Automated ECG multi-class classification system based on combining deep learning features with HRV and ECG measures

Electrocardiogram (ECG) serves as the gold standard for noninvasive diagnosis of several types of heart disorders. In this study, a novel hybrid approach of deep neural network combined with linear and nonlinear features extracted from ECG and heart rate variability (HRV) is proposed for ECG multi-class classification. The proposed system enhances the ECG diagnosis performance by combining optimized deep learning features with an effective aggregation of ECG features and HRV measures using chaos theory and fragmentation analysis. The constant-Q non-stationary Gabor transform technique is employed to convert the 1-D ECG signal into 2-D image which is sent to a pre-trained convolutional neural network structure, called AlexNet. The pair-wise feature proximity algorithm is employed to select the optimal features from the AlexNet output feature vector to be concatenated with the ECG and HRV measures. The concatenated features are sent to different types of classifiers to distinguish three distinct subjects, namely congestive heart failure, arrhythmia, and normal sinus rhythm (NSR). The results reveal that the linear discriminant analysis classifier has the highest accuracy compared to the other classifiers. The proposed system is investigated with real ECG data taken from well-known databases, and the experimental results show that the proposed diagnosis system outperforms other recent state-of-the-art systems in terms of accuracy 98.75%, specificity 99.00%, sensitivity of 98.18%, and computational time 0.15 s. This demonstrates that the proposed system can be used to assist cardiologists in enhancing the accuracy of ECG diagnosis in real-time clinical setting.

A Comprehensive Review on Wearable Health Monitoring Systems

This paper presents a comprehensive review of the wearable healthcare monitoring systems proposed by the researchers to date. One of the earliest wearable recorders, named “a silicon locket for ECG monitoring”, was developed at the Indian Institute of Technology, Bombay, in 2003. Thus, the wearable health monitoring systems, started with the acquisition of a single signal/ parameter to the present generation smart and affordable multi-parameter recording/monitoring systems, have evolved manifolds in these two decades. Wearable systems have dramatically changed in terms of size, cost, functionality, and accuracy. The early-day wearable recorders were with limited functionalities against today’s systems, e.g., Apple’s iWatch which comprises abundant health monitoring features like heart rate monitoring, breathing app, accelerometers, smart walking/ activity monitoring, and alerts. Most of the present-day smartphones are not only capable of recording various health features like body temperature, heart rate, photoplethysmograph (PPG) signal, calory consumption, smart activity monitoring, stress measurement, etc. through different apps, but they also help the user to get monitored by a family physician via GSM or even internet of things (IoT). One of the latest, state-of-the-art real-time personal health monitoring systems, Wearable IoT-cloud-based health monitoring system (WISE), is a beautiful amalgamation of body area sensor network (BASN) and IoT framework for ubiquitous health monitoring. The future of wearable health monitoring systems will be far beyond the IoT and BASN.

ECG signal classification based on deep CNN and BiLSTM

Background

Currently, cardiovascular disease has become a major disease endangering human health, and the number of such patients is growing. Electrocardiogram (ECG) is an important basis for {medical doctors to diagnose the cardiovascular disease, which can truly reflect the health of the heart. In this context, the contradiction between the lack of medical resources and the surge in the number of patients has become increasingly prominent. The use of computer-aided diagnosis of cardiovascular disease has become particularly important, so the study of ECG automatic classification method has a strong practical significance.

Methods

This article proposes a new method for automatic identification and classification of ECG.We have developed a dense heart rhythm network that combines a 24-layer Deep Convolutional Neural Network (DCNN) and Bidirectional Long Short-Term Memory (BiLSTM) to deeply mine the hierarchical and time-sensitive features of ECG data. Three different sizes of convolution kernels (32, 64 and 128) are used to mine the detailed features of the ECG signal, and the original ECG is filtered using a combination of wavelet transform and median filtering to eliminate the influence of noise on the signal. A new loss function is proposed to control the fluctuation of loss during the training process, and convergence mapping of the tan function in the range of 0–1 is employed to better reflect the model training loss and correct the optimization direction in time.

