Classification Method of ECG Signals Based on RANet

BACKGROUND

Electrocardiograms (ECG) are an important source of information on human heart health and are widely used to detect different types of arrhythmias.

OBJECTIVE

With the advancement of deep learning, end-to-end ECG classification models based on neural networks have been developed. However, deeper network layers lead to gradient vanishing. Moreover, different channels and periods of an ECG signal hold varying significance for identifying different types of ECG abnormalities.

METHODS

To solve these two problems, an ECG classification method based on a residual attention neural network is proposed in this paper. The residual network (ResNet) is used to solve the gradient vanishing problem. Moreover, it has fewer model parameters, and its structure is simpler. An attention mechanism is added to focus on key information, integrate channel features, and improve voting methods to alleviate the problem of data imbalance.

RESULTS

Experiments and verifications are conducted using the PhysioNet/CinC Challenge 2017 dataset. The average F1 value is 0.817, which is 0.064 higher than that for the ResNet model. Compared with the mainstream methods, the performance is excellent.

Early prediction of sudden cardiac death risk with Nested LSTM based on electrocardiogram sequential features

Electrocardiogram (ECG) signals are very important for heart disease diagnosis. In this paper, a novel early prediction method based on Nested Long Short-Term Memory (Nested LSTM) is developed for sudden cardiac death risk detection. First, wavelet denoising and normalization techniques are utilized for reliable reconstruction of ECG signals from extreme noise conditions. Then, a nested LSTM structure is adopted, which can guide the memory forgetting and memory selection of ECG signals, so as to improve the data processing ability and prediction accuracy of ECG signals. To demonstrate the effectiveness of the proposed method, four different models with different signal prediction techniques are used for comparison. The extensive experimental results show that this method can realize an accurate prediction of the cardiac beat's starting point and track the trend of ECG signals effectively. This study holds significant value for timely intervention for patients at risk of sudden cardiac death.

Detection of cardiac abnormalities from 12-lead ecg using complex wavelet sub-band features

AIM OF THE STUDY

This research endeavours to optimize cardiac anomaly detection by introducing a method focused on selecting the most effective Daubechis wavelet families. The principal aim is to differentiate between cardiac states that are normal and abnormal by utilizing longer electrocardiogram (ECG) signal events based on the Apnea ECG dataset. Apnea ECG is often used to detect sleep apnea, a sleep disorder characterized by repeated interruptions in breathing during sleep. By using machine learning methods, such as Principal Component Analysis (PCA) and different classifiers, the goal is to improve the precision of cardiac irregularity identification. Used method. To extract important statistical and sub-band information from lengthy ECG signal episodes, the study uses a novel method that combines discrete wavelet transform with Principal Component Analysis (PCA) for dimension reduction. The methodology focuses on successfully categorizing ECG signals by utilizing several classifiers, including multilayer perceptron (MLP) neural network, Ensemble Subspace K-Nearest Neighbour(KNN), and Ensemble Bagged Trees, together with varied Daubechis wavelet families (db2, db3, db4, db5, db6). Brief Description of Results. The results emphasize the importance of the chosen Daubechis wavelet family, db5, and its superiority in ECG representation. The method distinguishes normal and abnormal ECG signals well on the Physionet Apnea ECG database. The Neural Network-based method accurately recognizes 100% of healthy signals and 97.8% of problematic ones with 98.6% accuracy.

FINDINGS

The Ensemble Subspace K-Nearest Neighbour (KNN) and Ensemble Bagged Trees methods got 87.1% accuracy and 0.89 and 0.87 AOC curve values on this dataset, showing that the method works. Precision values of 0.96, 0.86, and 0.86 for MLP Neural Network, KNN Subspace, and Ensemble Bagged Trees confirm their robustness. These findings suggest wavelet families and machine learning can improve cardiac abnormality detection and categorization.

Application of LightGBM hybrid model based on TPE algorithm optimization in sleep apnea detection

Introduction

Sleep apnoea syndrome (SAS) is a serious sleep disorder and early detection of sleep apnoea not only reduces treatment costs but also saves lives. Conventional polysomnography (PSG) is widely regarded as the gold standard diagnostic tool for sleep apnoea. However, this method is expensive, time-consuming and inherently disruptive to sleep. Recent studies have pointed out that ECG analysis is a simple and effective diagnostic method for sleep apnea, which can effectively provide physicians with an aid to diagnosis and reduce patients' suffering.

Methods

To this end, in this paper proposes a LightGBM hybrid model based on ECG signals for efficient detection of sleep apnea. Firstly, the improved Isolated Forest algorithm is introduced to remove abnormal data and solve the data sample imbalance problem. Secondly, the parameters of LightGBM algorithm are optimised by the improved TPE (Tree-structured Parzen Estimator) algorithm to determine the best parameter configuration of the model. Finally, the fusion model TPE_OptGBM is used to detect sleep apnoea. In the experimental phase, we validated the model based on the sleep apnoea ECG database provided by Phillips-University of Marburg, Germany.

Results

The experimental results show that the model proposed in this paper achieves an accuracy of 95.08%, a precision of 94.80%, a recall of 97.51%, and an F1 value of 96.14%.

Discussion

All of these evaluation indicators are better than the current mainstream models, which is expected to assist the doctor's diagnostic process and provide a better medical experience for patients.

Accuracy of Heart-Rate-Recovery Parameters Assessed From a Wrist-Worn Photoplethysmography Monitor (Polar Unite)

PURPOSE

The accuracy of heart rate (HR) measured with a wrist-worn photoplethysmography (PPG) monitor is altered during rest-exercise and exercise-rest transitions, which questions the validity of postexercise HR-recovery (HRR) parameters estimated from this device.

METHODS

Thirty participants (50% female) randomly performed two 13-minute sequences (3' rest, 5' submaximal-intensity exercise, and 5' passive recovery) on treadmill and bicycle ergometers. HR was measured concomitantly with a 10-lead electrocardiogram (ECG) and a wrist-worn PPG monitor (Polar Unite). HRR was assessed by calculating Δ60 (the difference between HR during exercise and HR 60 s after exercise cessation) and by fitting HRR data into a monoexponential model.

RESULTS

By focusing on Δ60 and τ (the time constant of the monoexponential curve), levels of association (r) of the Unite versus the 10-lead ECG were high to very high (.73 < r < .93), and coefficients of variation were >20% (in absolute value), except for Δ60 in the bicycle ergometer condition (11.7%). In 97% of cases, the decrease in HR after exercise appeared later with the Unite. By adjusting the time window used for the analysis according to this time lag, coefficients of variation of Δ60 decreased below 10% in the bicycle ergometer condition.

CONCLUSIONS

If a wrist-worn PPG monitor is used to assess HRR, we recommend performing the submaximal-intensity exercise on a bicycle ergometer and focusing on Δ60. Furthermore, to obtain a more accurate Δ60, the time lag between the end of the exercise and the effective decrease in HR should also be considered before the calculation.

