Abnormal Heartbeats Research Articles

Predicting the Risk of Depression Based on ECG Using RNN.

This paper presents a model to predict the risk of depression based on electrocardiogram (ECG). This proposed model uses a Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) autoencoder to predict normal, abnormal, and PVC heartbeats. The RNN model is a deep learning-based model to classify normal, abnormal, and PVC heartbeats. We used the model as a classifier. The model uses a heart rates dataset to predict abnormal and PVC heartbeats. As for the dataset, we have used 5000 ECG samples. The model was trained on a training dataset and validation dataset. After that, it was tested on a test dataset. The model is trained on normal heartbeat rates, so the model can predict any heartbeat rates other than normal. Our contribution here is to build a model that can differentiate between “normal,” “abnormal,” and “risky” heartbeats. Our model predicts “normal” heartbeats with 97.24% accuracy and can predict “PVC” heartbeats with 100% accuracy. Other than the accuracy, we evaluated our model on the training loss graphs. These two types of training loss graphs were evaluated as “normal” versus “risky” and “abnormal” versus “risky.” We have seen great results there as well. The best losses for “normal,” “abnormal,” and “risky” are 5.71, 33.36, and 34.78. However, these results may improve if a larger dataset is used. In studies, it was found that patients suffering from depression may have a different kind of heartbeat than the normal ones. In most cases, it is PVC (Premature Ventricular Contraction) heartbeats. Therefore, the target is to predict abnormal heartbeats and PVC heartbeats.

A Computational Architecture for Inference of a Quantized-CNN for Detecting Atrial Fibrillation

Atrial Fibrillation is a common cardiac arrhythmia, which is characterized by an abnormal heartbeat rhythm that can be life-threatening. Recently, researchers have proposed several Convolutional Neural Networks (CNNs) to detect Atrial Fibrillation. CNNs have high requirements on computing and memory resources, which usually demand the use of High Performance Computing (eg, GPUs). This high energy demand is a challenge for portable devices. Therefore, efficient hardware implementations are required. We propose a computational architecture for the inference of a Quantized Convolutional Neural Network (Q-CNN) that allows the detection of the Atrial Fibrillation (AF). The architecture exploits data-level parallelism by incorporating SIMD-based vector units, which is optimized in terms of computation and storage and also optimized to perform both the convolutional and fully connected layers. The computational architecture was implemented and tested in a Xilinx Artix-7 FPGA. We present the experimental results regarding the quantization process in a different number of bits, hardware resources, and precision. The results show an accuracy of 94% accuracy for 22-bits. This work aims to be the basis for the future implementation of a portable, low-cost, and high-reliability device for the diagnosis of Atrial Fibrillation.

Risk Factors For Respiratory Disorders Among West African Workers In The E-Waste Sector

Introduction : In sub-Saharan Africa, the management of e-waste is increasingly involving workers who may not always be aware of the health risks related. The objective of this study is to determine the prevalence of respiratory diseases and their risk factors among workers in this informal sector in the West African region. Methods : A cross-sectional descriptive and analytical survey was conducted in the economic capitals of Benin, Burkina Faso, Ivory Coast and Mali on e-waste collection, treatment and recycling sites from November 13 to December 9, 2019. A total of 638 reclaimers, repairers and recyclers were selected by stratified sampling taking into account their representativeness by country. The risk factors for respiratory disorders were identified by mixed-effects logistic regression with a random effect on the country variable. Results : Among e-workers, the prevalence of respiratory disorders expressed is 47.9%. Their predictive factors were non-participation in e-waste sorting (p<0.001), participation in smelting lead batteries (p=0.001), previous exposure to mining (p<0.001), cooking in the living room (p<0.001), living in an open space (p=0),003) or in the family home (p=0.004), history of respiratory problems (p<0.001), feeling abnormal heartbeats in the last two weeks (p=0.016), occurrence of fever in the last two weeks (p<0.001) and not washing hands with soap (p<0.001). Conclusion : Awareness-raising interventions should be developed for this category of workers to reduce practices that pose a risk to their respiratory health and the adoption of protective measures. Key words: risk factor, respiratory disorder, informal sector, e-waste, West Africa.