Results

We applied the dataset provided by the 2017 PhysioNet/CINC challenge for verification. The experiment adopted ten-fold cross validation,and obtained an accuracy rate of 89.3\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\%$$\end{document}% and an F1 score of 0.891.

Conclusions

This article proposes its own method in the aspects of ECG data preprocessing, feature extraction and loss function design. Compared with the existing methods, this method improves the accuracy of automatic ECG classification and is helpful for clinical diagnosis and self-monitoring of atrial fibrillation.

Arrhythmia detection and classification using ECG and PPG techniques: a review

Electrocardiogram (ECG) and photoplethysmograph (PPG) are non-invasive techniques that provide electrical and hemodynamic information of the heart, respectively. This information is advantageous in the diagnosis of various cardiac abnormalities. Arrhythmia is the most common cardiovascular disease, manifested as single or multiple irregular heartbeats. However, due to the continuous manual observation, it becomes troublesome for experts sometimes to identify the paroxysmal nature of arrhythmia correctly. Moreover, due to advancements in technology, there is an inclination towards wearable sensors which monitor such patients continuously. Thus, there is a need for automatic detection techniques for the identification of arrhythmia. In the presented work, ECG and PPG-based state-of-the-art methods have been described, including preprocessing, feature extraction, and classification techniques for the detection of various arrhythmias. Additionally, this review exhibits various wearable sensors used in the literature and public databases available for the evaluation of results. The study also highlights the limitations of the current techniques and pragmatic solutions to improvise the ongoing effort.

Efficacy of Smart EEG Monitoring Amidst the COVID-19 Pandemic

Ever since the COVID-19 pandemic has majorly altered diagnosis and prognosis practices, the need for telemedicine and mobile/electronic health has never been more appreciated. Drastic complications of the pandemic such as burdens on the social and employment status resulting from extended quarantine and physical distancing, has also negatively impacted mental health. Doctors and healthcare workers have seen more than just the lungs affected by COVID-19. Neurological complications including stroke, headache, and seizures have been reported for populations of patients. Most mental conditions can be detected using the Electroencephalogram (EEG) signal. Brain disorders, neurodegenerative diseases, seizure/epilepsy, sleep/fatigue, stress, and depression have certain characteristics in the EEG wave, which clearly differentiate them from normal conditions. Smartphone apps analyzing the EEG signal have been introduced in the market. However, the efficacy of such apps has not been thoroughly investigated. Factors and their inter-relationships impacting efficacy can be studied through a causal model. This short communications/perspective paper outlines the initial premises of a system dynamics approach to assess the efficacy of smart EEG monitoring apps amid the pandemic, that could be revolutionary for patient well-being and care policies.

Multiclass ECG Signal Analysis Using Global Average-Based 2-D Convolutional Neural Network Modeling

Cardiovascular diseases have been reported to be the leading cause of mortality across the globe. Among such diseases, Myocardial Infarction (MI), also known as “heart attack”, is of main interest among researchers, as its early diagnosis can prevent life threatening cardiac conditions and potentially save human lives. Analyzing the Electrocardiogram (ECG) can provide valuable diagnostic information to detect different types of cardiac arrhythmia. Real-time ECG monitoring systems with advanced machine learning methods provide information about the health status in real-time and have improved user’s experience. However, advanced machine learning methods have put a burden on portable and wearable devices due to their high computing requirements. We present an improved, less complex Convolutional Neural Network (CNN)-based classifier model that identifies multiple arrhythmia types using the two-dimensional image of the ECG wave in real-time. The proposed model is presented as a three-layer ECG signal analysis model that can potentially be adopted in real-time portable and wearable monitoring devices. We have designed, implemented, and simulated the proposed CNN network using Matlab. We also present the hardware implementation of the proposed method to validate its adaptability in real-time wearable systems. The European ST-T database recorded with single lead L3 is used to validate the CNN classifier and achieved an accuracy of 99.23%, outperforming most existing solutions.

