A Review of Signal Processing Techniques for Electrocardiogram Signal Quality Assessment

Spectral Characteristics of Motion Artifacts in Wireless ECG and their Correlation with Reference Motion Sensors

The increasing population size of the elderly is fostering the development of telehealth and assisted living systems. In this respect, monitoring vital biophysical conditions using wireless devices, such as the wireless electrocardiogram (WECG), plays a pivotal role in telemonitoring. However, the freedom of movement brings with it motion artifacts, the magnitude of which can be significant enough to interfere with the cardiac signals. To reason about and remove the artifacts, reference models (signals) are needed. In the context of WECGs, one way to construct these models is to employ motion sensors that can pick up the motion affecting the electrodes of the WECGs. In this paper, we experimentally examine the spectra of motion artifacts and the existence of correlations between inertial sensors and motion artifacts. We make use of three different types of sensors (3D accelerometer, 3D gyroscope, and skin-electrode impedance sensor) to assess the characteristics of different movement types. We found that the spectra of motion artifacts are determined by the type of movement. While lower-intensity motion artifacts (e.g., bending forward) are most pronounced below 2 Hz, others (e.g., running) manifest themselves in a series of distinct peaks between 1-10 Hz.Index Terms- accelerometer, electrocardiogram, gyroscope, inertial sensor, motion artifacts, skin-electrode impedance, tele-monitoring.

Research Progress of ECG Monitoring Equipment and Algorithms Based on Polymer Materials

Heart diseases such as myocardial ischemia (MI) are the main causes of human death. The prediction of MI and arrhythmia is an effective method for the early detection, diagnosis, and treatment of heart disease. For the rapid detection of arrhythmia and myocardial ischemia, the electrocardiogram (ECG) is widely used in clinical diagnosis, and its detection equipment and algorithm are constantly optimized. This paper introduces the current progress of portable ECG monitoring equipment, including the use of polymer material sensors and the use of deep learning algorithms. First, it introduces the latest portable ECG monitoring equipment and the polymer material sensor it uses and then focuses on reviewing the progress of detection algorithms. We mainly introduce the basic structure of existing deep learning methods and enumerate the internationally recognized ECG datasets. This paper outlines the deep learning algorithms used for ECG diagnosis, compares the prediction results of different classifiers, and summarizes two existing problems of ECG detection technology: imbalance of categories and high computational overhead. Finally, we put forward the development direction of using generative adversarial networks (GAN) to improve the quality of the ECG database and lightweight ECG diagnosis algorithm to adapt to portable ECG monitoring equipment.

Electrocardiogram Quality Assessment with a Generalized Deep Learning Model Assisted by Conditional Generative Adversarial Networks

The electrocardiogram (ECG) is widely used for cardiovascular disease diagnosis and daily health monitoring. Before ECG analysis, ECG quality screening is an essential but time-consuming and experience-dependent work for technicians. An automatic ECG quality assessment method can reduce unnecessary time loss to help cardiologists perform diagnosis. This study aims to develop an automatic quality assessment system to search qualified ECGs for interpretation. The proposed system consists of data augmentation and quality assessment parts. For data augmentation, we train a conditional generative adversarial networks model to get an ECG segment generator, and thus to increase the number of training data. Then, we pre-train a deep quality assessment model based on a training dataset composed of real and generated ECG. Finally, we fine-tune the proposed model using real ECG and validate it on two different datasets composed of real ECG. The proposed system has a generalized performance on the two validation datasets. The model's accuracy is 97.1% and 96.4%, respectively for the two datasets. The proposed method outperforms a shallow neural network model, and also a deep neural network models without being pre-trained by generated ECG. The proposed system demonstrates improved performance in the ECG quality assessment, and it has the potential to be an initial ECG quality screening tool in clinical practice.

A signal quality assessment-based ECG waveform delineation method used for wearable monitoring systems

Identifying transient and nonpersistent abnormal electrocardiogram (ECG) waveforms by continuously monitoring the high-risk populations is of great importance for the diagnosis, treatment, and prevention of cardiovascular diseases. In recent years, fabric electrodes have been widely used in wearable devices because of their non-irritating properties and better comfort than traditional AgCl electrodes. However, the motion noise caused by the relative movement between the fabric electrodes and skin affects the quality of ECGs and reduces the accuracy of diagnosis. Therefore, delineating the ECG waveforms that are recorded from wearable devices with varying levels of noise is still challenging. In this study, a signal quality assessment (SQA)-based ECG waveform delineation method that is used for wearable systems was developed. The ECG signal was first preprocessed by a bandpass filter. Five indices, including the multiscale nonlinear amplitude statistical distribution (adSQI₁, adSQI₂), the proportion of energy-related to T wave (ptSQI), and heart rates computed from R waves and T waves (rHR and tHR, respectively), were then calculated from the preprocessed ECG signal. The signals were classified as good, acceptable, and unacceptable ECGs by combining these indices through the use of a neural network. Subsequently, the R waves or/and T waves were identified for the corresponding feature interpretations based on the SQA results. ECGs that were recorded from the chest belts from 29 volunteers at different activity statuses were divided into 4-s segments. A total of 7133 manually labeled segments were used to derive (4985 segments) and validate (2148 segments) the algorithm. The adSQI₁, adSQI₂, tHR, and rHR characteristics were significantly different among the good, acceptable, and unacceptable ECGs. The ptSQI value was considerably higher in the good ECGs than in the acceptable and unacceptable ECGs. The ECG segments of different quality levels were classified with an accuracy of 96.74% by using the proposed SQA method. The R waves and T waves were identified with accuracies of 99.95% and 99.57%, respectively, for segments that were classified as acceptable and/or good. The SQA-based ECG waveform delineation method can perform reliable analysis and has the potential to be applied in wearable ECG systems for the early diagnosis and prevention of cardiovascular diseases.