Ensemble of kernel extreme learning machine based random forest classifiers for automatic heartbeat classification

Automatic heartbeat classification technology based on the ECG plays an important role in assisting doctors with arrhythmia diagnosis. While many heartbeat classification studies can achieve good performance under the intra-patient paradigm, they still cannot offer acceptable classification results under the inter-patient paradigm. Additionally, the available ECG datasets are highly class imbalanced since normal heartbeats appear much more frequently than abnormal heartbeats, resulting in most methods having low sensitives and positive predictive values on minority class ectopic heartbeats. To solve the above problems, this study proposes an automatic ECG heartbeat classification method based on ensemble learning and multi-kernel learning. First, we use a linear combination of the radial basis function kernel and the polynomial kernel to produce a mixed-kernel-based extreme learning machine (MKELM). Then, a MKELM-based random forest binary classifier (MKELM-RF) is constructed. Finally, an ensemble multiclass classifier MKELM-RF-OVO is proposed based on one-vs.-one (OVO) reduction and MKELM-RF. We evaluated the proposed method on the public MIT-BIH-AR benchmarks database, under the inter-patient paradigm, classifying four types of heartbeats, namely, normal beats (N), supraventricular ectopic beats (S), ventricular ectopic beats (V) and the fusion of ventricular and normal (F). The obtained overall accuracy and the average positive predictive value are 98.1% and 93.9%, respectively, which are higher than the current studies by approximately 4% and 6%, respectively. The sensitivities for classes S and V are 1 and 94.4%, respectively, which outperforms most methods. The evaluation results show that our proposed method achieves a superior classification performance compared to the state-of-the-art methods.

Intelligent Medical Companion using Internet of Things

Improvement in quality of health and medicine has become of paramount importance. The solution to this problem requires a wearable device for continuous monitoring for the patient. As a result, Medical companion was the best choice for the patient who suffers Arrhythmia due to its low-cost and efficacy to save the life of the patient. Moreover, this system is able to deliver reliable heartbeat and body temperature data to a user in a real-time, with a smart mobile application. This system mainly consists of MAX30100 and LM35 that detect heart rate and temperature of the human respectively. The output of these sensors is given to the esp32 section, which runs an Arrhythmia algorithm, which is already programmed, into it. If an abnormal heartbeat is detected, then it activates the alert in the mobile application. This mobile application will automatically send an alert message for the emergency centre and the patient's caregiver; thereby the life of the person can be saved.

A Robust Multilevel DWT Densely Network for Cardiovascular Disease Classification.

Cardiovascular disease is the leading cause of death worldwide. Immediate and accurate diagnoses of cardiovascular disease are essential for saving lives. Although most of the previously reported works have tried to classify heartbeats accurately based on the intra-patient paradigm, they suffer from category imbalance issues since abnormal heartbeats appear much less regularly than normal heartbeats. Furthermore, most existing methods rely on data preprocessing steps, such as noise removal and R-peak location. In this study, we present a robust classification system using a multilevel discrete wavelet transform densely network (MDD-Net) for the accurate detection of normal, coronary artery disease (CAD), myocardial infarction (MI) and congestive heart failure (CHF). First, the raw ECG signals from different databases are divided into same-size segments using an original adaptive sample frequency segmentation algorithm (ASFS). Then, the fusion features are extracted from the MDD-Net to achieve great classification performance. We evaluated the proposed method considering the intra-patient and inter-patient paradigms. The average accuracy, positive predictive value, sensitivity and specificity were 99.74%, 99.09%, 98.67% and 99.83%, respectively, under the intra-patient paradigm, and 96.92%, 92.17%, 89.18% and 97.77%, respectively, under the inter-patient paradigm. Moreover, the experimental results demonstrate that our model is robust to noise and class imbalance issues.

Neural Respiratory Drive Estimation in Respiratory sEMG with Cardiac Arrhythmias.