Improved T-wave detection in electrocardiogram signals based non-stationary wavelet transform and QRS complex cancellation with kurtosis analysis

Objective. The T-wave in electrocardiogram (ECG) signal has the potential to enumerate various cardiac dysfunctions in the cardiovascular system. The primary objective of this research is to develop an efficient method for detecting T-waves in ECG signals, with potential applications in clinical diagnosis and continuous patient monitoring.Approach. In this work, we propose a novel algorithm for T-wave peak detection, which relies on a non-decimated stationary wavelet transform method (NSWT) and involves the cancellation of the QRS complex by utilizing its local extrema. The proposed scheme contains three stages: firstly, the technique is pre-processed using a two-stage median filter and Savitzky-Golay (SG) filter to remove the various artifacts from the ECG signal. Secondly, the NSWT technique is implemented using the bior 4.4 mother wavelet without downsampling, employing 24scale analysis, and involves the cancellation of QRS-complex using its local positions. After that, Sauvola technique is used to estimate the baseline and remove the P-wave peaks to enhance T-peaks for accurate detection in the ECG signal. Additionally, the moving average window and adaptive thresholding are employed to enhance and identify the location of the T-wave peaks. Thirdly, false positive T-peaks are corrected using the kurtosis coefficients method.Main results. The robustness and efficiency of the proposed technique have been corroborated by the QT database (QTDB). The results are also validated on a self-recorded database. In QTDB database, the sensitivity of 98.20%, positive predictivity of 99.82%, accuracy of 98.04%, and detection error rate of 1.95% have been achieved. The self-recorded dataset attains a sensitivity, positive predictivity, accuracy, and detection error rate of 99.94%, 99.96%, 99.90%, and 0.09% respectively.Significance. A T-wave peak detection based on NSWT and QRS complex cancellation, along with kurtosis analysis technique, demonstrates superior performance and enhanced detection accuracy compared to state-of-the-art techniques.

An intelligent diagnostic method of ECG signal based on Markov transition field and a ResNet

BACKGROUND AND OBJECTIVE

Heart disease seriously threatens human life and health. It has the character of abruptness and is necessary to accurately monitor and intelligently diagnose electrocardiograph signals in real-time. As part of the automation of heart monitoring, the electrocardiogram (ECG) intelligent diagnosis method based on deep learning not only meets the needs of real-time and accurate but also can abandon relevant professional knowledge, which makes it possible to be promoted in the general population.

METHODS

This paper presents an intelligent diagnosis method based on a ResNet. Firstly, ECG signals from MIT-BIH Database are converted into 2-dim matrices by Markov Transition Field. Secondly, the matrices are used as the input of a ResNet. Then, the ResNet is able to extract high abstract features of various diseases and realize intelligent identification of five heartbeat types, including Normal Beat, Left Bundle Branch Block Beat, Right Bundle Branch Block Beat, Premature Ventricular Contraction Beat, and Atrial Premature Contraction Beat. Eventually, the proposed model is used to identify Normal Beat and Atrial Fibrillation(AF) based on the PAF Prediction Challenge Database(the PAFPC Database) to verify its generalization ability.

RESULTS

The experiment result shows that the intelligent diagnosis method can reach a high F1-score of 97.7% and a high accuracy upon to 99.2% on MIT-BIH Database, which are higher than the models proposed by other researchers. Its mean sensitivity and mean specificity are 97.42% and 99.54%, respectively. Moreover, the accuracy of the generalization ability verification experiment is 94.57% on the PAFPC Database, which is also higher than the results of other studies.

CONCLUSION

The research results show that the method proposed in this paper still achieves higher accuracy and higher F1-score than other methods without any data preprocessing. This method has better classification performance than traditional machine learning methods and other deep learning methods. That is, the method based on Markov Transition Field and a ResNet has good application prospects. At the same time, it has been verified that the model proposed in this paper also has excellent generalization ability.

Deep Learning Modeling of Cardiac Arrhythmia Classification on Information Feature Fusion Image with Attention Mechanism

The electrocardiogram (ECG) is a crucial tool for assessing cardiac health in humans. Aiming to enhance the accuracy of ECG signal classification, a novel approach is proposed based on relative position matrix and deep learning network information features for the classification task in this paper. The approach improves the feature extraction capability and classification accuracy via techniques of image conversion and attention mechanism. In terms of the recognition strategy, this paper presents an image conversion using relative position matrix information. This information is utilized to describe the relative spatial relationships between different waveforms, and the image identification is successfully applied to the Gam-Resnet18 deep learning network model with a transfer learning concept for classification. Ultimately, this model achieved a total accuracy of 99.30%, an average positive prediction rate of 98.76%, a sensitivity of 98.90%, and a specificity of 99.84% with the relative position matrix approach. To evaluate the effectiveness of the proposed method, different image conversion techniques are compared on the test set. The experimental results demonstrate that the relative position matrix information can better reflect the differences between various types of arrhythmias, thereby improving the accuracy and stability of classification.

Electrocardiography signal compression using non-decimated stationary wavelet transform-based technique

BACKGROUND

&#xD;In telecardiology, the bio-signal acquisition processing and communication for clinical purposes occupies larger storage and significant bandwidth over a communication channel. Electrocardiograph (ECG) compression with effective reproductivity is highly desired. In the present work, a compression technique for ECG signals with less distortion by using a non-decimated stationary wavelet with a run-length encoding scheme has been proposed.&#xD;Method:&#xD;In the present work non-decimated stationary wavelet transform (NSWT) method has been developed to compress the ECG signals. The signal is subdivided into N levels with different thresholding values. The wavelet coefficients having values larger than the threshold are evaluated and the remaining are suppressed. In the presented technique, the biorthogonal wavelet is employed as it improves the compression ratio as well percentage root means square ratio when compared to the existing method and exhibits better results. Then the coefficients are pre-processed by using the Savitzky-Golay filter which discards the corrupted signals. The wavelet coefficients are quantized using dead-zone quantization which removes the value close to zeros. To encode these values run length encoding scheme is applied and compressed ECG signals are obtained.&#xD;Results:&#xD;The presented methodology has been evaluated on the MIT-BIH arrhythmias database which contains 4800 ECG fragments from forty-eight clinical records. An average compression ratio = 33.12, PRD =1.99, NPRD =2.53, and QS = 16.57 is obtained in the proposed technique.&#xD;Conclusion:&#xD;The proposed technique exhibits a high compression ratio and reduces distortion compared to the existing method.&#xD.

An Arrhythmia Classification Model Based on Vision Transformer with Deformable Attention

The electrocardiogram (ECG) is a highly effective non-invasive tool for monitoring heart activity and diagnosing cardiovascular diseases (CVDs). Automatic detection of arrhythmia based on ECG plays a critical role in the early prevention and diagnosis of CVDs. In recent years, numerous studies have focused on using deep learning methods to address arrhythmia classification problems. However, the transformer-based neural network in current research still has a limited performance in detecting arrhythmias for the multi-lead ECG. In this study, we propose an end-to-end multi-label arrhythmia classification model for the 12-lead ECG with varied-length recordings. Our model, called CNN-DVIT, is based on a combination of convolutional neural networks (CNNs) with depthwise separable convolution, and a vision transformer structure with deformable attention. Specifically, we introduce the spatial pyramid pooling layer to accept varied-length ECG signals. Experimental results show that our model achieved an F1 score of 82.9% in CPSC-2018. Notably, our CNN-DVIT outperforms the latest transformer-based ECG classification algorithms. Furthermore, ablation experiments reveal that the deformable multi-head attention and depthwise separable convolution are both efficient in extracting features from multi-lead ECG signals for diagnosis. The CNN-DVIT achieved good performance for the automatic arrhythmia detection of ECG signals. This indicates that our research can assist doctors in clinical ECG analysis, providing important support for the diagnosis of arrhythmia and contributing to the development of computer-aided diagnosis technology.

A Novel ECG Signal Denoising Algorithm Based on Sparrow Search Algorithm for Optimal Variational Modal Decomposition

ECG signal processing is an important basis for the prevention and diagnosis of cardiovascular diseases; however, the signal is susceptible to noise interference mixed with equipment, environmental influences, and transmission processes. In this paper, an efficient denoising method based on the variational modal decomposition (VMD) algorithm combined with and optimized by the sparrow search algorithm (SSA) and singular value decomposition (SVD) algorithm, named VMD-SSA-SVD, is proposed for the first time and applied to the noise reduction of ECG signals. SSA is used to find the optimal combination of parameters of VMD [K,α], VMD-SSA decomposes the signal to obtain finite modal components, and the components containing baseline drift are eliminated by the mean value criterion. Then, the effective modalities are obtained in the remaining components using the mutual relation number method, and each effective modal is processed by SVD noise reduction and reconstructed separately to finally obtain a clean ECG signal. In order to verify the effectiveness, the methods proposed are compared and analyzed with wavelet packet decomposition, empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm. The results show that the noise reduction effect of the VMD-SSA-SVD algorithm proposed is the most significant, and that it can suppress the noise and remove the baseline drift interference at the same time, and effectively retain the morphological characteristics of the ECG signals.