A Proposal for a Data-Driven Approach to the Influence of Music on Heart Dynamics

Electrocardiographic signals (ECG) and heart rate viability measurements (HRV) provide information in a range of specialist fields, extending to musical perception. The ECG signal records heart electrical activity, while HRV reflects the state or condition of the autonomic nervous system. HRV has been studied as a marker of diverse psychological and physical diseases including coronary heart disease, myocardial infarction, and stroke. HRV has also been used to observe the effects of medicines, the impact of exercise and the analysis of emotional responses and evaluation of effects of various quantifiable elements of sound and music on the human body. Variations in blood pressure, levels of stress or anxiety, subjective sensations and even changes in emotions constitute multiple aspects that may well-react or respond to musical stimuli. Although both ECG and HRV continue to feature extensively in research in health and perception, methodologies vary substantially. This makes it difficult to compare studies, with researchers making recommendations to improve experiment planning and the analysis and reporting of data. The present work provides a methodological framework to examine the effect of sound on ECG and HRV with the aim of associating musical structures and noise to the signals by means of artificial intelligence (AI); it first presents a way to select experimental study subjects in light of the research aims and then offers possibilities for selecting and producing suitable sound stimuli; once sounds have been selected, a guide is proposed for optimal experimental design. Finally, a framework is introduced for analysis of data and signals, based on both conventional as well as data-driven AI tools. AI is able to study big data at a single stroke, can be applied to different types of data, and is capable of generalisation and so is considered the main tool in the analysis.

Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study

Background

With the development and promotion of wearable devices and their mobile health (mHealth) apps, physiological signals have become a research hotspot. However, noise is complex in signals obtained from daily lives, making it difficult to analyze the signals automatically and resulting in a high false alarm rate. At present, screening out the high-quality segments of the signals from huge-volume data with few labels remains a problem. Signal quality assessment (SQA) is essential and is able to advance the valuable information mining of signals.

Objective

The aims of this study were to design an SQA algorithm based on the unsupervised isolation forest model to classify the signal quality into 3 grades: good, acceptable, and unacceptable; validate the algorithm on labeled data sets; and apply the algorithm on real-world data to evaluate its efficacy.

Methods

Data used in this study were collected by a wearable device (SensEcho) from healthy individuals and patients. The observation windows for electrocardiogram (ECG) and respiratory signals were 10 and 30 seconds, respectively. In the experimental procedure, the unlabeled training set was used to train the models. The validation and test sets were labeled according to preset criteria and used to evaluate the classification performance quantitatively. The validation set consisted of 3460 and 2086 windows of ECG and respiratory signals, respectively, whereas the test set was made up of 4686 and 3341 windows of signals, respectively. The algorithm was also compared with self-organizing maps (SOMs) and 4 classic supervised models (logistic regression, random forest, support vector machine, and extreme gradient boosting). One case validation was illustrated to show the application effect. The algorithm was then applied to 1144 cases of ECG signals collected from patients and the detected arrhythmia false alarms were calculated.

Results

The quantitative results showed that the ECG SQA model achieved 94.97% and 95.58% accuracy on the validation and test sets, respectively, whereas the respiratory SQA model achieved 81.06% and 86.20% accuracy on the validation and test sets, respectively. The algorithm was superior to SOM and achieved moderate performance when compared with the supervised models. The example case showed that the algorithm was able to correctly classify the signal quality even when there were complex pathological changes in the signals. The algorithm application results indicated that some specific types of arrhythmia false alarms such as tachycardia, atrial premature beat, and ventricular premature beat could be significantly reduced with the help of the algorithm.

Conclusions

This study verified the feasibility of applying the anomaly detection unsupervised model to SQA. The application scenarios include reducing the false alarm rate of the device and selecting signal segments that can be used for further research.