Neural respiratory drive as measured by the electromyography allows the study of the imbalance between the load on respiratory muscles and its capacity. Surface respiratory electromyography (sEMG) is a non-invasive tool used for indirectly assessment of NRD. It also provides a way to evaluate the level and pattern of respiratory muscle activation. The prevalence of electrocardiographic activity (ECG) in respiratory sEMG signals hinders its proper evaluation. Moreover, the occurrence of abnormal heartbeats or cardiac arrhythmias in respiratory sEMG measures can make even more challenging the NRD estimation. Respiratory sEMG can be evaluated using the fixed sample entropy (fSampEn), a technique which is less affected by cardiac artefacts. The aim of this work was to investigate the performance of the fSampEn, the root mean square (RMS) and the average rectified value (ARV) on respiratory sEMG signals with supraventricular arrhythmias (SVA) for NRD estimation. fSampEn, ARV and RMS parameters increased as the inspiratory load increased during the test. fSampEn was less influenced by ECG with SVAs for the NRD estimation showing a greater response to respiratory sEMG, reflected with a higher percentage increase with increasing load (228 % total increase, compared to 142 % and 135 % for ARV and RMS, respectively).

Evaluating Interoceptive Crossover between emotional and physical symptoms

ABSTRACT Symptom perception is complex and influenced by a number of psychological factors, including interoceptive ability and alexithymia. Some individuals may have difficulty distinguishing between internal signals, such as emotions and physical symptoms, however research in this area is sparse. The current study aimed to explore the incidence and nature of this phenomenon, labelled, 'Interoceptive Crossover'. 239 individuals completed an online survey and rated the perceived similarity between a range of emotions (e.g., Sad, Happy, Afraid and Calm) and physical symptoms (e.g., Stomach Pain, Fatigue/Tiredness, Headache and Abnormal Heartbeat) to assess the incidence and nature of Interoceptive Crossover. Individuals demonstrated crossover between emotions and physical symptoms. Some crossovers were more unsurprising and reported by a greater proportion of the sample, such as Afraid and Abnormal Heartbeat (74.5%); Sad and Fatigue (29.4%) and Afraid and Shortness of Breath (58.5%). Other crossovers were less prevalent in the sample and more unexpected such as Satisfied with Headache (1.2%); Bored with Back Pain (5.95%) and Happy and Back Pain (0.4%). Overall, individuals demonstrate Interoceptive Crossover of emotions and physical symptoms and some crossovers are more prevalent whilst others are rare and unexpected. This phenomenon needs further study with respect to relevant constructs including alexithymia and interoception.

Insula shows abnormal task-evoked and resting-state activity in first-episode drug-naïve generalized anxiety disorder.

Interoception is associated with neural activity in the insula of healthy humans. On the basis of the somatic symptoms in generalized anxiety disorder (GAD), especially abnormal heartbeat perception, we hypothesized that abnormal activity in the insula was associated with interoceptive awareness in patients with GAD. We investigated the psychological correlates of interoceptive awareness in a sample of 34 patients with first-onset, drug-naïve GAD and 30 healthy controls (HCs). Furthermore, we compared blood oxygenation level-dependent responses between the two groups during a heartbeat perception task to assess task-evoked activity and its relationship with psychological measures. We also examined between-group differences in insular subregions resting-state functional connectivity (rsFC), and its relationship with anxiety severity. Patients with GAD had significantly higher body perception scores than HCs. They also exhibited greater task-evoked activity in the left anterior insula, left posterior insula, and right anterior insula during interoceptive awareness than HCs. Left anterior insula activity was positively correlated with body awareness in patients with GAD, and rsFC between the left anterior insula and left medial prefrontal gyrus was negatively correlated with somatic anxiety severity. Investigating a sample of first-episode, drug-naïve patients, our study demonstrated abnormal interoceptive awareness in patients with GAD and that this was related to abnormal anterior insular activity during both rest and task. These results shed new light on the psychological and neural substrates of somatic symptoms in GAD, and they may serve to establish abnormal interoceptive awareness as a neural and psychological marker of GAD.

Very‐large‐scale integration implementation of a convolutional neural network accelerator for abnormal heartbeat detection

In this study, a very-large-scale integration implementation of a convolutional neural network (CNN) inference for abnormal heartbeat detection was proposed. Four-lead electrocardiogram signals were used to detect abnormal heartbeat conditions, such as premature ventricular complex. 1D CNNs and fully connected layers were utilised in the proposed chip to achieve high-speed, small-area, and high-accuracy arrhythmia detection. The proposed chip was implemented using a 90-nm complementary metal-oxide-semiconductor process and operated at 125 MHz with a core area. The power consumption was at high-speed operation frequency (125 MHz) and at for low-power applications. The detection accuracy was based on the MIT-BIH arrhythmia database. Consequently, the properties of high speed, low power, small area, and high accuracy were established in the proposed accelerator chip.