Flamingo-Optimization-Based Deep Convolutional Neural Network for IoT-Based Arrhythmia Classification

Cardiac arrhythmia is a deadly disease that threatens the lives of millions of people, which shows the need for earlier detection and classification. An abnormal signal in the heart causing arrhythmia can be detected at an earlier stage when the health data from the patient are monitored using IoT technology. Arrhythmias may suddenly lead to death and the classification of arrhythmias is considered a complicated process. In this research, an effective classification model for the classification of heart disease is developed using flamingo optimization. Initially, the ECG signal from the heart is collected and then it is subjected to the preprocessing stage; to detect and control the electrical activity of the heart, the electrocardiogram (ECG) is used. The input signals collected using IoT nodes are collectively presented in the base station for the classification using flamingo-optimization-based deep convolutional networks, which effectively predict the disease. With the aid of communication technologies and the contribution of IoT, medical professionals can easily monitor the health condition of patients. The performance is analyzed in terms of accuracy, sensitivity, and specificity.

Diagnosis of atrial fibrillation using self-complementary attentional convolutional neural network

BACKGROUND AND OBJECTIVE

Automatic recognition of wearable dynamic electrocardiographic (ECG) signals is a difficult problem in biomedical signal processing. However, with the widespread use of long-range ambulatory ECG, a large number of real-time ECG signals are generated in the clinic, and it is very difficult for clinicians to perform timely atrial fibrillation (AF) diagnosis. Therefore, developing a new AF diagnosis algorithm can relieve the pressure on the healthcare system and improve the efficiency of AF screening.

METHODS

In this study, a self-complementary attentional convolutional neural network (SCCNN) was designed to accurately identify AF in wearable dynamic ECG signals. First, a 1D ECG signal was converted into a 2D ECG matrix using the proposed Z-shaped signal reconstruction method. Then, a 2D convolutional network was used to extract shallow information from adjacent sampling points at close distances and interval sampling points at distant distances in the ECG signal. The self-complementary attention mechanism (SCNet) was used to focus and fuse channel information with spatial information. Finally, fused feature sequences were used to detect AF.

RESULTS

The accuracies of the proposed method on the three public databases were 99.79%, 95.51%, and 98.80%. The AUC values were 99.79%, 95.51%, and 98.77%, respectively. The sensitivity on the clinical database was as high as 99.62%.

CONCLUSIONS

These results show that the proposed method can accurately identify AF and has good generalization.

Classification of Blood Pressure Levels Based on Photoplethysmogram and Electrocardiogram Signals with a Concatenated Convolutional Neural Network

Hypertension is a severe public health issue worldwide that significantly increases the risk of cardiac vascular disease, stroke, brain hemorrhage, and renal dysfunction. Early screening of blood pressure (BP) levels is essential to prevent the dangerous complication associated with hypertension as the leading cause of death. Recent studies have focused on employing photoplethysmograms (PPG) with machine learning to classify BP levels. However, several studies claimed that electrocardiograms (ECG) also strongly correlate with blood pressure. Therefore, we proposed a concatenated convolutional neural network which integrated the features extracted from PPG and ECG signals. This study used the MIMIC III dataset, which provided PPG, ECG, and arterial blood pressure (ABP) signals. A total of 14,298 signal segments were obtained from 221 patients, which were divided into 9150 signals of train data, 2288 signals of validation data, and 2860 signals of test data. In the training process, five-fold cross-validation was applied to select the best model with the highest classification performance. The proposed concatenated CNN architecture using PPG and ECG obtained the highest test accuracy of 94.56-95.15% with a 95% confidence interval in classifying BP levels into hypotension, normotension, prehypertension, hypertension stage 1, and hypertension stage 2. The result shows that the proposed method is a promising solution to categorize BP levels effectively, assisting medical personnel in making a clinical diagnosis.

ECG segmentation algorithm based on bidirectional hidden semi-Markov model

Accurate segmentation of electrocardiogram (ECG) waves is crucial for cardiovascular diseases (CVDs). In this study, a bidirectional hidden semi-Markov model (BI-HSMM) based on the probability distributions of ECG waveform duration was proposed for ECG wave segmentation. Four feature-vectors of ECG signals were extracted as the observation sequence of the hidden Markov model (HMM), and the statistical probability distribution of each waveform duration was counted. Logistic regression (LR) was used to train model parameters. The starting and ending positions of the QRS wave were first detected, and thereafter, bidirectional prediction was employed for the other waves. Forwardly, ST segment, T wave, and TP segment were predicted. Backwardly, P wave and PQ segments were detected. The Viterbi algorithm was improved by integrating the recursive formula of the forward prediction and backward backtracking algorithms. In the QT database, the proposed method demonstrated excellent performance (Acc = 97.98%, F1 score of P wave = 98.37%, F1 score of QRS wave = 97.60%, F1 score of T wave = 97.79%). For the wearable dynamic electrocardiography (DCG) signals collected by the Shandong Provincial Hospital (SPH), the detection accuracy was 99.71% and the F1 of each waveform was above 99%. The experimental results and real DCG signal validation confirmed that the proposed new BI-HSMM method exhibits significant ability to segment the resting and DCG signals; this is conducive to the detection and monitoring of CVDs.

Independent Detection of T-Waves in Single Lead ECG Signal Using Continuous Wavelet Transform

INTRODUCTION

In the ECG signals, T-waves play a very important role in the detection of cardiac arrest. During myocardial ischemia, the first significant change occurs on the T-wave. These waves are generated due to the repolarization of the heart ventricle. The independent detection of T-waves is a bit challenging due to its variable nature, therefore, most of the algorithms available in the literature for T-wave detection use the detection of the QRS complex as the starting point. But accurate detection of Twave is very much required, as clinically, the first indication of a shortage of blood supply to the heart muscle (myocardial ischemia) shows up as changes in T-wave followed by other changes in the morphology of the ECG signal.

MATERIALS AND METHODS

In this paper, an efficient and novel algorithm based on Continuous Wavelet Transform (CWT) is presented to detect the Twave independently. In CWT, for better matching, a new mother wavelet is designed using the pattern and shape of the Twave. This algorithm is validated on all the signals of the QT database.

CONCLUSION

The algorithm attains an average sensitivity of 99.88% and positive predictivity of 99.81% for the signals annotated by the cardiologists in the database.

QRS complex detection using stationary wavelet transform and adaptive thresholding

Purpose- Electrocardiogram (ECG) signal is a record of the electrical activity of the heart and contains important clinical data about cardiovascular-related misfunctioning. The goal of the present work is to develop an improved QRS detection algorithm for the detection of heart abnormalities. Methods- In this present work stationary wavelet transforms (SWT) based method has been proposed for precise detection of QRS complex with 'sym2' mother wavelet. The stationary wavelet transform is a systematic mathematical tool to decompose the signal without downsampling using scale analysis and provides high detection of QRS complex and accurate localization of signal components. In the proposed method four level of decomposition is applied and the initial thresholding value is computed by the maximum amplitude of scale one at level four in SWT coefficients without the zero-crossing amplitude detection method. The multi-layered dynamic thresholding method has been applied to detect the true R-peak values and locate the QRS complex in the ECG signal. Results- For evaluation of results, the presented methodology is assessed on MIT-BIH, QTDB, and Noise stress test databases. In MIT-BIH, the sensitivity = 99.88%, positive predictivity = 99.93%, accuracy = 99.80% and detection error rate = 0.18% is achieved. In NSTD database, sensitivity = 97.46%, positive predictivity = 94.20%, accuracy = 91.95% and detection error rate = 8.47% and in QTDB, sensitivity = 99.95%, positive predictivity = 99.90%, accuracy = 99.71% and detection error rate = 0.16% is executed. Conclusion- In the presented proposed methodology, the computation complexity is low and exhibits a simple technique rather than an empirical approach. The proposed technique corroborates the performance for the detection of QRS complex with improved accuracy.