A novel method to reduce false alarms in ECG diagnostic systems: capture and quantification of noisy signals

Objective. Muscle artifacts (MA) and electrode motion artifacts (EMA) in electrocardiogram (ECG) signals lead to a large number of false alarms from cardiac diagnostic systems. To reduce false alarms, it is necessary to improve the performance of the diagnostic algorithm in noisy environments by removing excessively noisy signals. However, existing methods focus on signal quality assessment and contain too many artificial features. Here, we present a novel method to flexibly eliminate noisy signals without any artificial features.Approach. Our method contains an improved lightweight deep neural network (DNN) to capture the signal portions damaged by EMA and MA, uses the sample entropy to quantize noisy portions, and discards those portions that exceed a defined threshold. Our method was tested in conjunction with Pan-Tompkins (PT), Filter Bank (FB), and 'UNSW' R-peak detection algorithms along with two heartbeat classification algorithms on datasets synthesized from the MIT-BIH Noise Stress Test Database, the China Physiological Signal Challenge 2018 Database and the MIT-BIH Arrhythmia Database.Main results. For PT R-peak detection algorithms, the sensitivity (Se) increased noticeably from 89.01% to 99.42% in the synthesized datasets with a signal-to-noise ratio of 6 dB. With the same datasets, the Se of the FB algorithm increased about 9.29%, and a 3.64% increase occurred in the Se of the 'UNSW' algorithm. For heartbeat classification algorithms, the overall F1-score increased about 6% in the synthesized one-heartbeat datasets. It is the first study to utilize a DNN to capture noisy segments of the ECG signal.Significance. Too many false alarms can cause alarm fatigue. Our method can be utilized as the preprocessing before signal analysis, thereby reducing false alarms from the ECG diagnostic systems.

Registered report protocol: Developing an artifact index for capacitive electrocardiography signals acquired with an armchair

Continuous monitoring of an electrocardiogram (ECG) in private diagnostic spaces such as vehicles or apartments allows early detection of cardiovascular diseases. We will use an armchair with integrated capacitive electrodes to record the capacitive electrocardiogram (cECG) during everyday activities. However, movements and other artifacts affect the signal quality. Therefore, an artifact index is needed to detect artifacts and classify the cECG. The unavailability of cECG data and reliable ground truth information requires new recordings to develop an artifact index. This study is designed to test the hypothesis: an artifact index can be devised, which intends to estimate the signal quality of segments and classify signals. In a single-arm study with 44 subjects, we will record two activities of 11-minute duration: reading and watching television. During recording, we will capture cECG, ECG, and oxygen saturation (SpO2) with time synchronization as well as keypoint-based movement indicators obtained from a video camera. SpO2 provides additional information on the subject's health status. The keypoint-based movements indicate artifacts in the cECG. We will combine all ground truth data to evaluate the index. In the future, we aim at using the artifact index to exclude cECG segments with artifacts from further analysis. This will improve cECG technology for the measurement of cardiovascular parameters.

Automatic Detection of Atrial Fibrillation in ECG Using Co-Occurrence Patterns of Dynamic Symbol Assignment and Machine Learning

Early detection of atrial fibrillation from electrocardiography (ECG) plays a vital role in the timely prevention and diagnosis of cardiovascular diseases. Various algorithms have been proposed; however, they are lacking in considering varied-length signals, morphological transitions, and abnormalities over long-term recordings. We propose dynamic symbolic assignment (DSA) to differentiate a normal sinus rhythm (SR) from paroxysmal atrial fibrillation (PAF). We use ECG signals and their interbeat (RR) intervals from two public databases namely, AF Prediction Challenge Database (AFPDB) and AF Termination Challenge Database (AFTDB). We transform RR intervals into a symbolic representation and compute co-occurrence matrices. The DSA feature is extracted using varied symbol-length V, word-size W, and applied to five machine learning algorithms for classification. We test five hypotheses: (i) DSA captures the dynamics of the series, (ii) DSA is a reliable technique for various databases, (iii) optimal parameters improve DSA’s performance, (iv) DSA is consistent for variable signal lengths, and (v) DSA supports cross-data analysis. Our method captures the transition patterns of the RR intervals. The DSA feature exhibit a statistically significant difference in SR and PAF conditions (p < 0.005). The DSA feature with W=3 and V=3 yield maximum performance. In terms of F-measure (F), rotation forest and ensemble learning classifier are the most accurate for AFPDB (F = 94.6%) and AFTDB (F = 99.8%). Our method is effective for short-length signals and supports cross-data analysis. The DSA is capable of capturing the dynamics of varied-lengths ECG signals. Particularly, the optimal parameters-based DSA feature and ensemble learning could help to detect PAF in long-term ECG signals. Our method maps time series into a symbolic representation and identifies abnormalities in noisy, varied-length, and pathological ECG signals.

Removal of Electrocardiogram Artifacts From Local Field Potentials Recorded by Sensing-Enabled Neurostimulator

Sensing-enabled neurostimulators are an advanced technology for chronic observation of brain activities, and show great potential for closed-loop neuromodulation and as implantable brain-computer interfaces. However, local field potentials (LFPs) recorded by sensing-enabled neurostimulators can be contaminated by electrocardiogram (ECG) signals due to complex recording conditions and limited common-mode-rejection-ratio (CMRR). In this study, we propose a solution for removing such ECG artifacts from local field potentials (LFPs) recorded by a sensing-enabled neurostimulator. A synchronized monopolar channel was added as an ECG reference, and two pre-existing methods, i.e., template subtraction and adaptive filtering, were then applied. ECG artifacts were successfully removed and the performance of the method was insensitive to residual stimulation artifacts. This approach to removal of ECG artifacts broadens the range of applications of sensing-enabled neurostimulators.

