, and the average interval between first session (S1) and third session (S3L) was 1572.2 days. The dataset also covers several demographic classes such as genders, ethnicities, and age groups. The combination of raw ECG signals and demographic information turns the Heartprint dataset, which is made publicly available online, into a valuable resource for the development and evaluation of biometric recognition algorithms.

Artificial intelligence analysis of ECG signals to predict arrhythmia recurrence after cryoballoon ablation of atrial fibrillation

Abstract Introduction Cryoballoon-based pulmonary vein isolation (CB) is an effective option for rhythm control in atrial fibrillation (AF). There have been multiple attempts to predict arrhythmia recurrence, but with moderate success. Purpose To use artificial intelligence (AI) deep electrocardiogram (ECG) analysis to predict arrythmia recurrence after CB. Methods In a single-center study of 250 consecutive pts (58.2±12.6 years, 30% female) treated with CB for AF (05.2017–04.2019), 60% had paroxysmal AF (PAF), 66.5% had hypertension, and 27.2% had a redo CB. Analyses included left atrial volume (LA vol: indexed for BSA and assed by angio-MSCT in 76% and the rest with echo), left ventricle ejection fraction (LVEF) and hypertrophy (LVH: septal/posterior wall thickness ≥11mm in ♂ and ≥10mm in ♀) along with 30s arrhythmia recurrence at 2-yr follow-up. Baseline 500Hz raw 12-lead digital ECG signals were analyzed by means of convolutional neural network (CNN) architecture that was taught to process the 12-channel ECG signal (XML). The transfer learning method of CNN parameters learned on a very large number of coded consecutive training ECG samples (n=1,000) was adopted to analyze current sample of ECG signals. Results Arrhythmia recurrence at 2-yrs was 46.0% (n=115). There was gradual increase in predictive performance being the lowest if only baseline clinical data were analyzed and the highest combing all baseline clinical data plus anatomical and functional parameters (Table 1: #1–#3). AI baseline ECG analysis alone offered predictive performance similar to that made upon analysis of all baseline clinical data or joint analysis of LA vol, LVH, and LVEF (Table 1: #4). AI results added substantially to predictive performance of models using baseline clinical data alone (#1 vs #5, p<0.001) and joint analysis of baseline clinical plus LA vol, LVH and LVEF (#3 vs #6, p=0.0130) (Fig. 1). Conclusions Prediction of recurrence after CB using raw ECG data with deep AI analysis is feasible. Joint analysis of results of AI of baseline ECG and basic clinical data offers predictive performance similar to that made upon analysis of clinical data including advanced information on LA volume and LVH and function. AI analysis of baseline ECG adds significantly to models aimed at recurrent AF prediction. Funding Acknowledgement Type of funding sources: Public hospital(s). Main funding source(s): National Institute of Cardiology, Warsaw, Poland

DDCNN: A Deep Learning Model for AF Detection From a Single-Lead Short ECG Signal.

With the popularity of the wireless body sensor network, real-time and continuous collection of single-lead electrocardiogram (ECG) data becomes possible in a convenient way. Data mining from the collected single-lead ECG waves has therefore aroused extensive attention worldwide, where early detection of atrial fibrillation (AF) is a hot research topic. In this paper, a two-channel convolutional neural network combined with a data augmentation method is proposed to detect AF from single-lead short ECG recordings. It consists of three modules, the first module denoises the raw ECG signals and produces 9-s ECG signals and heart rate (HR) values. Then, the ECG signals and HR rate values are fed into the convolutional layers for feature extraction, followed by three fully connected layers to perform the classification. The data augmentation method is used to generate synthetic signals to enlarge the training set and increase the diversity of the single-lead ECG signals. Validation experiments and the comparison with state-of-the-art studies demonstrate the effectiveness and advantages of the proposed method.

A Parallel Cross Convolutional Recurrent Neural Network for Automatic Imbalanced ECG Arrhythmia Detection with Continuous Wavelet Transform.