A method to detect sleep apnea using residual attention mechanism network from single-lead ECG signal

Sleep apnea is a sleep disorder caused by weakened or suspended breathing during sleep, which seriously affects the work and health of patients. The traditional polysomnography (PSG) detection process is complicated and expensive, which has attracted researchers to explore a rapid detection method based on single-lead ECG signals. However, existing ECG-based sleep apnea detection methods have certain limitations and complexities, mainly relying on human-crafted features. To solve the problem, the paper develops a sleep apnea detection method based on a residual attention mechanism network. The method uses the RR interval signal and the R-peak signal derived from the ECG signal as input, realizes feature extraction through the residual network (ResNet), and adds the SENet attention mechanism to deepen the mining of channel features. Experimental results show that the per-segment accuracy of the proposed method can reach 86.2%. Compared with existing works, its accuracy has increased by 1.1-8.1%. These results show that the proposed residual attention network can effectively use ECG signals to quickly detect sleep apnea. Meanwhile, compared with existing works, the proposed method overcomes the limitations and complexity of human-crafted features in sleep apnea detection research.

Deep Compressive Sensing on ECG Signals with Modified Inception Block and LSTM

In practical electrocardiogram (ECG) monitoring, there are some challenges in reducing the data burden and energy costs. Therefore, compressed sensing (CS) which can conduct under-sampling and reconstruction at the same time is adopted in the ECG monitoring application. Recently, deep learning used in CS methods improves the reconstruction performance significantly and can removes of some of the constraints in traditional CS. In this paper, we propose a deep compressive-sensing scheme for ECG signals, based on modified-Inception block and long short-term memory (LSTM). The framework is comprised of four modules: preprocessing; compression; initial; and final reconstruction. We adaptively compressed the normalized ECG signals, sequentially using three convolutional layers, and reconstructed the signals with a modified Inception block and LSTM. We conducted our experiments on the MIT-BIH Arrhythmia Database and Non-Invasive Fetal ECG Arrhythmia Database to validate the robustness of our model, adopting Signal-to-Noise Ratio (SNR) and percentage Root-mean-square Difference (PRD) as the evaluation metrics. The PRD of our scheme was the lowest and the SNR was the highest at all of the sensing rates in our experiments on both of the databases, and when the sensing rate was higher than 0.5, the PRD was lower than 2%, showing significant improvement in reconstruction performance compared to the comparative methods. Our method also showed good recovering quality in the noisy data.

Diabetes Detection and Management through Photoplethysmographic and Electrocardiographic Signals Analysis: A Systematic Review

(1) Background: Diabetes mellitus (DM) is a chronic, metabolic disease characterized by elevated levels of blood glucose. Recently, some studies approached the diabetes care domain through the analysis of the modifications of cardiovascular system parameters. In fact, cardiovascular diseases are the first leading cause of death in diabetic subjects. Thanks to their cost effectiveness and their ease of use, electrocardiographic (ECG) and photoplethysmographic (PPG) signals have recently been used in diabetes detection, blood glucose estimation and diabetes-related complication detection. This review's aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (2) Method: We performed a systematic review based on articles that focus on the use of ECG and PPG signals in diabetes care. The search was focused on keywords related to the topic, such as "Diabetes", "ECG", "PPG", "Machine Learning", etc. This was performed using databases, such as PubMed, Google Scholar, Semantic Scholar and IEEE Xplore. This review's aim is to provide a detailed overview of all the published methods, from the traditional (non machine learning) to the deep learning approaches, to detect and manage diabetes using PPG and ECG signals. This review will allow researchers to compare and understand the differences, in terms of results, amount of data and complexity that each type of approach provides and requires. (3) Results: A total of 78 studies were included. The majority of the selected studies focused on blood glucose estimation (41) and diabetes detection (31). Only 7 studies focused on diabetes complications detection. We present these studies by approach: traditional, machine learning and deep learning approaches. (4) Conclusions: ECG and PPG analysis in diabetes care showed to be very promising. Clinical validation and data processing standardization need to be improved in order to employ these techniques in a clinical environment.

Can the Standard Configuration of a Cardiac Monitor Lead to Medical Errors under a Stress Induction?

The essential factor that enables medical patient monitoring is the vital signs monitor, whereas the key in communication with the monitor is the user interface. The way the data display on the monitors is standard, and it is often not changed; however, vital signs monitors are now configurable. Not all the data have to be displayed concurrently; not all data are necessary at a given moment. There arises a question: is the standard monitor configuration sufficient, or can it lead to mistakes related to delays in perceiving parameter changes? Some researchers argue that mistakes in life-saving activities is not mainly due to medical mistakes but due to poorly designed patient life monitor interfaces, among other reasons. In addition, it should be emphasized that the activity that saves the patient’s life is accompanied by stress, which is often caused by the chaos occurring in the hospital emergency department. This raises the following question: is the standard user interface, which they are used to, still effective under stress conditions? Therefore, our primary consideration is the measure of reaction speed of medical staff, which means the perception of the changes of vital signs on the patient’s monitor, for stress and stressless situations. The paper attempts to test the thesis of the importance of the medical interface and its relation to medical mistakes, extending it with knowledge about the difference in speed of making decisions by the medical staff with regard to the stress stimulus.

Automatic ECG classification and label quality in training data

OBJECTIVE

Within the PhysioNet/Computing in Cardiology Challenge 2021, we focused on the design of a machine learning algorithm to identify cardiac abnormalities from electrocardiogram recordings (ECGs) with a various number of leads and to assess the diagnostic potential of reduced-lead ECGs compared to standard 12-lead ECGs.

APPROACH

In our solution, we developed a model based on a deep convolutional neural network, which is a 1D variant of the popular ResNet50 network. This base model was pre-trained on a large training set with our proposed mapping of original labels to SNOMED codes, using three-valued labels. In the next phase, the model was fine-tuned for the Challenge metric and conditions.

MAIN RESULTS

In the Challenge, our proposed approach (team CeZIS) achieved a Challenge test score of 0.52 for all lead configurations, placing us 5th out of 39 in the official ranking. Our improved post-Challenge solution was evaluated as the best for all ranked configurations, i.e., for 12-lead, 3-lead, and 2-lead versions of the full test set with the Challenge test score of 0.62, 0.61, and 0.59, respectively.

SIGNIFICANCE

In addition to building the model for identifying cardiac anomalies, we provide a more detailed description of the issues associated with label mapping and propose its modification in order to obtain a better starting point for training more powerful classification models. We compare the performance of models for different numbers of leads and identify labels for which two leads are sufficient. Moreover, we evaluate the label quality in individual parts of the Challenge training set.

Deep Learning Techniques in the Classification of ECG Signals Using R-Peak Detection Based on the PTB-XL Dataset

Deep Neural Networks (DNNs) are state-of-the-art machine learning algorithms, the application of which in electrocardiographic signals is gaining importance. So far, limited studies or optimizations using DNN can be found using ECG databases. To explore and achieve effective ECG recognition, this paper presents a convolutional neural network to perform the encoding of a single QRS complex with the addition of entropy-based features. This study aims to determine what combination of signal information provides the best result for classification purposes. The analyzed information included the raw ECG signal, entropy-based features computed from raw ECG signals, extracted QRS complexes, and entropy-based features computed from extracted QRS complexes. The tests were based on the classification of 2, 5, and 20 classes of heart diseases. The research was carried out on the data contained in a PTB-XL database. An innovative method of extracting QRS complexes based on the aggregation of results from established algorithms for multi-lead signals using the k-mean method, at the same time, was presented. The obtained results prove that adding entropy-based features and extracted QRS complexes to the raw signal is beneficial. Raw signals with entropy-based features but without extracted QRS complexes performed much worse.