Multi-Class ECG Beat Classification Based on a Gaussian Mixture Model of Karhunen-Loève Transform

Cardiovascular diseases are one of the main causes of death around the world. Automatic classification of electrocardiogram (ECG) signals is of paramount importance in the unmanned detection of a wide range of heartbeat abnormalities. In this paper an effective multi-class beat classifier, based on a statistical identification of a minimum-complexity model, is presented. This methodology extracts from the ECG signal the multivariate relationships of its natural modes, by means of the separation property of the Karhunen-Loeve transform (KLT). Then, it exploits an optimized expectation maximization (EM) algorithm to find the optimal parameters of a Gaussian mixture model, with the focus being in reducing the number of parameters. The resulting statistical model is thus based on the estimation of the multivariate probability density function (PDF) that characterizes each beat type. Based on the above statistical characterization a multi-class ECG classification was performed. The experiments, conducted on the ECG signals from the MIT-BIH arrhythmia database, demonstrated the validity and, considering the reduced model size, the excellent performance of this technique to classify the ECG signals into different disease categories.

A high-precision arrhythmia classification method based on dual fully connected neural network

As an important arrhythmia detection method, the electrocardiogram (ECG) can directly reflect abnormalities in cardiac physiological activity. In view of the difficulty in the diagnosis of arrhythmia in different people, automatic arrhythmia detection methods have been studied in previous works. In this paper, we present a dual fully-connected neural network model for accurate classification of heartbeats. Our method is following the AAMI inter-patient standard, which includes normal beats (N), supraventricular ectopic beats (S), ventricular ectopic beats (V), fusion beats (F), and unknown beats (Q). Firstly, a total of 105 features are extracted from the preprocessed signals. Then, a two-layer classifier is introduced in the classification stage. Each layer contains two independent fully-connected neural networks, and the threshold criterion is also added in the second layer. For verification, both the MIT arrhythmia database (MITDB) and the MIT supraventricular arrhythmia database (SVDB) were adopted. The experiments demonstrate that the proposed method has high performance for arrhythmia detection. It also achieves high sensitivity for class S and V, which can easily detect potentially abnormal heartbeats. Furthermore, the proposed method can interfere with the classification effect for a certain disease and have more advantages in dataset size when comparing a convolutional neural network (CNN). Once properly trained, the proposed method can be employed as a tool to automatically detect arrhythmia from ECG.

Deep Learning-Based Stacked Denoising and Autoencoder for ECG Heartbeat Classification

The electrocardiogram (ECG) is a widely used, noninvasive test for analyzing arrhythmia. However, the ECG signal is prone to contamination by different kinds of noise. Such noise may cause deformation on the ECG heartbeat waveform, leading to cardiologists’ mislabeling or misinterpreting heartbeats due to varying types of artifacts and interference. To address this problem, some previous studies propose a computerized technique based on machine learning (ML) to distinguish between normal and abnormal heartbeats. Unfortunately, ML works on a handcrafted, feature-based approach and lacks feature representation. To overcome such drawbacks, deep learning (DL) is proposed in the pre-training and fine-tuning phases to produce an automated feature representation for multi-class classification of arrhythmia conditions. In the pre-training phase, stacked denoising autoencoders (DAEs) and autoencoders (AEs) are used for feature learning; in the fine-tuning phase, deep neural networks (DNNs) are implemented as a classifier. To the best of our knowledge, this research is the first to implement stacked autoencoders by using DAEs and AEs for feature learning in DL. Physionet’s well-known MIT-BIH Arrhythmia Database, as well as the MIT-BIH Noise Stress Test Database (NSTDB). Only four records are used from the NSTDB dataset: 118 24 dB, 118 −6 dB, 119 24 dB, and 119 −6 dB, with two levels of signal-to-noise ratio (SNRs) at 24 dB and −6 dB. In the validation process, six models are compared to select the best DL model. For all fine-tuned hyperparameters, the best model of ECG heartbeat classification achieves an accuracy, sensitivity, specificity, precision, and F1-score of 99.34%, 93.83%, 99.57%, 89.81%, and 91.44%, respectively. As the results demonstrate, the proposed DL model can extract high-level features not only from the training data but also from unseen data. Such a model has good application prospects in clinical practice.

