Automated detection of atrial fibrillation using long short-term memory network with RR interval signals

Semi-Supervised Analysis of the Electrocardiogram Using Deep Generative Models

Deep learning has gained increased impact on medical classification problems in recent years, with models being trained to high performance. However neural networks require large amounts of labeled data, which on medical data can be expensive and cumbersome to obtain. We propose a semi-supervised setup using an unsupervised variational autoencoder combined with a supervised classifier to distinguish between atrial fibrillation and non-atrial fibrillation using ECG records from the MIT-BIH Atrial Fibrillation Database. The proposed model was compared to a fully-supervised convolutional neural network at different proportions of labeled and unlabeled data (1%-50% labeled and the remaining unlabeled). The results demonstrate that the semi-supervised approach was superior to the fully-supervised, from using as little as 5% (5,594 samples) labeled data with an accuracy of 98.7%. The work provides proof of concept and demonstrates that the proposed semisupervised setup can train high accuracy models at low amounts of labeled data.

Information fusion and multi-classifier system for miner fatigue recognition in plateau environments based on electrocardiography and electromyography signals

BACKGROUND AND OBJECTIVE

Human factors are important contributors to accidents, especially human error induced by fatigue. In this study, field tests and analyses were conducted on physiological indexes extracted from electrocardiography (ECG) and electromyography (EMG) signals in miners working under the extreme conditions of a plateau environment. To provide insights into models for fatigue classification and recognition based on machine learning, multi-modal feature information fusion and miner fatigue identification based on ECG and EMG signals as physiological indicators were studied.

METHODS

Fifty-five miners were randomly selected as field test subjects, and characteristic signals were extracted from 110 groups of ECG and EMG signals as the basic signals for fatigue analysis. We conducted principal component analysis (PCA) and grey relational analysis (GRA) on the measurement indicators. Support vector machine (SVM), random forest (RF) and extreme gradient boosting (XG-Boost) machine learning models were used for fatigue classification based on multi-modal information fusion. The area under the receiver operating characteristic (ROC) curve and the confusion matrix were used to evaluate the performance of the recognition models.

RESULTS

The ECG and EMG signals showed obvious changes with fatigue. The results of fatigue model identification showed that PCA feature fusion was superior to GRA feature fusion for all three machine learning approaches, and XG-Boost achieved the best performance, with a recognition accuracy of 89.47%, a sensitivity and specificity of 100%, and an AUC of 0.90. The SVM model also showed good recognition performance (89.47% accuracy, AUC=0.89). The worst performance was that of the RF model, with a recognition accuracy of only 78.95%.

CONCLUSIONS

This study shows that the physiological indexes of ECG and EMG exhibit obvious, regular changes with fatigue and that it is feasible to use SVM, RF and XG-Boost models for miner fatigue identification. The PCA fusion technique can improve the identification accuracy more than the GRA method. XG-Boost classification yields the best accuracy and robustness. This study can serve as a reference for clinical research on the identification of human fatigue at high altitudes and for the clinical study of acute mountain sickness and human acclimatization to high altitudes.

Review of Deep Learning-Based Atrial Fibrillation Detection Studies

Atrial fibrillation (AF) is a common arrhythmia that can lead to stroke, heart failure, and premature death. Manual screening of AF on electrocardiography (ECG) is time-consuming and prone to errors. To overcome these limitations, computer-aided diagnosis systems are developed using artificial intelligence techniques for automated detection of AF. Various machine learning and deep learning (DL) techniques have been developed for the automated detection of AF. In this review, we focused on the automated AF detection models developed using DL techniques. Twenty-four relevant articles published in international journals were reviewed. DL models based on deep neural network, convolutional neural network (CNN), recurrent neural network, long short-term memory, and hybrid structures were discussed. Our analysis showed that the majority of the studies used CNN models, which yielded the highest detection performance using ECG and heart rate variability signals. Details of the ECG databases used in the studies, performance metrics of the various models deployed, associated advantages and limitations, as well as proposed future work were summarized and discussed. This review paper serves as a useful resource for the researchers interested in developing innovative computer-assisted ECG-based DL approaches for AF detection.

Considerations on Performance Evaluation of Atrial Fibrillation Detectors

OBJECTIVE

A large number of atrial fibrillation (AF) detectors have been published in recent years, signifying that the comparison of detector performance plays a central role, though not always consistent. The aim of this study is to shed needed light on aspects crucial to the evaluation of detection performance.