Automatic detection of arrhythmia using electrocardiogram (ECG) and deep learning (DL) is very important to reduce the global death rate from cardiovascular diseases (CVD). Previous studies on automatic arrhythmia detection relied largely on various ECG features and have achieved considerable classification accuracy using DL-based models. However, most previous research has ignored multi-class imbalanced problems in ECG arrhythmia detection. Therefore, it remains a challenge to improve the classification performance of the DL-based models. This paper proposes a novel parallel cross convolutional recurrent neural network in order to improve the arrhythmia detection performance of imbalanced ECG signals. The proposed model incorporates a recurrent neural network and a two-dimensional (2D) convolutional neural network (CNN) and can effectively learn temporal characteristics and rich spatial information of raw ECG signals. Continuous wavelet transform (CWT) is used to transform the ECG signals into a 2D scalogram composed of time–frequency components, and subsequently, the 2D-CNN can learn spatial information from the 2D scalogram. The proposed model is not only efficient in learning features with imbalanced samples but can also significantly improve model convergence with higher accuracy. The overall performance of our proposed model is evaluated based on the MIT-BIH arrhythmia dataset. Detailed analysis of evaluation metrics reveals that the proposed model is very effective in arrhythmia detection and significantly better than the existing hierarchical network models.

A Deep Learning Framework for Automatic Sleep Apnea Classification Based on Empirical Mode Decomposition Derived from Single-Lead Electrocardiogram.

Background: Although polysomnography (PSG) is a gold standard tool for diagnosing sleep apnea (SA), it can reduce the patient’s sleep quality by the placement of several disturbing sensors and can only be interpreted by a highly trained sleep technician or scientist. In recent years, electrocardiogram (ECG)-derived respiration (EDR) and heart rate variability (HRV) have been used to automatically diagnose SA and reduce the drawbacks of PSG. Up to now, most of the proposed approaches focus on machine-learning (ML) algorithms and feature engineering, which require prior expert knowledge and experience. The present study proposes an SA detection algorithm to differentiate a normal and apnea event using a deep-learning (DL) framework based on 1D and 2D deep CNN with empirical mode decomposition (EMD) of a preprocessed ECG signal. The EMD is ideally suited to extract essential components which are characteristic of the underlying biological or physiological processes. In addition, the simple and compact architecture of 1D deep CNN, which only performs 1D convolutions, and pretrained 2D deep CNNs, are suitable for real-time and low-cost hardware implementation. Method: This study was validated using 7 h to nearly 10 h overnight ECG recordings from 33 subjects with an average apnea-hypopnea index (AHI) of 30.23/h originated from PhysioNet Apnea-ECG database (PAED). In preprocessing, the raw ECG signal was normalized and filtered using the FIR band pass filter. The preprocessed ECG signal was then decomposed using the empirical mode decomposition (EMD) technique to generate several features. Several important generated features were selected using neighborhood component analysis (NCA). Finally, deep learning algorithm based on 1D and 2D deep CNN were used to perform the classification of normal and apnea event. The synthetic minority oversampling technique (SMOTE) was also applied to evaluate the influence of the imbalanced data problem. Results: The segment-level classification performance had 93.8% accuracy with 94.9% sensitivity and 92.7% specificity based on 5-fold cross-validation (5fold-CV), meanwhile, the subject-level classification performance had 83.5% accuracy with 75.9% sensitivity and 88.7% specificity based on leave-one-subject-out cross-validation (LOSO-CV). Conclusion: A novel and robust SA detection algorithm based on the ECG decomposed signal using EMD and deep CNN was successfully developed in this study.

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

As the number of people suffering from cardiovascular diseases increases every year, it becomes essential to have an accurate automatic electrocardiogram (ECG) diagnosis system. Researchers have adopted different methods, such as deep learning, to investigate arrhythmias classification. However, the importance of ECG waveform features is generally ignored when deep learning approaches are applied to classification tasks. P-wave, QRS-wave, and T-wave, containing plenty of physiological information, are three critical waves in the ECG heartbeat. The accurate localization of these critical ECG wave components is a prerequisite for ECG classification and diagnosis. In this study, a novel P-QRS-T wave localization method based on hybrid neural networks is proposed. The raw ECG signal is preprocessed sequentially by filtering, heartbeat extraction, and data standardization. The hybrid neural network is constructed by combining the residual neural network (ResNet) and the Long Short-Term Memory (LSTM). It predicts the relative positions of the P-peak, QRS-peak, and T-peak for each heartbeat. The proposed algorithm was validated on four ECG databases with input noise of different signal-to-noise ratio (SNR) levels. The results show that the proposed method can accurately predict the positions of the three key waves. The proposed P-QRS-T localization approach can improve the efficiency of ECG delineation. Integrated with cardiac disease classification methods, it can contribute to the development of advanced automatic ECG diagnosis systems.