Sustainable Smartphone-Based Healthcare Systems: A Systems Engineering Approach to Assess the Efficacy of Respiratory Monitoring Apps

Recent technological developments along with advances in smart healthcare have been rapidly changing the healthcare industry and improving outcomes for patients. To ensure reliable smartphone-based healthcare interfaces with high levels of efficacy, a system dynamics model with sustainability indicators is proposed. The focus of this paper is smartphone-based breathing monitoring systems that could possibly use breathing sounds as the data acquisition input. This can especially be useful for the self-testing procedure of the ongoing global COVID-19 crisis in which the lungs are attacked and breathing is affected. The method of investigation is based on a systems engineering approach using system dynamics modeling. In this paper, first, a causal model for a smartphone-based respiratory function monitoring is introduced. Then, a systems thinking approach is applied to propose a system dynamics model of the smartphone-based respiratory function monitoring system. The system dynamics model investigates the level of efficacy and sustainability of the system by studying the behavior of various factors of the system including patient wellbeing and care, cost, convenience, user friendliness, in addition to other embedded software and hardware breathing monitoring system design and performance metrics (e.g., accuracy, real-time response, etc.). The sustainability level is also studied through introducing various indicators that directly relate to the three pillars of sustainability. Various scenarios have been applied and tested on the proposed model. The results depict the dynamics of the model for the efficacy and sustainability of smartphone-based breathing monitoring systems. The proposed ideas provide a clear insight to envision sustainable and effective smartphone-based healthcare monitoring systems.

Optimal Multi-Stage Arrhythmia Classification Approach

Arrhythmia constitutes a problem with the rate or rhythm of the heartbeat, and an early diagnosis is essential for the timely inception of successful treatment. We have jointly optimized the entire multi-stage arrhythmia classification scheme based on 12-lead surface ECGs that attains the accuracy performance level of professional cardiologists. The new approach is comprised of a three-step noise reduction stage, a novel feature extraction method and an optimal classification model with finely tuned hyperparameters. We carried out an exhaustive study comparing thousands of competing classification algorithms that were trained on our proprietary, large and expertly labeled dataset consisting of 12-lead ECGs from 40,258 patients with four arrhythmia classes: atrial fibrillation, general supraventricular tachycardia, sinus bradycardia and sinus rhythm including sinus irregularity rhythm. Our results show that the optimal approach consisted of Low Band Pass filter, Robust LOESS, Non Local Means smoothing, a proprietary feature extraction method based on percentiles of the empirical distribution of ratios of interval lengths and magnitudes of peaks and valleys, and Extreme Gradient Boosting Tree classifier, achieved an F1-Score of 0.988 on patients without additional cardiac conditions. The same noise reduction and feature extraction methods combined with Gradient Boosting Tree classifier achieved an F1-Score of 0.97 on patients with additional cardiac conditions. Our method achieved the highest classification accuracy (average 10-fold cross-validation F1-Score of 0.992) using an external validation data, MIT-BIH arrhythmia database. The proposed optimal multi-stage arrhythmia classification approach can dramatically benefit automatic ECG data analysis by providing cardiologist level accuracy and robust compatibility with various ECG data sources.

Feature extraction of ECG signal

This paper deals with new approaches to analyse electrocardiogram (ECG) signals for extracting useful diagnostic features. Initially, elimination of different types of noise is carried out using maximal overlap discrete wavelet transform (MODWT) and universal thresholding. Next, R-peak fiducial points are detected from these noise free ECG signals using discrete wavelet transform along with thresholding. Then, extraction of other features, viz., Q waves, S waves, P waves, T waves, P wave onset and offset points, T wave onset and offset points, QRS onset and offset points are identified using some rule based algorithms. Eventually, other important features are computed using the above extracted features. The software developed for this purpose has been validated by extensive testing of ECG signals acquired from the MIT-BIH database. The resulting signals and tabular results illustrate the performance of the proposed method. The sensitivity, predictivity and error of beat detection are 99.98%, 99.97% and 0.05%, respectively. The performance of the proposed beat detection method is compared to other existing techniques, which shows that the proposed method is superior to other methods.