Landsat 8 Lake Water Clarity Empirical Algorithms: Large-Scale Calibration and Validation Using Government and Citizen Science Data from across Canada

Water clarity has been extensively assessed in Landsat-based remote sensing studies of inland waters, regularly relying on locally calibrated empirical algorithms, and close temporal matching between field data and satellite overpass. As more satellite data and faster data processing systems become readily accessible, new opportunities are emerging to revisit traditional assumptions concerning empirical calibration methodologies. Using Landsat 8 images with large water clarity datasets from southern Canada, we assess: (1) whether clear regional differences in water clarity algorithm coefficients exist and (2) whether model fit can be improved by expanding temporal matching windows. We found that a single global algorithm effectively represents the empirical relationship between in situ Secchi disk depth (SDD) and the Landsat 8 Blue/Red band ratio across diverse lake types in Canada. We also found that the model fit improved significantly when applying a median filter on data from ever-wider time windows between the date of in situ SDD sample and the date of satellite overpass. The median filter effectively removed the outliers that were likely caused by atmospheric artifacts in the available imagery. Our findings open new discussions on the ability of large datasets and temporal averaging methods to better elucidate the true relationships between in situ water clarity and satellite reflectance data.

Adaptive learning and cross training improves R-wave detection in ECG

BACKGROUND AND OBJECTIVE

Automated R-wave detection plays a vital role in electrocardiography (ECG) and ECG-based computer-aided diagnosis. Recently, a multi-level one-dimensional (1D) deep learning approach was presented that shows good performance as compared to traditional methods.

METHODS

In this paper, we present several improvements of the multi-level 1D convolutional neural network (CNN)-based deep learning approach using: (i) adaptive deep learning, (ii) cross-database training, and (iii) cross-lead training. For this, we consider ECG signals from four publicly available databases: MIT-BIH, INCART, TELE, and SDDB, having 109,404, 175,660, 6,708, and 1,684,447 annotated beats, respectively. Except for TELE, all databases provide at least two-lead recordings. To evaluate the improvements, experiments are performed with adaptive k-times cross-trained databases validation scheme (k = 5). The hypothesis tested are: (i) the improvements outperform the state-of-the-art, (ii) cross-database training and adaptive deep learning contribute, and (iii) additional databases or cross-lead training further improves the results.

RESULTS

Our proposed approach outperforms the state-of-the-art. In terms of F-measure, F = 99.75% and F = 95.25% is obtained for the MIT-BIH and TELE databases, respectively. Further, cross-database training (F = 98.02%) is found to be more effective than training on individual databases (F = 97.33%). The performance of our approach further improves when additional databases and different leads are used for training.

CONCLUSION

Existing state-of-the-art methods perform low on noisy and pathological signals. Adaptive cross-data training identifies the optimal model. Using multiple datasets and leads allows analyzing noisy, pathological and mobile-recorded long-term ECG signals without ground truths. These conclusions are based on the comprehensive evaluation of four different databases, and in total, about 4.5 million annotated beats.

Quantifying Signal Quality From Unimodal and Multimodal Sources: Application to EEG With Ocular and Motion Artifacts

With prevalence of electrophysiological data collected outside of the laboratory from portable, non-invasive modalities growing at a rapid rate, the quality of these recorded data, if not adequate, could affect the effectiveness of medical devices that depend of them. In this work, we propose novel methods to evaluate electrophysiological signal quality to determine how much of the data represents the physiological source of interest. Data driven models are investigated through Bayesian decision and deep learning-based methods to score unimodal (signal and noise recorded on same device) and multimodal (signal and noise each recorded from different devices) data, respectively. We validate these methods and models on three electroencephalography (EEG) data sets (N = 60 subjects) to score EEG quality based on the presence of ocular artifacts with our unimodal method and motion artifacts with our multimodal method. Further, we apply our unimodal source method to compare the performance of two different artifact removal algorithms. Our results show we are able to effectively score EEG data using both methods and apply our method to evaluate the performance of other artifact removal algorithms that target ocular artifacts. Methods developed and validated here can be used to assess data quality and evaluate the effectiveness of certain noise-reduction algorithms.

A review of wearable and unobtrusive sensing technologies for chronic disease management

With the rapidly increasing number of patients with chronic disease, numerous recent studies have put great efforts into achieving long-term health monitoring and patient management. Specifically, chronic diseases including cardiovascular disease, chronic respiratory disease and brain disease can threaten patients' health conditions over a long period of time, thus effecting their daily lives. Vital health parameters, such as heart rate, respiratory rate, SpO2 and blood pressure, are closely associated with patients’ conditions. Wearable devices and unobtrusive sensing technologies can detect such parameters in a convenient way and provide timely predictions on health condition deterioration by tracking these biomedical signals and health parameters. In this paper, we review current advancements in wearable devices and unobtrusive sensing technologies that can provides possible tools and technological supports for chronic disease management. Current challenges and future directions of related techniques are addressed accordingly.