A deep learning approach to cardiovascular disease classification using empirical mode decomposition for ECG feature extraction

Deep learning has achieved promising results on a broad spectrum of tasks using an end-to-end approach, and domain-specific knowledge can be used to supplement it by either constraining the solution-space, or to transform data such that relevant signals are more influential during the training process. This is especially important in the context of continuous recordings or wearable-based monitoring, where signal quality may be constrained by hardware, such as a limited number of available electrodes, or by external perturbations. In this study, a global feature extraction method for multi-periodic signals is proposed, which effectively classifies multi-cycle normal and abnormal heartbeats. The abnormal heartbeats are classed as the Left Bundle Branch Block beat (LBBB), Right Bundle Branch Block beat (RBBB), and Paced beat (P). The signal analysis process of the electrocardiogram (ECG) recordings consist of three main stages: (I) segmentation of the ECG data and partitioning of the data set; (II) generation of an overall feature map representing the “heartbeat condition” based on Empirical Mode Decomposition (EMD); and (III) a classification stage for determining the patient’s heartbeat condition. The extracted feature image is used to classify the heartbeat condition using a two-dimensional Convolutional Neural Network (CNN). This method is applied to the publicly available MIT-BIH arrhythmia database. Experimental results show that the reconstructed ECG features outperform use of the raw ECG signals. Under self-test conditions of 3 min of ECG signal, the Total Classification Accuracy (TCA) was approximately 99.01%, while the TCA without the proposed method was approximately 90.69%.

Training machine learning models with synthetic data improves the prediction of ventricular origin in outflow tract ventricular arrhythmias.

In order to determine the site of origin (SOO) in outflow tract ventricular arrhythmias (OTVAs) before an ablation procedure, several algorithms based on manual identification of electrocardiogram (ECG) features, have been developed. However, the reported accuracy decreases when tested with different datasets. Machine learning algorithms can automatize the process and improve generalization, but their performance is hampered by the lack of large enough OTVA databases. We propose the use of detailed electrophysiological simulations of OTVAs to train a machine learning classification model to predict the ventricular origin of the SOO of ectopic beats. We generated a synthetic database of 12-lead ECGs (2,496 signals) by running multiple simulations from the most typical OTVA SOO in 16 patient-specific geometries. Two types of input data were considered in the classification, raw and feature ECG signals. From the simulated raw 12-lead ECG, we analyzed the contribution of each lead in the predictions, keeping the best ones for the training process. For feature-based analysis, we used entropy-based methods to rank the obtained features. A cross-validation process was included to evaluate the machine learning model. Following, two clinical OTVA databases from different hospitals, including ECGs from 365 patients, were used as test-sets to assess the generalization of the proposed approach. The results show that V2 was the best lead for classification. Prediction of the SOO in OTVA, using both raw signals or features for classification, presented high accuracy values (>0.96). Generalization of the network trained on simulated data was good for both patient datasets (accuracy of 0.86 and 0.84, respectively) and presented better values than using exclusively real ECGs for classification (accuracy of 0.84 and 0.76 for each dataset). The use of simulated ECG data for training machine learning-based classification algorithms is critical to obtain good SOO predictions in OTVA compared to real data alone. The fast implementation and generalization of the proposed methodology may contribute towards its application to a clinical routine.

A Deep Learning Algorithm for Detecting Acute Pericarditis by Electrocardiogram.