Heart rate monitoring and therapeutic devices: A wavelet transform based approach for the modeling and classification of congestive heart failure

Heart rate monitoring and therapeutic devices include real-time sensing capabilities reflecting the state of the heart. Current circuitry can be interpreted as a cardiac electrical signal compression algorithm representing the time signal information into a single event description of the cardiac activity. It is observed that some detection techniques developed for ECG signal detection like artificial neural network, genetic algorithm, Hilbert transform, hidden Markov model are some sophisticated algorithms which provide suitable results but their implementation on a silicon chip is very complicated. Due to less complexity and high performance, wavelet transform based approaches are widely used. In this paper, after a thorough analysis of various wavelet transforms, it is found that Biorthogonal wavelet transform is best suited to detect ECG signal's QRS complex. The main steps involved in ECG detection process consist of de-noising and locating different ECG peaks using adaptive slope prediction thresholding. Furthermore, the significant challenges involved in the wireless transmission of ECG data are data conversion and power consumption. As medical regulatory boards demand a lossless compression technique, lossless compression technique with a high bit compression ratio is highly required. Furthermore, in this work, LZMA based ECG data compression technique is proposed. The proposed methodology achieves the highest signal to noise ratio, and lowest root mean square error. Also, the proposed ECG detection technique is capable of distinguishing accurately between healthy, myocardial infarction, congestive heart failure and coronary artery disease patients with a detection accuracy, sensitivity, specificity, and error of 99.92%, 99.94%, 99.92% and 0.0013, respectively. The use of LZMA data compression of ECG data achieves a high compression ratio of 18.84. The advantages and effectiveness of the proposed algorithm are verified by comparing with the existing methods.

From Pacemaker to Wearable: Techniques for ECG Detection Systems

With the alarming rise in the deaths due to cardiovascular diseases (CVD), present medical research scenario places notable importance on techniques and methods to detect CVDs. As adduced by world health organization, technological proceeds in the field of cardiac function assessment have become the nucleus and heart of all leading research studies in CVDs in which electrocardiogram (ECG) analysis is the most functional and convenient tool used to test the range of heart-related irregularities. Most of the approaches present in the literature of ECG signal analysis consider noise removal, rhythm-based analysis, and heartbeat detection to improve the performance of a cardiac pacemaker. Advancements achieved in the field of ECG segments detection and beat classification have a limited evaluation and still require clinical approvals. In this paper, approaches on techniques to implement on-chip ECG detector for a cardiac pacemaker system are discussed. Moreover, different challenges regarding the ECG signal morphology analysis deriving from medical literature is extensively reviewed. It is found that robustness to noise, wavelet parameter choice, numerical efficiency, and detection performance are essential performance indicators required by a state-of-the-art ECG detector. Furthermore, many algorithms described in the existing literature are not verified using ECG data from the standard databases. Some ECG detection algorithms show very high detection performance with the total number of detected QRS complexes. However, the high detection performance of the algorithm is verified using only a few datasets. Finally, gaps in current advancements and testing are identified, and the primary challenge remains to be implementing bullseye test for morphology analysis evaluation.

Identification of Location Specific Feature Points in a Cardiac Cycle Using a Novel Seismocardiogram Spectrum System