Review and Challenges of Technologies for Real-Time Human Behavior Monitoring

A person's behavior significantly influences their health and well-being. It also contributes to the social environment in which humans interact, with cascading impacts to the health and behaviors of others. During social interactions, our understanding and awareness of vital nonverbal messages expressing beliefs, emotions, and intentions can be obstructed by a variety of factors including greatly flawed self-awareness. For these reasons, human behavior is a very important topic to study using the most advanced technology. Moreover, technology offers a breakthrough opportunity to improve people's social awareness and self-awareness through machine-enhanced recognition and interpretation of human behaviors. This paper reviews (1) the social psychology theories that have established the framework to study human behaviors and their manifestations during social interactions and (2) the technologies that have contributed to the monitoring of human behaviors. State-of-the-art in sensors, signal features, and computational models are categorized, summarized, and evaluated from a comprehensive transdisciplinary perspective. This review focuses on assessing technologies most suitable for real-time monitoring while highlighting their challenges and opportunities in near-future applications. Although social behavior monitoring has been highly reported in psychology and engineering literature, this paper uniquely aims to serve as a disciplinary convergence bridge and a guide for engineers capable of bringing new technologies to bear against the current challenges in real-time human behavior monitoring.

A Review on the State of the Art in Atrial Fibrillation Detection Enabled by Machine Learning

Atrial Fibrillation (AF) the most commonly occurring type of cardiac arrhythmia is one of the main causes of morbidity and mortality worldwide. The timely diagnosis of AF is an equally important and challenging task because of its asymptomatic and episodic nature. In this paper, state-of-the-art ECG data-based machine learning models and signal processing techniques applied for auto diagnosis of AF are reviewed. Moreover, key biomarkers of AF on ECG and the common methods and equipment used for the collection of ECG data are discussed. Besides that, the modern wearable and implantable ECG sensing technologies used for gathering AF data are presented briefly. In the end, key challenges associated with the development of auto diagnosis solutions of AF are also highlighted. This is the first review paper of its kind that comprehensively presents a discussion on all these aspects related to AF auto-diagnosis in one place. It is observed that there is a dire need for low energy and low cost but accurate auto diagnosis solutions for the proactive management of AF.

Recommendations for determining the validity of consumer wearable heart rate devices: expert statement and checklist of the INTERLIVE Network

Assessing vital signs such as heart rate (HR) by wearable devices in a lifestyle-related environment provides widespread opportunities for public health related research and applications. Commonly, consumer wearable devices assessing HR are based on photoplethysmography (PPG), where HR is determined by absorption and reflection of emitted light by the blood. However, methodological differences and shortcomings in the validation process hamper the comparability of the validity of various wearable devices assessing HR. Towards Intelligent Health and Well-Being: Network of Physical Activity Assessment (INTERLIVE) is a joint European initiative of six universities and one industrial partner. The consortium was founded in 2019 and strives towards developing best-practice recommendations for evaluating the validity of consumer wearables and smartphones. This expert statement presents a best-practice validation protocol for consumer wearables assessing HR by PPG. The recommendations were developed through the following multi-stage process: (1) a systematic literature review based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses, (2) an unstructured review of the wider literature pertaining to factors that may introduce bias during the validation of these devices and (3) evidence-informed expert opinions of the INTERLIVE Network. A total of 44 articles were deemed eligible and retrieved through our systematic literature review. Based on these studies, a wider literature review and our evidence-informed expert opinions, we propose a validation framework with standardised recommendations using six domains: considerations for the target population, criterion measure, index measure, testing conditions, data processing and the statistical analysis. As such, this paper presents recommendations to standardise the validity testing and reporting of PPG-based HR wearables used by consumers. Moreover, checklists are provided to guide the validation protocol development and reporting. This will ensure that manufacturers, consumers, healthcare providers and researchers use wearables safely and to its full potential.

Machine learning for predictive data analytics in medicine: A review illustrated by cardiovascular and nuclear medicine examples

The evidence-based medicine allows the physician to evaluate the risk-benefit ratio of a treatment through setting and data. Risk-based choices can be done by the doctor using different information. With the emergence of new technologies, a large amount of data is recorded offering interesting perspectives with machine learning for predictive data analytics. Machine learning is an ensemble of methods that process data to model a learning problem. Supervised machine learning algorithms consist in using annotated data to construct the model. This category allows to solve prediction data analytics problems. In this paper, we detail the use of supervised machine learning algorithms for predictive data analytics problems in medicine. In the medical field, data can be split into two categories: medical images and other data. For brevity, our review deals with any kind of medical data excluding images. In this article, we offer a discussion around four supervised machine learning approaches: information-based, similarity-based, probability-based and error-based approaches. Each method is illustrated with detailed cardiovascular and nuclear medicine examples. Our review shows that model ensemble (ME) and support vector machine (SVM) methods are the most popular. SVM, ME and artificial neural networks often lead to better results than those given by other algorithms. In the coming years, more studies, more data, more tools and more methods will, for sure, be proposed.