(1) Background: Acute pericarditis is often confused with ST-segment elevation myocardial infarction (STEMI) among patients presenting with acute chest pain in the emergency department (ED). Since a deep learning model (DLM) has been validated to accurately identify STEMI cases via 12-lead electrocardiogram (ECG), this study aimed to develop another DLM for the detection of acute pericarditis in the ED. (2) Methods: This study included 128 ECGs from patients with acute pericarditis and 66,633 ECGs from patients visiting the ED between 1 January 2010 and 31 December 2020. The ECGs were randomly allocated based on patients to the training, tuning, and validation sets, at a 3:1:1 ratio. We used raw ECG signals to train a pericarditis-DLM and used traditional ECG features to train a machine learning model. A human–machine competition was conducted using a subset of the validation set, and the performance of the Philips automatic algorithm was also compared. STEMI cases in the validation set were extracted to analyze the DLM ability of differential diagnosis between acute pericarditis and STEMI using ECG. We also followed the hospitalization events in non-pericarditis cases to explore the meaning of false-positive predictions. (3) Results: The pericarditis-DLM exceeded the performance of all participating human experts and algorithms based on traditional ECG features in the human–machine competition. In the validation set, the pericarditis-DLM could detect acute pericarditis with an area under the receiver operating characteristic curve (AUC) of 0.954, a sensitivity of 78.9%, and a specificity of 97.7%. However, our pericarditis-DLM also misinterpreted 10.2% of STEMI ECGs as pericarditis cases. Therefore, we generated an integrating strategy combining pericarditis-DLM and a previously developed STEMI-DLM, which provided a sensitivity of 73.7% and specificity of 99.4%, to identify acute pericarditis in patients with chest pains. Compared to the true-negative cases, patients with false-positive results using this strategy were associated with higher risk of hospitalization within 3 days due to cardiac disorders (hazard ratio (HR): 8.09; 95% confidence interval (CI): 3.99 to 16.39). (4) Conclusions: The AI-enhanced algorithm may be a powerful tool to assist clinicians in the early detection of acute pericarditis and differentiate it from STEMI using 12-lead ECGs.

A Deep Learning Scheme for Detecting Atrial Fibrillation Based on Fusion of Raw and Discrete Wavelet Transformed ECG Features.

Atrial fibrillation is the most common sustained cardiac arrhythmia and the electrocardiogram (ECG) is a powerful non-invasive tool for its clinical diagnosis. Automatic AF detection remains a very challenging task due to the high inter-patient variability of ECGs. In this paper, an automatic AF detection scheme is proposed based on a deep learning network that utilizes both raw ECG signal and its discrete wavelet transform (DWT) version. In order to utilize the time-frequency characteristics of the ECG signal, first level DWT is applied and both high and low frequency components are then utilized in the 1D CNN network in parallel. If only the transformed data are utilized in the network, original variations in the data may not be explored, which also contains useful information to identify the abnormalities. A multi-phase training scheme is proposed which facilitates parallel optimization for efficient gradient propagation. In the proposed network, features are directly extracted from raw ECG and DWT coefficients, followed by 2 fully connected layers to process features furthermore and to detect arrhythmia in the recordings. Classification performance of the proposed method is tested on PhysioNet-2017 dataset and it offers superior performance in detecting AF from normal, alternating and noisy cases in comparison to some state-of-the-art methods.

Identifying Arrhythmias Based on ECG Classification Using Enhanced-PCA and Enhanced-SVM Methods

The "Cardio Vascular Diseases (CVDs)" had already attained worrisome proportions in both advanced and emerging nations in recent times. Physically inactive behaviors, altered eating, and occupational routines, and reduced daily fitness were all recognized as crucial contextual elements, in addition to genetics. Considering CVDs have such a significant morbidity and mortality, accurate and early diagnosis of cardiac disease by "ElectroCardioGram (ECG)" allows clinicians to decide suitable therapy for a multitude of cardiovascular disorders. The interpretation of ECG signal is an important bio-signal processing area that involves the application of computer science and engineering to detect and visualize the functional status of the heart. Therefore, in the present work, a detailed study on ECG signals denoising and abnormalities detection using different techniques were performed. Annoying distortions and noisy particles are common in ECG signals. The "Biased Finite Impulse Response (BFIR)" preprocessing filtering is employed in this research to eliminate the noises in the raw ECG signals. The "Nonlinear-Hamilton" segmentation method is employed to segment the 'R' peak signals. To decrease the extraneous features included in the segmented ECG data, the innovative "Enhanced Principal Component Analysis (EPCA)" was applied for feature extraction. A unique "Enhanced version of the Support Vector Machine (ESVM)" framework with a "Weighting Kernel" based technique is proposed for classifying the ECG data. The 'Q', 'R', and 'S' waves in the given ECG data will be identified by this framework, allowing it to characterize the cardiac rhythm. The evaluation metrics of the EPCA-ESVM proposed method is comparatively analyzed with our previous approach EPSO. To estimate the results for the dataset from MIT-BIH it was experimented with by the EPSO and the EPCA-ESVM methods focused upon different parameters such as Accuracy, F1-score, etc. The final findings of the EPCA-ESVM method were good than the EPSO method in which the accuracy is higher even though unbalanced data were present.