Seismocardiogram (SCG) or mechanocardiography is a noninvasive cardiac diagnostic method; however, previous studies used only a single sensor to detect cardiac mechanical activities that will not be able to identify location-specific feature points in a cardiac cycle corresponding to the four valvular auscultation locations. In this study, a multichannel SCG spectrum measurement system was proposed and examined for cardiac activity monitoring to overcome problems like, position dependency, time delay, and signal attenuation, occurring in traditional single-channel SCG systems. ECG and multichannel SCG signals were simultaneously recorded in 25 healthy subjects. Cardiac echocardiography was conducted at the same time. SCG traces were analyzed and compared with echocardiographic images for feature point identification. Fifteen feature points were identified in the corresponding SCG traces. Among them, six feature points, including left ventricular lateral wall contraction peak velocity, septal wall contraction peak velocity, transaortic peak flow, transpulmonary peak flow, transmitral ventricular relaxation flow, and transmitral atrial contraction flow were identified. These new feature points were not observed in previous studies because the single-channel SCG could not detect the location-specific signals from other locations due to time delay and signal attenuation. As the results, the multichannel SCG spectrum measurement system can record the corresponding cardiac mechanical activities with location-specific SCG signals and six new feature points were identified with the system. This new modality may help clinical diagnoses of valvular heart diseases and heart failure in the future.

Robust off-line heartbeat detection using ECG and pressure-signals

Artefacts in pressure- and ECG-signals generally arise due to different causes. Therefore, the combined analysis of both signals can increase the effectiveness of heartbeat detection compared to analysis using solely ECG-signals. In this paper, we present an algorithm for heartbeat annotation by combining the analysis of both the pressure- and ECG-signals. The novelties of our algorithm are as follows: (1) development of a new approach for annotating heartbeats using pressure-signals, (2) development of a mechanism that identifies and corrects paced rhythms, and (3) development of a noise detection approach. Our algorithm is tested on the datasets from the extended phase of the Physionet CINC-2014 challenge and produces an overall score of 87.31%. Finally, we put forth several recommendations that could further improve our algorithm.

HeartSearcher: finds patients with similar arrhythmias based on heartbeat classification

Long-term electrocardiogram data can be acquired by linking a Holter monitor to a mobile phone. However, most systems of this variety are simply designed to detect arrhythmia through heartbeat classification, and do not provide any additional support for clinical decisions. HeartSearcher identifies patients with similar arrhythmias from heartbeat classifications, by summarising each patient's typical heartbeat pattern in the form of a regular expression, and then ranking patients according to the similarities of their patterns. Results obtained using electrocardiogram data from the MIT-BIH arrhythmia database show that this abstraction reduces the volume of heartbeat classifications by 98% on average, offering great potential to support clinical decisions.

The effect of multiscale PCA de-noising in epileptic seizure detection

In this paper we describe the effect of Multiscale Principal Component Analysis (MSPCA) de-noising method in terms of epileptic seizure detection. In addition, we developed a patient-independent seizure detection algorithm using Freiburg EEG database. Each patient contains datasets called "ictal" and "interictal". Window length of 16 s was applied to extract EEG segments from datasets of each patient. Furthermore, Power Spectral Density (PSD) of each EEG segment was estimated using different spectral analysis methods. Afterwards, these values were fed as input to different machine learning methods that were responsible for seizure detection. We also applied MSPCA de-noising method to EEG segments prior to PSD estimation to determine if MSPCA can further enhance the classifiers' performance. The MSPCA drastically improved both the sensitivity and the specificity, increasing the overall accuracy of all three classifiers up to 20%. The best overall detection accuracy (99.59%) was achieved when Eigenvector analysis was used for frequency estimation, and C4.5 as a classifier. The experiment results show that MSPCA is an effective de-noising method for improving the classification performance in epileptic seizure detection.

Data structure-guided development of electrocardiographic signal characterization and classification

OBJECTIVE

The study introduces and elaborates on a certain perspective of biomedical data analysis where data structure is revealed through fuzzy clustering. The key objective of the study is to develop a characterization of the content of the clusters by offering a number of their descriptors established on the basis of membership grades of patterns included there, as well as on the basis of their class membership. Next, a design of a cluster-based classifier is presented in which the structure of the classifier is based on a collection of clusters. The structure also exploits the descriptors of the clusters as well as aggregates their characteristics with the activation levels of the associated clusters formed in the feature space in which QRS complexes are represented.