Real-Time Stress Level Feedback from Raw Ecg Signals for Personalised, Context-Aware Applications Using Lightweight Convolutional Neural Network Architectures

Human stress is intricately linked with mental processes such as decision making. Public protection practitioners, including Law Enforcement Agents (LEAs), are forced to make difficult decisions during high-pressure operations, under strenuous circumstances. In this respect, systems and applications that assist such practitioners to take decisions, are increasingly incorporating user stress level information for their development, adaptation, and evaluation. To that end, our goal is to accurately detect and classify the level of acute, short-term stress, in real time, for the development of personalized, context-aware solutions for LEAs. Deep Neural Networks (DNNs), and in particular Convolutional Neural Networks (CNNs), have been gaining traction in the field of stress analysis, exhibiting promising results. Furthermore, the electrocardiogram (ECG) signals, have also been widely adopted for estimating levels of stress. In this work, we propose two CNN architectures for the stress detection and 3-level (low, moderate, high) stress classification tasks, using ultra short-term raw ECG signals (3 s). One architecture is simple and with a low memory footprint, suitable for running in wearable edge-computing nodes, and the other is able to learn more complex features, having more trainable parameters. The models were trained on the two publicly available stress classification datasets, after applying pre-processing techniques, such as data pruning, down-sampling, and data augmentation, using a sliding window approach. After hyperparameter tuning, using 4-fold cross-validation, the evaluation on the test set demonstrated state-of-the-art accuracy both on the 3- and 2-level stress classification task using the DriveDB dataset, reporting an accuracy of 83.55% and 98.77% respectively.

Classification of electrocardiogram signals with waveform morphological analysis and support vector machines

Electrocardiogram (ECG) indicates the occurrence of various cardiac diseases, and the accurate classification of ECG signals is important for the automatic diagnosis of arrhythmia. This paper presents a novel classification method based on multiple features by combining waveform morphology and frequency domain statistical analysis, which offer improved classification accuracy and minimise the time spent for classifying signals. A wavelet packet is used to decompose a denoised ECG signal, and the singular value, maximum value, and standard deviation of the decomposed wavelet packet coefficients are calculated to obtain the frequency domain feature space. The slope threshold method is applied to detect R peak and calculate RR intervals, and the first two RR intervals are extracted as time-domain features. The fusion feature space is composed of time and frequency domain features. A combination of support vector machine (SVM) with the help of grid search and waveform morphological analysis is applied to complete nine types of ECG signal classification. Computer simulations show that the accuracy of the proposed algorithm on multiple types of arrhythmia databases can reach 96.67%.

Improved NLMS-based adaptive denoising method for ECG signals

BACKGROUND

Traditional least mean square algorithm (LMS) tends to converge faster and thus the larger the steady-state error of the algorithm.

OBJECTIVE

In order to solve this issue, an improved adaptive normalized least mean square (NLMS) ECG signal denoising algorithm is proposed through utilizing the NLMS and the least mean square algorithm with added momentum term (MLMS).

METHODS

The algorithm firstly performs LMS adaptive filtering on the original ECG signal. Then, the algorithm uses the relative error of the prior error signal and the posterior error signal before and after filtering to adaptively determine the iteration step factor. Finally, the expected error is set to determine whether the denoising meets the expected requirements. This method is applied to the MIT-BIH ECG database established by the Massachusetts Institute of Technology.

RESULTS

Experimental results have shown that the proposed algorithm can achieve good denoising for the target signal, and the average signal to noise ratio (SNR) of the proposed method is 17.6016, the RMSE is only 0.0334, and the average smoothness index R is only 0.0325.

CONCLUSION

The proposed algorithm effectively removes the original ECG signal noise, and improves the smoothness of the signal the denoising efficiency.

Optimization based ECG watermarking in RDWT-SVD domain

With the increase in point of care services, communication of digital patient records through open network has multi-folded. This digital data is used to obtain the remote medical assistance from the smart healthcare centres. Protecting this data during transmission is a very big challenge. One of the most important medical data is electrocardiogram (ECG) signal which detects the cardiovascular diseases and any alteration in the signal may affect the diagnosis. In this work, an ECG watermarking based on redundant discrete wavelet transform (RDWT) and singular value decomposition (SVD) is developed. First, the ECG signal is converted into 2-D matrix using pan-tompkins algorithm. Then, we use the hybrid of RDWT and SVD to conceal the patient data and logo image into the 2-D ECG image. We also use hybrid of optimization scheme to improve the robustness of the watermark. Preliminary experimental results indicate the optimal invisibility and robustness result is more effective up to 97.89% than the traditional schemes respectively, which makes it suitable for ownership authentication of ECG signal.

AFCNNet: Automated detection of AF using chirplet transform and deep convolutional bidirectional long short term memory network with ECG signals

Atrial fibrillation (AF) is the most common type of cardiac arrhythmia and is characterized by the heart's beating in an uncoordinated manner. In clinical studies, patients often do not have visible symptoms during AF, and hence it is harder to detect this cardiac ailment. Therefore, automated detection of AF using the electrocardiogram (ECG) signals can reduce the risk of stroke, coronary artery disease, and other cardiovascular complications. In this paper, a novel time-frequency domain deep learning-based approach is proposed to detect AF and classify terminating and non-terminating AF episodes using ECG signals. This approach involves evaluating the time-frequency representation (TFR) of ECG signals using the chirplet transform. The two-dimensional (2D) deep convolutional bidirectional long short-term memory (BLSTM) neural network model is used to detect and classify AF episodes using the time-frequency images of ECG signals. The proposed TFR based 2D deep learning approach is evaluated using the ECG signals from three public databases. Our developed approach has obtained an accuracy, sensitivity, and specificity of 99.18% (Confidence interval (CI) as [98.86, 99.49]), 99.17% (CI as [98.85 99.49]), and 99.18% (CI as [98.86 99.49]), respectively, with 10-fold cross-validation (CV) technique to detect AF automatically. The proposed approach also classified terminating and non-terminating AF episodes with an average accuracy of 75.86%. The average accuracy value obtained using the proposed approach is higher than the short-time Fourier transform (STFT), discrete-time continuous wavelet transform (DT-CWT), and Stockwell transform (ST) based time-frequency analysis methods with deep convolutional BLSTM models to detect AF. The proposed approach has better AF detection performance than the existing deep learning-based techniques using ECG signals from the MIT-BIH database.

ECG Signal Classification Using Deep Learning Techniques Based on the PTB-XL Dataset

The analysis and processing of ECG signals are a key approach in the diagnosis of cardiovascular diseases. The main field of work in this area is classification, which is increasingly supported by machine learning-based algorithms. In this work, a deep neural network was developed for the automatic classification of primary ECG signals. The research was carried out on the data contained in a PTB-XL database. Three neural network architectures were proposed: the first based on the convolutional network, the second on SincNet, and the third on the convolutional network, but with additional entropy-based features. The dataset was divided into training, validation, and test sets in proportions of 70%, 15%, and 15%, respectively. The studies were conducted for 2, 5, and 20 classes of disease entities. The convolutional network with entropy features obtained the best classification result. The convolutional network without entropy-based features obtained a slightly less successful result, but had the highest computational efficiency, due to the significantly lower number of neurons.

Construction of wavelet dictionaries for ECG modeling

Technical details, algorithms, and MATLAB implementation for a method advanced in the paper ``Wavelet Based Dictionaries for Dimensionality Reduction of ECG Signals'', are presented. This work aims to be the companion of that publication, in which an adaptive mathematical model for a given ECG record is proposed. The method comprises the following building blocks.(i)

Construction of a suitable redundant set, called 'dictionary', for decomposing an ECG signal as a superposition of elementary components, called 'atoms', selected from that dictionary.