METHODS

Three types of AF detector, using either information on rhythm, rhythm and morphology, or segments of ECG samples, are implemented and studied on both real and simulated ECG signals. The properties of different performance measures are investigated, for example, in relation to dataset imbalance.

RESULTS

The results show that performance can differ considerably depending on the way detector output is compared to database annotations, i.e., beat-to-beat, segment-to-segment, or episode-to-episode comparison. Moreover, depending on the type of detector, the results substantiate that physiological and technical factors, e.g., changes in ECG morphology, rate of atrial premature beats, and noise level, can have a considerable influence on performance.

CONCLUSION

The present study demonstrates overall strengths and weaknesses of different types of detector, highlights challenges in AF detection, and proposes five recommendations on how to handle data and characterize performance.

Cardiac Arrhythmia Classification Based on One-Dimensional Morphological Features

The electrocardiogram (ECG) is the most commonly used tool for diagnosing cardiovascular diseases. Recently, there have been a number of attempts to classify cardiac arrhythmias using machine learning and deep learning techniques. In this study, we propose a novel method to generate the gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) from one-dimensional signals. From the GLCM and GLRLM, we extracted morphological features for automatic ECG signal classification. The extracted features were combined with six machine learning algorithms (decision tree, k-nearest neighbor, naïve Bayes, logistic regression, random forest, and XGBoost) to classify cardiac arrhythmias. Experiments were conducted on a 12-lead ECG database collected from Chapman University and Shaoxing People’s Hospital. Of the six machine learning algorithms, combining XGBoost with the proposed features yielded an accuracy of 90.46%, an AUC of 0.982, a sensitivity of 0.892, a precision of 0.900, and an F1 score of 0.895 and presented better results than wavelet features with XGBoost. The experimental results show the effectiveness of the proposed feature extraction algorithm.

TP-CNN: A Detection Method for atrial fibrillation based on transposed projection signals with compressed sensed ECG

BACKGROUND AND OBJECTIVE

Atrial fibrillation (AF) is the most prevalent arrhythmia, which increases the mortality of several complications. The use of wearable devices to detect atrial fibrillation is currently attracting a great deal of attention. Patients use wearable devices to continuously collect individual ECG signals and transmit them to the cloud for diagnosis. However, the ECG acquisition and transmission of wearable devices consumes a lot of energy. In order to solve this problem, some scholars have skipped the complex reconstruction process of compressed ECG signals and directly classified the compressed ECG signals, but the AF recognition rate is not high by this method. There is no explanation as to why the compressed ECG signals can be used for AF detection.

METHODS

Firstly, a simple deterministic measurement matrix (SDMM) is used to perform random projection operation on the ECG signals to complete the compression. Then, we use the transpose of the SDMM to perform transpose projection operation on the compressed signals in the cloud to obtain the approximate signals. We verify the similarity between the approximate ECG signal and the original ECG signal to explain why the compressed ECG signals are effective in AF detection. Finally, the Transposed Projection - Convolutional Neural Network (TP-CNN) is used to effectively detect AF on the obtained approximate ECG signals. Our proposed method is validated in the MIT-BIH AFDB.

RESULTS

The experimental results show that when compression ratios (CRs) are from 2 to 10, the average Pearson correlation coefficients between the approximate signals and the original signals are from 0.9867 to 0.8326, the average cosine similarities between the four frequency domain-based HRV features (including mean RR, RMSSD, SDNN and R density) are from 1.00 to 0.9958, from 1.00 to 0.9959, from 0.9978 to 0.8619 and from 0.9982 to 0.8707, respectively. Furthermore, when CR=10 (ECG was compressed to 1/10 of the original signal), the accuracy, specificity, f1 score and matthews correlation coefficient for AF detection of approximate signals were 99.32%, 99.43%, 99.14% and 98.57%, respectively.

CONCLUSION

Our proposed method illustrates the approximate signals have significant characteristics of the original signals and they are valid to classify the approximate signals. Meanwhile, comparing with the state-of-the-art methods, TP-CNN exceeded the results of the method for compressed signals and were also competitive compared with the classification results of the original signals, and is a promising method for AF detection in wearable application scenarios.