METHODS AND MATERIALS

The underlying methods involve the use of fuzzy clustering and two essential ways of representing QRS complexes with the use of the Hermite expansion of signals and piecewise aggregate approximation (PAA). The material involves QRS segments coming from the MIT-BIH Arrhythmia Database.

RESULTS

The key results demonstrate and quantify the effectiveness of QRS characterization with the use of clustering realized in the space of coefficients of the Hermite series expansion and the PAA expansion. In general, accuracy of the discussed classification schemes increases with the increase of the number of clusters; the difference varies in the range of 30% (when moving from 10 to 60 clusters). The fuzzification coefficient of the fuzzy C-Means clustering algorithm has a visible impact on the quality of the results in the range of up 40% difference in the classification of accuracy (when the coefficient varies in-between 1.1 and 2.5). The PAA representation space leads to slightly better results than those obtained when using the Hermite representation of the signals, the difference is of around 5%.

CONCLUSIONS

It was shown that granular representation of electrocardiographic signals is essential to data analysis and classification by providing a means to reveal and characterize the data structure and by providing prerequisites to construct pattern classifiers. The study also shows that fuzzy clusters deliver important structural information about the data that could be further quantified by looking into the content of clusters.

RPCA-based detection and quantification of motion artifacts in ECG signals

In this paper, a recursive principal component analysis (RPCA)-based algorithm is applied for detecting and quantifying the motion artifact episodes encountered in an ECG signal. The motion artifact signal is synthesized by low-pass filtering a random noise signal with different spectral ranges of LPF (low pass filter): 0-5 Hz, 0-10 Hz, 0-15 Hz and 0-20 Hz. Further, the analysis of the algorithm is carried out for different values of SNR levels and forgetting factors (α) of an RPCA algorithm. The algorithm derives an error signal, wherever a motion artifact episode (noise) is present in the entire ECG signal with 100% accuracy. The RPCA error magnitude is almost zero for the clean signal portion and considerably high wherever the motion artifacts (noisy episodes) are encountered in the ECG signals. Further, the general trend of the algorithm is to produce a smaller magnitude of error for higher SNR (i.e. low level of noise) and vice versa. The quantification of the RPCA algorithm has been made by applying it over 25 ECG data-sets of different morphologies and genres with three different values of SNRs for each forgetting factor and for each of four spectral ranges.

NON-INVASIVE ESTIMATION OF DIABETES RELATED FEATURES FROM ECG USING GRAPHICAL PROGRAMAMING LANGUAGE AND MATLAB

Electrocardiography deals with the electrical activity of the heart. The condition of cardiac health is given by the electrocardiogram (ECG). ECG analysis is one of the most important aspects of research in the field of biomedical sciences and healthcare. The precision in the identification of various parameters in the ECG is of great importance for the reliability of an automated ECG analyzing system and diagnosis of cardiac diseases. Many algorithms have been developed in the last few years, each with their own advantages and limitations. In this work, we have developed an algorithm for 12-lead ECG parameter detection which works in three steps. Initially, the signal is denoised by the wavelet transform approach using a graphical programming language called LabVIEW (Laboratory Virtual Instrument Engineering Workbench). Next, primary features are detected from the denoised ECG signal using Matlab, and lastly, the secondary features related to diabetes are estimated from the detected primary features. Diabetes mellitus (DM), which is characterized by raised blood glucose levels in an individual, affects an estimated 2–4% of the world's population, making it one of the major chronic illnesses prevailing today. Recently, there has been increasing interest in the study of relationship between diabetes and cardiac health. Thus, in this work, we estimate diabetic-related secondary ECG features like corrected QT interval (QTc), QT dispersion (QTd), P wave dispersion (PD), and ST depression (STd). Our software performance is evaluated using CSE DS-3 multi-lead data base and the data acquired at SGGS IE & T, Nanded, MS, which contains 5000 samples recorded at a sampling frequency of 500 HZ. The proposed algorithm gives a sensitivity of 99.75% and a specificity of 99.83%.