Deep Convolutional Recurrent Model for Automatic Scoring Sleep Stages Based on Single-Lead ECG Signal.

Background: Sleep stage scoring, which is an essential step in the quantitative analysis of sleep monitoring, relies on human experts and is therefore subjective and time-consuming; thus, an easy and accurate method is needed for the automatic scoring of sleep stages. Methods: In this study, we constructed a deep convolutional recurrent (DCR) model for the automatic scoring of sleep stages based on a raw single-lead electrocardiogram (ECG). The DCR model uses deep convolutional and recurrent neural networks to apply the complex and cyclic rhythms of human sleep. It consists of three convolutional and two recurrent layers and is optimized by dropout and batch normalization. The constructed DCR model was evaluated using multiclass classification, including five-class sleep stages (wake, N1, N2, N3, and rapid eye movement (REM)) and three-class sleep stages (wake, non-REM (NREM), and REM), using a raw single-lead ECG signal. The single-lead ECG signal was collected from 112 subjects in two groups: control (52 subjects) and sleep apnea (60 subjects). The single-lead ECG signal was preprocessed, segmented at a duration of 30 s, and divided into a training set of 89 subjects and test set of 23 subjects. Results: We achieved an overall accuracy of 74.2% for five classes and 86.4% for three classes. Conclusions: These results show the DCR model’s superior performance over those in the previous studies, highlighting that the model can be an alternative tool for sleep monitoring and sleep screening.

PO-620-07 AN ENSEMBLE OF FEATURES BASED DEEP LEARNING NEURAL NETWORK FOR REDUCTION OF INAPPROPRIATE ATRIAL FIBRILLATION DETECTION IN IMPLANTABLE CARDIAC MONITORS

Multiple studies have been reported for electrocardiogram (ECG) classification using deep learning neural networks. Most of these studies use the ECG as input to a convolution neural network (CNN) which then automatically generate features from the raw ECG signal. To develop an application specific deep learning CNNs using custom ensemble of features to reduce inappropriate AF detections in implantable cardiac monitors (ICM). The ensemble of features was developed and combined to form an input signal for deep learning CNN. The ensemble of features were designed based on the electro-physiological characteristics during AF: presence of fibrillation/flutter waves or absence of single p-wave between two R-waves, incoherence of RR intervals, and AF begetting more AF. A small custom CNN model using 6 convolution layers and the publicly available RESNET18 model were used. The deep learning models were trained and validated using more than 60K ICM detected AF episodes that were adjudicated to be true AF or false detections. The trained models were evaluated using an independent test dataset of ICM detected and adjudicated AF episodes from patients who were not included in the training and validation dataset. The training and validation dataset consisted of 31,768 true AF episodes (2516 patients) and 28,527 false episodes (2126 patients). The validation set used 20% of randomly chosen episodes of each type. The independent test set consisted of 4546 true AF episodes (418 patients) and 5384 false episodes (605 patients). In the validation set, the custom CNN had an area under ROC curve (AUC) of 0.996 (0.993 for RESNET18) and a threshold for discrimination was defined such that a relative sensitivity and specificity of 99.2% and 92.8% (99.2% and 87.9% for RESNET18) was obtained. The performance results for the two models in the independent test dataset for the pre-defined threshold is shown in the figure, with relative sensitivity and specificity of around 99% and 90% respectively. An ensemble of features based deep learning CNN was developed that reduced inappropriate AF detection in ICM by over 90% while preserving sensitivity for detection of true AF. For an application specific feature based CNN, a smaller sized custom CNN performed as well as a larger sized established CNN.