Wearable Devices for Ambulatory Cardiac Monitoring: JACC State-of-the-Art Review

Ambulatory monitoring devices are enabling a new paradigm of health care by collecting and analyzing long-term data for reliable diagnostics. These devices are becoming increasingly popular for continuous monitoring of cardiac diseases. Recent advancements have enabled solutions that are both affordable and reliable, allowing monitoring of vulnerable populations from the comfort of their homes. They provide early detection of important physiological events, leading to timely alerts for seeking medical attention. In this review, the authors aim to summarize the recent developments in the area of ambulatory and remote monitoring solutions for cardiac diagnostics. The authors cover solutions based on wearable devices, smartphones, and other ambulatory sensors. The authors also present an overview of the limitations of current technologies, their effectiveness, and their adoption in the general population, and discuss some of the recently proposed methods to overcome these challenges. Lastly, we discuss the possibilities opened by this new paradigm, for the future of health care and personalized medicine.

Assessing the signal quality of electrocardiograms from varied acquisition sources: A generic machine learning pipeline for model generation

BACKGROUND AND OBJECTIVE

Long-term electrocardiogram monitoring comes at the expense of signal quality. During unconstrained movements, the electrocardiogram is often corrupted by motion artefacts, which can lead to inaccurate physiological information. In this situation, automated quality assessment methods are useful to increase the reliability of the measurements. A generic machine learning pipeline that generates classification models for electrocardiogram quality assessment is presented in this article. The presented pipeline is tested on signals from varied acquisition sources, towards selecting segments that can be used for heart rate analysis in lifestyle applications.

METHODS

Electrocardiogram recordings from traditional, wearable and ubiquitous devices, are segmented in 10 s windows and manually labeled by experienced researchers into two quality classes. To capture the electrocardiogram dynamics, a comprehensive set of 43 features is extracted from each segment, based on the time-domain signal, its Fast Fourier Transform, the Autocorrelation function and the Stationary Wavelet Transform. To select the most relevant features for each acquisition source we employ both a customized hybrid approach and the state-of-the-art Neighborhood Component Analysis method and compare them. Support Vector Machines (SVM), Decision Trees, K-Nearest-Neighbors and supervised ensemble methods are tested as possible binary classifiers.

RESULTS

The results for the best performing models on traditional, wearable and ubiquitous electrocardiogram datasets are, respectively: balanced-accuracy: 89%, F1-score: 93% with the Fine Gaussian SVM model and 10 features; balanced-accuracy: 93%, F1-score: 93% with the Fine Gaussian SVM model and 11 features; balanced-accuracy: 95%, F1-score: 86%, with the Fine Gaussian SVM model and 8 features.

CONCLUSIONS

According to the results, our generic pipeline can generate classification models tailored to individual acquisition sources, provided that a standard Lead I or Lead II is available. Such models accurately establish whether the electrocardiogram quality is good or bad for heart rate analysis. Furthermore, removing bad quality segments decreases errors in heart rate calculation.

QRS Differentiation to Improve ECG Biometrics under Different Physical Scenarios Using Multilayer Perceptron

Currently, machine learning techniques are successfully applied in biometrics and Electrocardiogram (ECG) biometrics specifically. However, not many works deal with different physiological states in the user, which can provide significant heart rate variations, being these a key matter when working with ECG biometrics. Techniques in machine learning simplify the feature extraction process, where sometimes it can be reduced to a fixed segmentation. The applied database includes visits taken in two different days and three different conditions (sitting down, standing up after exercise), which is not common in current public databases. These characteristics allow studying differences among users under different scenarios, which may affect the pattern in the acquired data. Multilayer Perceptron (MLP) is used as a classifier to form a baseline, as it has a simple structure that has provided good results in the state-of-the-art. This work studies its behavior in ECG verification by using QRS complexes, finding its best hyperparameter configuration through tuning. The final performance is calculated considering different visits for enrolling and verification. Differentiation in the QRS complexes is also tested, as it is already required for detection, proving that applying a simple first differentiation gives a good result in comparison to state-of-the-art similar works. Moreover, it also improves the computational cost by avoiding complex transformations and using only one type of signal. When applying different numbers of complexes, the best results are obtained when 100 and 187 complexes in enrolment, obtaining Equal Error Rates (EER) that range between 2.79–4.95% and 2.69–4.71%, respectively.

A Deep Learning Approach for Featureless Robust Quality Assessment of Intermittent Atrial Fibrillation Recordings from Portable and Wearable Devices