(ii)

Implementation of the greedy strategy Optimized Orthogonal Matching Pursuit (OOMP) for selecting the atoms intervening in the signal decomposition.

This paper gives the details of the algorithms for implementing stage (i), which is not fully elaborated in the previous publication. The proposed dictionaries are constructed from known wavelet families, but translating the prototypes with a shorter step than that corresponding to a wavelet basis. Stage (ii) is readily implementable by the available function OOMP.•

The use of the software and the power of the technique is illustrated by reducing the dimensionality of ECG records taken from the MIT-BIH Arrhythmia Database.

•

The MATLAB software has been made publicly available on a dedicated website.

•

We provide the explanations, algorithms and software for the construction of scaling functions and wavelet prototypes for 17 different wavelet families. The procedure is designed to allow for straightforward extension of the software by the inclusion of additional options for the wavelet families.

PVC arrhythmia classification based on fractional order system modeling

It is well known that many physiological phenomena are modeled accurately and effectively using fractional operators and systems. This type of modeling is due mainly to the dynamical link between fractional-order systems and the fractal structures of the physiological systems. The automatic characterization of the premature ventricular contraction (PVC) is very important for early diagnosis of patients with different life-threatening cardiac diseases. In this paper, a classification scheme of normal and PVC beats of the electrocardiogram (ECG) signal is proposed. The clustering features used for normal and PVC beats discrimination are the parameters of the commensurate order linear fractional model of the frequency content of the QRS complex of the ECG signal. A series of tests and comparisons have been performed to evaluate and validate the efficiency of the proposed PVC classification algorithm using the MIT-BIH arrhythmia database. The proposed PVC classification method has achieved an overall accuracy of 94.745%, a specificity of 95.178% and a sensitivity of 90.021% using all the 48 records of the database.

Ensemble of Deep Learning Models for Sleep Apnea Detection: An Experimental Study

Sleep Apnea is a breathing disorder occurring during sleep. Older people suffer most from this disease. In-time diagnosis of apnea is needed which can be observed by the application of a proper health monitoring system. In this work, we focus on Obstructive Sleep Apnea (OSA) detection from the Electrocardiogram (ECG) signals obtained through the body sensors. Our work mainly consists of an experimental study of different ensemble techniques applied on three deep learning models—two Convolutional Neural Network (CNN) based models, and a combination of CNN and Long Short-Term Memory (LSTM) models, which were previously proposed in the OSA detection domain. We have chosen four ensemble techniques—majority voting, sum rule and Choquet integral based fuzzy fusion and trainable ensemble using Multi-Layer Perceptron (MLP) for our case study. All the experiments are conducted on the benchmark PhysioNet Apnea-ECG Database. Finally, we have achieved highest OSA detection accuracy of 85.58% using the MLP based ensemble approach. Our best result is also able to surpass many of state-of-the-art methods.

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.

Identification of 27 abnormalities from multi-lead ECG signals: an ensembled SE_ResNet framework with Sign Loss function

Objective. Cardiovascular disease is a major threat to health and one of the primary causes of death globally. The 12-lead ECG is a cheap and commonly accessible tool to identify cardiac abnormalities. Early and accurate diagnosis will allow early treatment and intervention to prevent severe complications of cardiovascular disease. Our objective is to develop an algorithm that automatically identifies 27 ECG abnormalities from 12-lead ECG databases.Approach. Firstly, a series of pre-processing methods were proposed and applied on various data sources in order to mitigate the problem of data divergence. Secondly, we ensembled two SE_ResNet models and one rule-based model to enhance the performance of various ECG abnormalities' classification. Thirdly, we introduce a Sign Loss to tackle the problem of class imbalance, and thus improve the model's generalizability.Main results. In the PhysioNet/Computing in Cardiology Challenge (2020), our proposed approach achieved a challenge validation score of 0.682, and a full test score of 0.514, placed us 3rd out of 40 in the official ranking.Significance. We proposed an accurate and robust predictive framework that combines deep neural networks and clinical knowledge to automatically classify multiple ECG abnormalities. Our framework is able to identify 27 ECG abnormalities from multi-lead ECG signals regardless of discrepancies in data sources and the imbalance of data labeling. We trained our framework on five datasets and validated it on six datasets from various countries. The outstanding performance demonstrate the effectiveness of our proposed framework.

Using Convolutional Neural Network and a Single Heartbeat for ECG Biometric Recognition

The electrocardiogram (ECG) signal has become a popular biometric modality due to characteristics that make it suitable for developing reliable authentication systems. However, the long segment of signal required for recognition is still one of the limitations of existing ECG biometric recognition methods and affects its acceptability as a biometric modality. This paper investigates how a short segment of an ECG signal can be effectively used for biometric recognition, using deep-learning techniques. A small convolutional neural network (CNN) is designed to achieve better generalization capability by entropy enhancement of a short segment of a heartbeat signal. Additionally, it investigates how various blind and feature-dependent segments with different lengths affect the performance of the recognition system. Experiments were carried out on two databases for performance evaluation that included single and multisession records. In addition, a comparison was made between the performance of the proposed classifier and four well-known CNN models: GoogLeNet, ResNet, MobileNet and EfficientNet. Using a time-frequency domain representation of a short segment of an ECG signal around the R-peak, the proposed model achieved an accuracy of 99.90% for PTB, 98.20% for the ECG-ID mixed-session, and 94.18% for ECG-ID multisession datasets. Using the preprinted ResNet, we obtained 97.28% accuracy for 0.5-second segments around the R-peaks for ECG-ID multisession datasets, outperforming existing methods. It was found that the time-frequency domain representation of a short segment of an ECG signal can be feasible for biometric recognition by achieving better accuracy and acceptability of this modality.

Constrained transformer network for ECG signal processing and arrhythmia classification

BACKGROUND

Heart disease diagnosis is a challenging task and it is important to explore useful information from the massive amount of electrocardiogram (ECG) records of patients. The high-precision diagnostic identification of ECG can save clinicians and cardiologists considerable time while helping reduce the possibility of misdiagnosis at the same time.Currently, some deep learning-based methods can effectively perform feature selection and classification prediction, reducing the consumption of manpower.

METHODS

In this work, an end-to-end deep learning framework based on convolutional neural network (CNN) is proposed for ECG signal processing and arrhythmia classification. In the framework, a transformer network is embedded in CNN to capture the temporal information of ECG signals and a new link constraint is introduced to the loss function to enhance the classification ability of the embedding vector.

RESULTS

To evaluate the proposed method, extensive experiments based on real-world data were conducted. Experimental results show that the proposed model achieve better performance than most baselines. The experiment results also proved that the transformer network pays more attention to the temporal continuity of the data and captures the hidden deep features of the data well. The link constraint strengthens the constraint on the embedded features and effectively suppresses the effect of data imbalance on the results.

CONCLUSIONS

In this paper, an end-to-end model is used to process ECG signal and classify arrhythmia. The model combine CNN and Transformer network to extract temporal information in ECG signal and is capable of performing arrhythmia classification with acceptable accuracy. The model can help cardiologists perform assisted diagnosis of heart disease and improve the efficiency of healthcare delivery.