ECG Heartbeat Arrhythmia Classification Using Time-Series Augmented Signals and Deep Learning Approach

Abstract Electrocardiogram (ECG) signals are the best way to monitor the functionality and health of the cardiovascular system and also identify ailments related to it. Abnormal heartbeats are reflected in the ECG pattern and such abnormal signals are called as Arrhythmias. Automated classification and identification of the ECG arrhythmia signal that provides faster and more accurate result is increasingly becoming the need of the moment. Various machine learning skills have been applied to advance the accuracy of results and increase the speed and robustness of the models. A lot of focus has been given to the architectures and datasets employed but preprocessing of the data being equally important. In this paper, a preprocessing technique that significantly improves the accuracy of the deep learning models used for ECG classification is proposed with a modified deep learning architecture that adds to the training stability. With this preprocessing technique and deep learning model, the system is able to attain accuracy levels of more than 99% without overfitting the model.

Electrolyte disturbances in children receiving omeprazole for gastroesophageal reflux disease.

Background:Gastroesophageal reflux disease (GERD) is one of the common gastrointestinal diseases with various side effects. Proton pump inhibitor (PPI) drugs are widely used for their treatment and long-term ingestion, which results in an electrolyte imbalance. This study investigates the changes in serum magnesium, calcium, sodium, and potassium after long-term use of omeprazole in children.Materials and Methods:This cross-sectional study was conducted in 2016–2017 on 97 children and adolescents, aged 1–15 years, with GERD, in Isfahan, Iran. Enrolled were patients visiting a referral pediatric gastroenterology clinic (Imam Hossein and Amin Hospitals) examined by an academic pediatric gastroenterologist. Before and 4 weeks after omeprazole administration, clinical manifestations including lethargy, muscle spasm, dyspnea, nausea, vomiting, abnormal heartbeat and deep tendon reflexes, and Chvostek and Trousseau signs were recorded in a data-gathering form. In addition, fasting serum magnesium, calcium, sodium, and potassium were measured.Results:The McNemar test results showed that omeprazole can reduce sodium, calcium, and magnesium levels statistically significantly (P < 0.05), but potassium levels do not have a meaningful reduction (P > 0.05).Conclusion:Consumption of omeprazole might cause asymptomatic hypomagnesemia, hypocalcemia, and hypernatremia in children. Such side effects should be considered in the follow-up of children under treatment with this medication.

Untact Abnormal Heartbeat Wave Detection Using Non-Contact Sensor through Transfer Learning

This paper presents an important advancement in heart activity monitoring, focusing on non-contact sensor data, which tend to be noisy due to interference, and the limitations of non-contact (untact) technology. A preprocessing filter and optimal classification model are proposed to improve the accuracy and reliability of heart rate data measured by a non-contact Doppler radar sensor, and the results are compared to those of a contact heart rate sensor (Holter monitor). The MIT-BIH Arrhythmia Database of PhysioNet are used for learning, and the results from the non-contact sensor and Holter monitor are compared for verification. To train the abnormal heartbeat waveform classification model, (1) an optimal heart rate data separation window size is selected through iterative model comparison and used for data separation, and (2) meaningful indicators of heart rate variability are selected; the data are transformed and applied as model characteristics. The non-contact sensor data are then applied to three filter algorithms, and the accuracy is assessed by comparison with the contact sensor data using the trained abnormal heartbeat waveform classification model. Learning is performed using 12 classification models, and the accuracies of the models are compared. This study demonstrates an effective new method of transfer learning for contact data abnormality detection.

Frequency Responses of Conventional and Amplified Stethoscopes for Measuring Heart Sounds.