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

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

Detection of Brief Episodes of Atrial Fibrillation Based on Electrocardiomatrix and Convolutional Neural Network

Background: Brief episodes of atrial fibrillation (AF) may evolve into longer AF episodes increasing the chances of thrombus formation, stroke, and death. Classical methods for AF detection investigate rhythm irregularity or P-wave absence in the ECG, while deep learning approaches profit from the availability of annotated ECG databases to learn discriminatory features linked to different diagnosis. However, some deep learning approaches do not provide analysis of the features used for classification. This paper introduces a convolutional neural network (CNN) approach for automatic detection of brief AF episodes based on electrocardiomatrix-images (ECM-images) aiming to link deep learning to features with clinical meaning. Materials and Methods: The CNN is trained using two databases: the Long-Term Atrial Fibrillation and the MIT-BIH Normal Sinus Rhythm, and tested on three databases: the MIT-BIH Atrial Fibrillation, the MIT-BIH Arrhythmia, and the Monzino-AF. Detection of AF is done using a sliding window of 10 beats plus 3 s. Performance is quantified using both standard classification metrics and the EC57 standard for arrhythmia detection. Layer-wise relevance propagation analysis was applied to link the decisions made by the CNN to clinical characteristics in the ECG. Results: For all three testing databases, episode sensitivity was greater than 80.22, 89.66, and 97.45% for AF episodes shorter than 15, 30 s, and for all episodes, respectively. Conclusions: Rhythm and morphological characteristics of the electrocardiogram can be learned by a CNN from ECM-images for the detection of brief episodes of AF.

Automated Arrhythmia Detection Based on RR Intervals

Abnormal heart rhythms, also known as arrhythmias, can be life-threatening. AFIB and AFL are examples of arrhythmia that affect a growing number of patients. This paper describes a method that can support clinicians during arrhythmia diagnosis. We propose a deep learning algorithm to discriminate AFIB, AFL, and NSR RR interval signals. The algorithm was designed with data from 4051 subjects. With 10-fold cross-validation, the algorithm achieved the following results: ACC = 99.98%, SEN = 100.00%, and SPE = 99.94%. These results are significant because they show that it is possible to automate arrhythmia detection in RR interval signals. Such a detection method makes economic sense because RR interval signals are cost-effective to measure, communicate, and process. Having such a cost-effective solution might lead to widespread long-term monitoring, which can help detecting arrhythmia earlier. Detection can lead to treatment, which improves outcomes for patients.

Automatic Detection of Short-Term Atrial Fibrillation Segments Based on Frequency Slice Wavelet Transform and Machine Learning Techniques

Atrial fibrillation (AF) is the most frequently encountered cardiac arrhythmia and is often associated with other cardiovascular and cerebrovascular diseases, such as ischemic heart disease, chronic heart failure, and stroke. Automatic detection of AF by analyzing electrocardiogram (ECG) signals has an important application value. Using the contaminated and actual ECG signals, it is not enough to only analyze the atrial activity of disappeared P wave and appeared F wave in the TQ segment. Moreover, the best analysis method is to combine nonlinear features analyzing ventricular activity based on the detection of R peak. In this paper, to utilize the information of the P-QRS-T waveform generated by atrial and ventricular activity, frequency slice wavelet transform (FSWT) is adopted to conduct time-frequency analysis on short-term ECG segments from the MIT-BIH Atrial Fibrillation Database. The two-dimensional time-frequency matrices are obtained. Furthermore, an average sliding window is used to convert the two-dimensional time-frequency matrices to the one-dimensional feature vectors, which are classified using five machine learning (ML) techniques. The experimental results show that the classification performance of the Gaussian-kernel support vector machine (GKSVM) based on the Bayesian optimizer is better. The accuracy of the training set and validation set are 100% and 93.4%. The accuracy, sensitivity, and specificity of the test set without training are 98.15%, 96.43%, and 100%, respectively. Compared with previous research results, our proposed FSWT-GKSVM model shows stability and robustness, and it could achieve the purpose of automatic detection of AF.

HADLN: Hybrid Attention-Based Deep Learning Network for Automated Arrhythmia Classification

In recent years, with the development of artificial intelligence, deep learning model has achieved initial success in ECG data analysis, especially the detection of atrial fibrillation. In order to solve the problems of ignoring the correlation between contexts and gradient dispersion in traditional deep convolution neural network model, the hybrid attention-based deep learning network (HADLN) method is proposed to implement arrhythmia classification. The HADLN can make full use of the advantages of residual network (ResNet) and bidirectional long–short-term memory (Bi-LSTM) architecture to obtain fusion features containing local and global information and improve the interpretability of the model through the attention mechanism. The method is trained and verified by using the PhysioNet 2017 challenge dataset. Without loss of generality, the ECG signal is classified into four categories, including atrial fibrillation, noise, other, and normal signals. By combining the fusion features and the attention mechanism, the learned model has a great improvement in classification performance and certain interpretability. The experimental results show that the proposed HADLN method can achieve precision of 0.866, recall of 0.859, accuracy of 0.867, and F1-score of 0.880 on 10-fold cross-validation.