Automated Detection of Hypertension Using Physiological Signals: A Review

Arterial hypertension (HT) is a chronic condition of elevated blood pressure (BP), which may cause increased incidence of cardiovascular disease, stroke, kidney failure and mortality. If the HT is diagnosed early, effective treatment can control the BP and avert adverse outcomes. Physiological signals like electrocardiography (ECG), photoplethysmography (PPG), heart rate variability (HRV), and ballistocardiography (BCG) can be used to monitor health status but are not directly correlated with BP measurements. The manual detection of HT using these physiological signals is time consuming and prone to human errors. Hence, many computer-aided diagnosis systems have been developed. This paper is a systematic review of studies conducted on the automated detection of HT using ECG, HRV, PPG and BCG signals. In this review, we have identified 23 studies out of 250 screened papers, which fulfilled our eligibility criteria. Details of the study methods, physiological signal studied, database used, various nonlinear techniques employed, feature extraction, and diagnostic performance parameters are discussed. The machine learning and deep learning based methods based on ECG and HRV signals have yielded the best performance and can be used for the development of computer-aided diagnosis of HT. This work provides insights that may be useful for the development of wearable for continuous cuffless remote monitoring of BP based on ECG and HRV signals.

IoT-enabled cloud-based real-time remote ECG monitoring system

Statistical reports all around the world have deemed cardiovascular diseases (CVDs) as the largest contributor to the death count. The electrocardiogram (ECG) is a widely accepted technology employed for investigation of CVDs of the person. The proposed solution deals with an efficient internet of things (IoT) enabled real-time ECG monitoring system using cloud computing technologies. The article presents a cloud-centric solution to provide remote monitoring of CVD. Sensed ECG data are transmitted to S3 bucket provided by Amazon web service (AWS) through a mobile gateway. AWS cloud uses HTTP and MQTT servers to provide data visualisation, quick response and long-live connection to device and user. Bluetooth low energy (BLE 4.0) is used as a communication protocol for low-power data transmission between device and mobile gateway. The proposed system is implemented with filtering algorithms to ignore distractions, environmental noise and motion artefacts. It offers an analysis of ECG signals to detect various parameters such as heartbeat, PQRST wave and QRS complex intervals along with respiration rate. The proposed system prototype has been tested and validated for reliable ECG monitoring remotely in real-time.

[Application of Improved Wavelet Threshold in Denoising of ECG Signals]

The ECG signal is susceptible to interference from the external environment during the acquisition process, affecting the analysis and processing of the ECG signal. After the traditional soft-hard threshold function is processed, there is a defect that the signal quality is not high and the continuity at the threshold is poor. An improved threshold function wavelet denoising is proposed, which has better regulation and continuity, and effectively solves the shortcomings of traditional soft and hard threshold functions. The Matlab simulation is carried out through a large amount of data, and various processing methods are compared. The results show that the improved threshold function can improve the denoising effect and is superior to the traditional soft and hard threshold denoising.

Explainable artificial intelligence for heart rate variability in ECG signal

Electrocardiogram (ECG) signal is one of the most reliable methods to analyse the cardiovascular system. In the literature, there are different deep learning architectures proposed to detect various types of tachycardia diseases, such as atrial fibrillation, ventricular fibrillation, and sinus tachycardia. Even though all types of tachycardia diseases have fast beat rhythm as the common characteristic feature, existing deep learning architectures are trained with the corresponding disease-specific features. Most of the proposed works lack the interpretation and understanding of the results obtained. Hence, the objective of this letter is to explore the features learned by the deep learning models. For the detection of the different types of tachycardia diseases, the authors used a transfer learning approach. In this method, the model is trained with one of the tachycardia diseases called atrial fibrillation and tested with other tachycardia diseases, such as ventricular fibrillation and sinus tachycardia. The analysis was done using different deep learning models, such as RNN, LSTM, GRU, CNN, and RSCNN. RNN achieved an accuracy of 96.47% for atrial fibrillation data set, 90.88% accuracy for CU-ventricular tachycardia data set, and also achieved an accuracy of 94.71, and 94.18% for MIT-BIH malignant ventricular ectopy database for ECG lead I and lead II, respectively. The RNN model could only achieve an accuracy of 23.73% for the sinus tachycardia data set. A similar trend is shown by other models. From the analysis, it was evident that even though tachycardia diseases have fast beat rhythm as their common feature, the model was not able to detect different types of tachycardia diseases. The deep learning model could only detect atrial fibrillation and ventricular fibrillation and failed in the case of sinus tachycardia. From the analysis, they were able to interpret that, along with the fast beat rhythm, the model has learned the absence of P-wave which is a common feature for ventricular fibrillation and atrial fibrillation but sinus tachycardia disease has an upright positive P-wave. The time-based analysis is conducted to find the time complexity of the models. The analysis conveyed that RNN and RSCNN models could achieve better performance with lesser time complexity.

A Novel Classification Method for a Driver's Cognitive Stress Level by Transferring Interbeat Intervals of the ECG Signal to Pictures

In this study, a novel classification method for a driver's cognitive stress level was proposed, whereby the interbeat intervals extracted from an electrocardiogram (ECG) signal were transferred to pictures, and a convolution neural network (CNN) was used to train the pictures to classify a driver's cognitive stress level. First, we defined three levels of tasks and collected the ECG signal of the driver at different cognitive stress levels by designing and performing a driving simulation experiment. We extracted the interbeat intervals and converted them to pictures according to the number of consecutive interbeat intervals in each picture. Second, the CNN model was used to train the data set to recognize the cognitive stress levels. Classification accuracies of 100%, 91.6% and 92.8% were obtained for the training set, validation set and test set, respectively, and were compared with those the BP neural network. Last, we discussed the influence of the number of interbeat intervals in each picture on the performance of the proposed classification method. The results showed that the performance initially improved with an increase in the number of interbeat intervals. A downward trend was observed when the number exceeded 40, and when the number was 40, the model performed best with the highest accuracy (98.79%) and a relatively low relative standard deviation (0.019).

Early Detection of Atrial Fibrillation Based on ECG Signals

Atrial fibrillation, often called AF is considered to be the most common type of cardiac arrhythmia, which is a major healthcare challenge. Early detection of AF and the appropriate treatment is crucial if the symptoms seem to be consistent and persistent. This research work focused on the development of a heart monitoring system which could be considered as a feasible solution in early detection of potential AF in real time. The objective was to bridge the gap in the market for a low-cost, at home use, noninvasive heart health monitoring system specifically designed to periodically monitor heart health in subjects with AF disorder concerns. The main characteristic of AF disorder is the considerably higher heartbeat and the varying period between observed R waves in electrocardiogram (ECG) signals. This proposed research was conducted to develop a low cost and easy to use device that measures and analyzes the heartbeat variations, varying time period between successive R peaks of the ECG signal and compares the result with the normal heart rate and RR intervals. Upon exceeding the threshold values, this device creates an alert to notify about the possible AF detection. The prototype for this research consisted of a Bitalino ECG sensor and electrodes, an Arduino microcontroller, and a simple circuit. The data was acquired and analyzed using the Arduino software in real time. The prototype was used to analyze healthy ECG data and using the MIT-BIH database the real AF patient data was analyzed, and reasonable threshold values were found, which yielded a reasonable success rate of AF detection.

[Development of a Wearable Wireless ECG Monitoring System with Ultra-low Power Consumption]

This study describes the development of a wireless and wearable ECG monitoring system with ultra-low power consumption. The system is mainly composed of a connection part of an ECG electrode sticker, an electrocardiogram collecting part, a data storage part, a Bluetooth main control unit, a charging module, a voltage regulator and a lithium battery. The low-power ECG acquisition chip ADS1292R and the ultra-low-power Bluetooth microcontroller nRF51822 together constitute the ECG signal acquisition and wireless data communication part. The collected ECG signals can be sent to the mobile APP through the Bluetooth function provided by the MCU, and can completly display and analysis to achieve low power system. After testing, the system power consumption is only (3.7 V×2.87 mA)10.619 mW, and if it is optimized, it can further reduce power consumption, therefore, the system design can have good applicability.