Atrial fibrillation (AF) is the most common heart rhythm disturbance in clinical practice. It often starts with asymptomatic and very short episodes, which are extremely difficult to detect without long-term monitoring of the patient’s electrocardiogram (ECG). Although recent portable and wearable devices may become very useful in this context, they often record ECG signals strongly corrupted with noise and artifacts. This impairs automatized ulterior analyses that could only be conducted reliably through a previous stage of automatic identification of high-quality ECG intervals. So far, a variety of techniques for ECG quality assessment have been proposed, but poor performances have been reported on recordings from patients with AF. This work introduces a novel deep learning-based algorithm to robustly identify high-quality ECG segments within the challenging environment of single-lead recordings alternating sinus rhythm, AF episodes and other rhythms. The method is based on the high learning capability of a convolutional neural network, which has been trained with 2-D images obtained when turning ECG signals into wavelet scalograms. For its validation, almost 100,000 ECG segments from three different databases have been analyzed during 500 learning-testing iterations, thus involving more than 320,000 ECGs analyzed in total. The obtained results have revealed a discriminant ability to detect high-quality and discard low-quality ECG excerpts of about 93%, only misclassifying around 5% of clean AF segments as noisy ones. In addition, the method has also been able to deal with raw ECG recordings, without requiring signal preprocessing or feature extraction as previous stages. Consequently, it is particularly suitable for portable and wearable devices embedding, facilitating early detection of AF as well as other automatized diagnostic facilities by reliably providing high-quality ECG excerpts to further processing stages.

Feasibility of Long-Term Daily Life Electrocardiogram Monitoring Based on a Wearable Armband Device

A study on the feasibility of obtaining usable electrocardiogram (ECG) signals from a wearable armband during 24-hour continuous monitoring is presented. The wearable armband records 3-channel ECG and, unlike the conventional Holter monitors, it is convenient for long-term daily life monitoring because it uses no obstructive leads and it is based on dry (no gels) electrodes, which do not cause skin irritation. An optimal channel selector is presented, based on a linear classifier using features that are related to the ECG signal quality. In addition, this linear classifier is also used for artifact detection. The developed optimal channel selector and artifact detector are applied to 24-hour armband ECG recordings from 5 subjects. For reference comparison, the subjects also wore a Holter device. The armband obtained usable data during 51.07±13.54% (inter-subject mean ± standard deviation) of the non-bed recording time, and the mean heart rate was accurately (relative error with respect to the Holter less than 10%) estimated from the armband selected ECG channel from 94.39±3.41% of the usable data. During the bed recording time, the percentage of usable data was 93.54±2.92%, and mean heart rate was estimated accurately from 97.01±1.80% of those data. These results suggest that the armband device is potentially feasible for a long-term daily life heart rate monitoring based on the presented channel selector and artifact detector, especially during the bed time.

The complexity of clinically-normal sinus-rhythm ECGs is decreased in equine athletes with a diagnosis of paroxysmal atrial fibrillation

Equine athletes have a pattern of exercise which is analogous to human athletes and the cardiovascular risks in both species are similar. Both species have a propensity for atrial fibrillation (AF), which is challenging to detect by ECG analysis when in paroxysmal form. We hypothesised that the proarrhythmic background present between fibrillation episodes in paroxysmal AF (PAF) might be detectable by complexity analysis of apparently normal sinus-rhythm ECGs. In this retrospective study ECG recordings were obtained during routine clinical work from 82 healthy horses and from 10 horses with a diagnosis of PAF. Artefact-free 60-second strips of normal sinus-rhythm ECGs were converted to binary strings using threshold crossing, beat detection and a novel feature detection parsing algorithm. Complexity of the resulting binary strings was calculated using Lempel-Ziv (‘76 & ‘78) and Titchener complexity estimators. Dependence of Lempel-Ziv ‘76 and Titchener T-complexity on the heart rate in ECG strips obtained at low heart rates (25–60 bpm) and processed by the feature detection method was found to be significantly different in control animals and those diagnosed with PAF. This allows identification of horses with PAF from sinus-rhythm ECGs with high accuracy.

Detection and classification of ECG noises using decomposition on mixed codebook for quality analysis

In this Letter, a robust technique is presented to detect and classify different electrocardiogram (ECG) noises including baseline wander (BW), muscle artefact (MA), power line interference (PLI) and additive white Gaussian noise (AWGN) based on signal decomposition on mixed codebooks. These codebooks employ temporal and spectral-bound waveforms which provide sparse representation of ECG signals and can extract ECG local waves as well as ECG noises including BW, PLI, MA and AWGN simultaneously. Further, different statistical approaches and temporal features are applied on decomposed signals for detecting the presence of the above mentioned noises. The accuracy and robustness of the proposed technique are evaluated using a large set of noise-free and noisy ECG signals taken from the Massachusetts Institute of Technology-Boston's Beth Israel Hospital (MIT-BIH) arrhythmia database, MIT-BIH polysmnographic database and Fantasia database. It is shown from the results that the proposed technique achieves an average detection accuracy of above 99% in detecting all kinds of ECG noises. Furthermore, average results show that the technique can achieve an average sensitivity of 98.55%, positive productivity of 98.6% and classification accuracy of 97.19% for ECG signals taken from all three databases.

Real-Time Quality Assessment of Long-Term ECG Signals Recorded by Wearables in Free-Living Conditions

OBJECTIVE

Nowadays, methods for ECG quality assessment are mostly designed to binary distinguish between good/bad quality of the whole signal. Such classification is not suitable to long-term data collected by wearable devices. In this paper, a novel approach to estimate long-term ECG signal quality is proposed.

METHODS

The real-time quality estimation is performed in a local time window by calculation of continuous signal-to-noise ratio (SNR) curve. The layout of the data quality segments is determined by analysis of SNR waveform. It is distinguished between three levels of ECG signal quality: signal suitable for full wave ECG analysis, signal suitable only for QRS detection, and signal unsuitable for further processing.