Learning Explainable Time-Morphology Patterns for Automatic Arrhythmia Classification from Short Single-Lead ECGs

Automatic detection of abnormal heart rhythms, including atrial fibrillation (AF), using signals obtained from a single-lead wearable electrocardiogram (ECG) device, is useful for daily cardiac health monitoring. In this study, we propose a novel image-based deep learning framework to classify single-lead ECG recordings of short variable length into several different rhythms associated with arrhythmias. By transforming variable-length 1D ECG signals into fixed-size 2D time-morphology representations and feeding them to the beat-interval-texture convolutional neural network (BIT-CNN) model, we aimed to learn the comprehensible characteristics of beat shape and inter-beat patterns over time for arrhythmia classification. The proposed approach allows feature embedding vectors to provide interpretable time-morphology patterns focused at each step of the learning process. In addition, this method reduces the number of model parameters needed to be trained and aids visual interpretation, while maintaining similar performance to other CNN-based approaches to arrhythmia classification. For experiments, we used the PhysioNet/CinC Challenge 2017 dataset and achieved an overall F_{1_NAO} of 81.75% and F_{1_NAOP} of 76.87%, which are comparable to those of the state-of-the-art methods for variable-length ECGs.

AF episodes recognition using optimized time-frequency features and cost-sensitive SVM

Although atrial fibrillation (AF) Arrhythmia is highly prevalent within a wide range of populations with major associated risks and due to its episodic occurrence, its recognition remains a challenge for doctors. This paper aims to present and experimentally validate a new efficient approach for the detection and classification of this cardiac anomaly using multiple Electrocardiogram (ECG) signals. This work consists of applying Stockwell transform (ST) with compact support kernel (ST-CSK) for ECG time-frequency analysis. The estimation of the atrial activity (AA) is then achieved after analyzing P-waves of the ECG signals for each heartbeat. ECG signals segmentation allows characterizing the AA by making use of its (t, f) flatness, (t, f) flux, energy concentration and heart rate variability. The features matrix is employed as an input of the support vector machines (SVM) working in binary and asymmetrical mode with an embedded reject option. The proposed algorithm is trained and then tested using different ECG sources namely two databases provided by PhysionNet (MIT-BIH Arrhythmia, MIT-BIH Atrial Fibrillation) and recorded ECG signals using MySignals HW development platform with raspberry Pi 3 model B[Formula: see text]. The used method has achieved [Formula: see text] and [Formula: see text] as sensitivity and specificity, respectively. The obtained results confirm that the proposed approach represents a promising tool for Atrial Fibrillation Episodes (AFE) recognition with significant separability between Normal atrial activity and atrial activity with AF even under real and clinical conditions.

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

There has been an exponential growth of artificial intelligence (AI) and machine learning (ML) publications aimed at advancing our understanding of atrial fibrillation (AF), which has been mainly driven by the confluence of two factors: the advances in deep neural networks (DeepNNs) and the availability of large, open access databases. It is observed that most of the attention has centred on applying ML for dvsetecting AF, particularly using electrocardiograms (ECGs) as the main data modality. Nearly a third of them used DeepNNs to minimize or eliminate the need for transforming the ECGs to extract features prior to ML modelling; however, we did not observe a significant advantage in following this approach. We also found a fraction of studies using other data modalities, and others centred in aims, such as risk prediction, AF management, and others. From the clinical perspective, AI/ML can help expand the utility of AF detection and risk prediction, especially for patients with additional comorbidities. The use of AI/ML for detection and risk prediction into applications and smart mobile health (mHealth) technology would enable ‘real time’ dynamic assessments. AI/ML could also adapt to treatment changes over time, as well as incident risk factors. Incorporation of a dynamic AI/ML model into mHealth technology would facilitate ‘real time’ assessment of stroke risk, facilitating mitigation of modifiable risk factors (e.g. blood pressure control). Overall, this would lead to an improvement in clinical care for patients with AF.