Background:Frequencies of normal and abnormal heart sounds have previously been reported, but the acoustic analyses of the frequency responses of conventional and amplified stethoscopes for different heart sounds have not yet been reported.Objectives:To compare the acoustic analysis of frequency responses of three stethoscopes (conventional and amplified) for measuring simulated heart sounds.Materials and Methods:This exploratory study used Starkey SLI-ST3, Cardionics E-Scope II (both electronic) and Littmann Classic S.E. II (conventional) stethoscopes, as they share the same basic design with twin ear tubes coupled to ear tips and chest piece options (bell vs. diaphragm modes). Acoustic analyses using the diaphragm were performed in a soundproof booth and frequency response curves at 85 (the largest), 250, 400, 550 and 1050 Hz were compared for three different digitized heart sound simulations: normal, aortic valvular stenosis (AVS) and pulmonic valvular stenosis.Results:Amplified stethoscopes provided the most amplification of normal and abnormal heart sounds across all five frequencies compared with the conventional stethoscope. The Starkey SLI-ST3 stethoscope was better at amplifying normal heartbeats than the Cardionics E-Scope II and Littman Classic S.E. II; however, it came last for amplifying normal heartbeats of ~85 Hz. Cardionics E-Scope II had advantages in amplifying abnormal heartbeats (i.e., aortic valvular stenosis and pulmonic valvular stenosis) over the other two stethoscopes.Conclusion:This study showed that amplified stethoscopes provided better amplification of normal and abnormal heart sounds across the five measured frequencies. Therefore, health professionals should interpret manufacturer claims regarding gain (dB) and frequency (Hz) with caution, and those with hearing loss should carefully investigate the “audio performance” of the stethoscopes. Future research should focus on these effects through coupling with hearing aids.

Classification of ECG Heartbeat Arrhythmia: A Review

Abstract Manual identification of ECG heart-beat classes by cardiologists is time consuming and cumbersome. These professionals rely on computer based methods for determination of these heart-disease types. In this work, existing literature is organized into a proposed taxonomy based on dichotomies involving full time series-based versus feature-based, AAMI versus Non-AAMI, and inter-patient versus intra-patient based distinctions. The basic contributions of this work are systematic review of literature on heart-beat abnormality detection, identifying research gaps and the research issues unmet sofar in the literature to propose novel approaches for addressing these gaps.

Automated arrhythmia classification based on a combination network of CNN and LSTM

Arrhythmia is an abnormal heartbeat rhythm, and its prevalence increases with age. An electrocardiogram (ECG) is a standard tool for detecting cardiac activity. However, because of the low amplitude, complexity, and non-linearity of the ECG signal, it is difficult to manually perform a rapid and accurate classification. Therefore, an automatic system that can identify different abnormal heartbeats from a large amount of ECG data should be developed for use in the healthcare field. This study proposed an approach based on deep learning that combined convolutional neural networks (CNNs) and long short-term memory networks (LSTM) to automatically identify six types of ECG signals: normal (N) sinus rhythm segments, atrial fibrillation (AFIB), ventricular bigeminy (B), pacing rhythm (P), atrial flutter (AFL), and sinus bradycardia (SBR). The proposed network applied a multi-input structure to process 10 s ECG signal segments and corresponding RR intervals from the MIT-BIH arrhythmia database. With a five-fold cross-validation strategy, this network achieved 99.32 % accuracy. Then, the diversity of the subjects was increased in the training data by supplementing database, improving the previous network model. The method was validated using two additional databases, which are independent of the training database of the network. For the new N and AFIB in additional databases, the proposed method achieved an average accuracy of 97.15 %. The results showed that the proposed model had robust generalization performance and could be used as an auxiliary tool to help clinicians diagnose arrhythmia after training with a larger database.

Classification of temporal data using dynamic time warping and compressed learning

This study proposes an algorithm combining the dynamic time warping (DTW) and compressed learning (CL) techniques for temporal data classification. The DTW is used to address nonsynchronous effects in temporal data for determining an adequate reference trajectory. The CL is employed to represent the temporal data effectively and classify the data efficiently by cooperating with the reference trajectory. By applying the proposed algorithm and four other classification methods to several data sets, the proposed algorithm is shown to have satisfactory classification accuracies within a reasonable time. According to this advantage, the proposed algorithm is extended to establish an online monitoring system to detect abnormal types of cardiac arrhythmia for users with wearable healthcare devices. The numerical results indicate that the proposed classifier has satisfactory recognition results for detecting personal abnormal heartbeats in real time.