RESULTS

The SNR limits for reliable QRS detection and full ECG waveform analysis are 5 and 18 dB respectively. The method was developed and tested using synthetic data and validated on real data from wearable device.

CONCLUSION

The proposed solution is a robust, accurate and computationally efficient algorithm for annotation of ECG signal quality that will facilitate the subsequent tailored analysis of ECG signals recorded in free-living conditions.

SIGNIFICANCE

The field of long-term ECG signals self-monitoring by wearable devices is swiftly developing. The analysis of massive amount of collected data is time consuming. It is advantageous to characterize data quality in advance and thereby limit consequent analysis to useable signals.

Computational approaches for detection of cardiac rhythm abnormalities: Are we there yet?

The analysis of an electrocardiogram (ECG) is able to provide vital information on the electrical activity of the heart and is crucial for the accurate diagnosis of cardiac arrhythmias. Due to the nature of some arrhythmias, this might be a time-consuming and difficult to accomplish process. The advent of novel machine learning technologies in this field has a potential to revolutionise the use of the ECG. In this review, we outline key advances in ECG analysis for atrial, ventricular and complex multiform arrhythmias, as well as discuss the current limitations of the technology and the barriers that must be overcome before clinical integration is feasible.

Artefact detection and quality assessment of ambulatory ECG signals

BACKGROUND AND OBJECTIVES

The presence of noise sources could reduce the diagnostic capability of the ECG signal and result in inappropriate treatment decisions. To mitigate this problem, automated algorithms to detect artefacts and quantify the quality of the recorded signal are needed. In this study we present an automated method for the detection of artefacts and quantification of the signal quality. The suggested methodology extracts descriptive features from the autocorrelation function and feeds these to a RUSBoost classifier. The posterior probability of the clean class is used to create a continuous signal quality assessment index. Firstly, the robustness of the proposed algorithm is investigated and secondly, the novel signal quality assessment index is evaluated.

METHODS

Data were used from three different studies: a Sleep study, the PhysioNet 2017 Challenge and a Stress study. Binary labels, clean or contaminated, were available from different annotators with experience in ECG analysis. Two types of realistic ECG noise from the MIT-BIH Noise Stress Test Database (NSTDB) were added to the Sleep study to test the quality index. Firstly, the model was trained on the Sleep dataset and subsequently tested on a subset of the other two datasets. Secondly, all recording conditions were taken into account by training the model on a subset derived from the three datasets. Lastly, the posterior probabilities of the model for the different levels of agreement between the annotators were compared.

RESULTS

AUC values between 0.988 and 1.000 were obtained when training the model on the Sleep dataset. These results were further improved when training on the three datasets and thus taking all recording conditions into account. A Pearson correlation coefficient of 0.8131 was observed between the score of the clean class and the level of agreement. Additionally, significant quality decreases per noise level for both types of added noise were observed.

CONCLUSIONS

The main novelty of this study is the new approach to ECG signal quality assessment based on the posterior clean class probability of the classifier.

Data Fusion of Multivariate Time Series: Application to Noisy 12-Lead ECG Signals

Twelve-lead Electrocardiograph (ECG) signals fusion is crucial for further ECG signal processing. In this paper, based on the idea of the local weighted linear prediction algorithm, a novel fusion data algorithm is proposed, which was applied in data fusion of the 12-lead ECG signals. In order to analyze the signal quality comprehensively, the quality characteristics should be adequately retained in the final fused result. In our algorithm, the values for the weighted coefficient of state points were closely related to the final fused result. Thus, two fuzzy inference systems were designed to calculate the weighted coefficients. For the sake of assessing the performance of our method, synthetic ECG signals and realistic ECG signals were applied in the experiments. Experimental results indicate that our method can fuse the 12-lead ECG signals effectively with inherit the quality characteristics of original ECG signals inherited properly.

A Comparative Analysis of Methods for Evaluation of ECG Signal Quality after Compression

The assessment of ECG signal quality after compression is an essential part of the compression process. Compression facilitates the signal archiving, speeds up signal transmission, and reduces the energy consumption. Conversely, lossy compression distorts the signals. Therefore, it is necessary to express the compression performance through both compression efficiency and signal quality. This paper provides an overview of objective algorithms for the assessment of both ECG signal quality after compression and compression efficiency. In this area, there is a lack of standardization, and there is no extensive review as such. 40 methods were tested in terms of their suitability for quality assessment. For this purpose, the whole CSE database was used. The tested signals were compressed using an algorithm based on SPIHT with varying efficiency. As a reference, compressed signals were manually assessed by two experts and classified into three quality groups. Owing to the experts' classification, we determined corresponding ranges of selected quality evaluation methods' values. The suitability of the methods for quality assessment was evaluated based on five criteria. For the assessment of ECG signal quality after compression, we recommend using a combination of these methods: PSim SDNN, QS, SNR1, MSE, PRDN1, MAX, STDERR, and WEDD SWT.