Classification of Sleep Apnea Severity by Electrocardiogram Monitoring Using a Novel Wearable Device

Sleep apnea (SA) is a prevalent disorder diagnosed by polysomnography (PSG) based on the number of apnea–hypopnea events per hour of sleep (apnea–hypopnea index, AHI). PSG is expensive and technically complex; therefore, its use is rather limited to the initial diagnostic phase and simpler devices are required for long-term follow-up. The validity of single-parameter wearable devices for the assessment of sleep apnea severity is still debated. In this context, a wearable electrocardiogram (ECG) acquisition system (ECG belt) was developed and its suitability for the classification of sleep apnea severity was investigated using heart rate variability analysis with or without data pre-filtering. Several classification algorithms were compared and support vector machine was preferred due to its simplicity and overall performance. Whole-night ECG signals from 241 patients with a suspicion of sleep apnea were recorded using both the ECG belt and patched ECG during PSG recordings. 65% of patients had an obstructive sleep apnea and the median AHI was 21 [IQR: 7–40] h−1. The classification accuracy obtained from the ECG belt (accuracy: 72%, sensitivity: 70%, specificity: 74%) was comparable to the patched ECG (accuracy: 74%, sensitivity: 88%, specificity: 61%). The highest classification accuracy was obtained for the discrimination between individuals with no or mild SA vs. moderate to severe SA. In conclusion, the ECG belt provided signals comparable to patched ECG and could be used for the assessment of sleep apnea severity, especially during follow-up.

A New Methodology Based on EMD and Nonlinear Measurements for Sudden Cardiac Death Detection

Heart diseases are among the most common death causes in the population. Particularly, sudden cardiac death (SCD) is the cause of 10% of the deaths around the world. For this reason, it is necessary to develop new methodologies that can predict this event in the earliest possible stage. This work presents a novel methodology to predict when a person can develop an SCD episode before it occurs. It is based on the adroit combination of the empirical mode decomposition, nonlinear measurements, such as the Higuchi fractal and permutation entropy, and a neural network. The obtained results show that the proposed methodology is capable of detecting an SCD episode 25 min before it appears with a 94% accuracy. The main benefits of the proposal are: (1) an improved detection time of 25% compared with previously published works, (2) moderate computational complexity since only two features are used, and (3) it uses the raw ECG without any preprocessing stage, unlike recent previous works.

[Design of Portable Fuzzy Diagnosis Instrument for ECG Signal Based on Internet of Things]

OBJECTIVE

A method for dynamically collecting and processing ECG signals was designed to obtain classification information of abnormal ECG signals.

METHODS

Firstly, the ECG eigenvectors were acquired by real-time acquisition of ECG signals combined with discrete wavelet transform, and then the ECG fuzzy information entropy was calculated. Finally, the Euclidean distance was used to obtain the semantic distance of ECG signals, and the classification information of abnormal signals was obtained.

RESULTS

The device could effectively identify abnormal ECG signals on an embedded platform based on the Internet of Things, and improved the diagnosis accuracy of heart diseases.

CONCLUSIONS

The fuzzy diagnosis device of ECG signal could accurately classify the abnormal signal and output an online signal classification matrix with a high confidence interval.

Applicability of a Textile ECG-Belt for Unattended Sleep Apnoea Monitoring in a Home Setting

Sleep monitoring in an unattended home setting provides important information complementing and extending the clinical polysomnography findings. The validity of a wearable textile electrocardiography (ECG)-belt has been proven in a clinical setting. For evaluation in a home setting, ECG signals and features were acquired from 12 patients (10 males and 2 females, showing an interquartile range for age of 48–59 years and for body mass indexes (BMIs) of 28.0–35.5) over 28 nights. The signal quality was assessed by artefacts detection, signal-to-noise ratio, and Poincaré plots. To assess the validity, the data were compared to previously reported data from the clinical setting. It was found that the artefact percentage was slightly reduced for the ECG-belt from 9.7% ± 14.7% in the clinical setting, to 7.5% ± 10.8% in the home setting. The signal-to-noise ratio was improved in the home setting and reached similar values to the gel electrodes in the clinical setting. Finally, it was found that for artefact percentages above 3%, Poincaré plots are instrumental to evaluate the origin of artefacts. In conclusion, the application of the ECG-belt in a home setting did not result in a reduction in signal quality compared to the ECG-belt used in the clinical setting, and thus provides new opportunities for patient pre-screening or follow-up.

ECG anomaly class identification using LSTM and error profile modeling

Automatic diagnosis of cardiac events is a current problem of interest in which deep learning has shown promising success. We have earlier reported the use of Long Short Term Memory (LSTM) networks-trained on normal ECG patterns-to the detection of anomalies from the prediction errors for real-time diagnostic applications. In this work, we extend our anomaly detection algorithm by introducing a second stage predictor that can identify the actual anomaly class from the error outputs of the first stage model. Results from seven types of anomalies have been presented including Atrial Premature Contraction (APC), Paced Beat (PB), Premature Ventricular Contraction (PVC), Right Bundle Branch Block (RBBB), Ventricular Bigeminy (VB), Ventricular Couplets (VCs) and Ventricular Tachycardia (VT). To optimize anomaly class prediction performance, multiple choices of second stage models such as multilayer perceptron (MLP), support vector machine (SVM) and logistic regression have been employed. A featurization scheme for LSTM prediction errors in the form of overall summaries has been proposed and a successful predictor for the same was developed with good performance. Our results indicate that the error vectors represented by their summary features carry useful predictive information about actual ECG anomaly type. We discuss how the accuracy scores without attention to inherent class imbalances and paucity of data instances may produce misleading performance estimates and hence accurate background models are needed to estimate true predictive performance of multi-class predictors such as those presented in this work. The training data sets and related resources for this study are provided at http://ecg.sciwhylab.org.

ECG Signal Classification Using Various Machine Learning Techniques

Electrocardiogram (ECG) signal is a process that records the heart rate by using electrodes and detects small electrical changes for each heat rate. It is used to investigate some types of abnormal heart function including arrhythmias and conduction disturbance. In this paper the proposed method is used to classify the ECG signal by using classification technique. First the Input signal is preprocessed by using filtering method such as low pass, high pass and butter worth filter to remove the high frequency noise. Butter worth filter is to remove the excess noise in the signal. After preprocessing peak points are detected by using peak detection algorithm and extract the features for the signal are extracted using statistical parameters. Finally, extracted features are classified by using SVM, Adaboost, ANN and Naïve Bayes classifier to classify the ECG signal database into normal or abnormal ECG signal. Experimental result shows that the accuracy of the SVM, Adaboost, ANN and Naïve Bayes classifier is 87.5%, 93%, 94 and 99.7%. Compared to other classifier naïve bayes classifier accuracy is high.

Separation of electrocardiographic from electromyographic signals using dynamic filtration

Trunk muscle electromyographic (EMG) signals are often contaminated by the electrical activity of the heart. During low or moderate muscle force, these electrocardiographic (ECG) signals disturb the estimation of muscle activity. Butterworth high-pass filters with cut-off frequency of up to 60 Hz are often used to suppress the ECG signal. Such filters disturb the EMG signal in both frequency and time domain. A new method based on the dynamic application of Savitzky-Golay filter is proposed. EMG signals of three left trunk muscles and pure ECG signal were recorded during different motor tasks. The efficiency of the method was tested and verified both with the experimental EMG signals and with modeled signals obtained by summing the pure ECG signal with EMG signals at different levels of signal-to-noise ratio. The results were compared with those obtained by application of high-pass, 4th order Butterworth filter with cut-off frequency of 30 Hz. The suggested method is separating the EMG signal from the ECG signal without EMG signal distortion across its entire frequency range regardless of amplitudes. Butterworth filter suppresses the signals in the 0-30 Hz range thus preventing the low-frequency analysis of the EMG signal. An additional disadvantage is that it passes high-frequency ECG signal components which is apparent at equal and higher amplitudes of the ECG signal as compared to the EMG signal. The new method was also successfully verified with abnormal ECG signals.