Psychophysiological data-driven multi-feature information fusion and recognition of miner fatigue in high-altitude and cold areas

Fatigue-induced human error is a leading cause of accidents. The purpose of this exploratory study in China was to perform field tests to measure fatigue psychophysiological parameters, such as electrocardiography (ECG), electromyography (EMG), pulse, blood pressure, reaction time and vital capacity (VC), in miners in high-altitude and cold areas and to perform multi-feature information fusion and fatigue identification. Forty-five miners were randomly selected as subjects for a field test, and feature signals were extracted from 90 psychophysiological features as basic signals for fatigue analysis. Fatigue sensitivity indices were obtained by Pearson correlation analysis, t-test and receiver operating characteristic (ROC) curve performance evaluation. The ECG time-domain, ECG frequency-domain, EMG, VC, systolic blood pressure (SBP), and pulse were significantly different after miner fatigue. The support vector machine (SVM) and random forest (RF) techniques were used to classify and identify fatigue by information fusion and factor combination. The optimal fatigue classification factors were ECG-FD (CV Accuracy = 85.0%) and EMG (CV Accuracy = 90.0%). The optimal combination of factors was ECG-TD + ECG-FD + EMG (CV accuracy = 80.0%). Furthermore, SVM machine learning had a good recognition effect. This study shows that SVM and RF can effectively identify miner fatigue based on fatigue-related factor combinations. ECG-FD and EMG are the best indicators of fatigue, and the best performance and robustness are obtained with three-factor combination classification. This study on miner fatigue identification provides a reference for research on clinical medicine and the identification of human fatigue under high-altitude, cold and low-oxygen conditions.

A SCALABLE HYBRID MODEL FOR ATRIAL FIBRILLATION DETECTION

In this work, a scalable hybrid model is proposed for the purpose of screening and continuous monitoring of atrial fibrillation (AF) using electrocardiogram (ECG) signals collected from wearable ECG devices. The time series of RR intervals (with units in seconds) extracted from the ECG signal is fed into a recurrent neural network (RNN), and the bandpass filtered and scaled signal itself is fed into a convolutional neural network (CNN). At the post-processing stage, these two predictions are merged. An additional logistic regression model using statistical features of “pseudo” PR interval sequence is applied to aid making the final prediction. The proposed model is trained and validated on several datasets from PhysioNet and achieves a precision of 98.28% and a specificity of 99.82% on a dataset collected from several PhysioNet databases. This hybrid model has already been deployed through a WeChat applet, providing services those using wearable ECG devices, thus helping the screening and continuous out-of-hospital monitoring of the disease of AF.

Automated Atrial Fibrillation Detection Based on Feature Fusion Using Discriminant Canonical Correlation Analysis

Atrial fibrillation (AF) is one of the most common cardiovascular diseases, with a high disability rate and mortality rate. The early detection and treatment of atrial fibrillation have great clinical significance. In this paper, a multiple feature fusion is proposed to screen out AF recordings from single lead short electrocardiogram (ECG) recordings. The proposed method uses discriminant canonical correlation analysis (DCCA) feature fusion. It fully takes intraclass correlation and interclass correlation into consideration and solves the problem of computation and information redundancy with simple series or parallel feature fusion. The DCCA integrates traditional features extracted by expert knowledge and deep learning features extracted by the residual network and gated recurrent unit network to improve the low accuracy of a single feature. Based on the Cardiology Challenge 2017 dataset, the experiments are designed to verify the effectiveness of the proposed algorithm. In the experiments, the F1 index can reach 88%. The accuracy, sensitivity, and specificity are 91.7%, 90.4%, and 93.2%, respectively.

Deep convolutional neural network for the automated detection of Subthalamic nucleus using MER signals

BACKGROUND

Deep brain stimulation (DBS) surgery has been extensively conducted for treating advanced Parkinson's disease (PD) patient's symptoms. DBS hinges on the localization of the subthalamic nucleus (STN) in which a permanent electrode should be accurately placed to produce electrical current. Microelectrode recording (MER) signals are routinely recorded in the procedure of DBS surgery to validate the planned trajectories. However, manual MER signals interpretation with the goal of detecting STN borders requires expertise and prone to inter-observer variability. Therefore, a computerized aided system would be beneficial to automatic detection of the dorsal and ventral borders of the STN in MER.

NEW METHOD

In this study, a new deep learning model based on convolutional neural system for automatic delineation of the neurophysiological borders of the STN along the electrode trajectory was developed.

COMPARISON WITH EXISTING METHODS

The proposed model does not involve any conventional standardization, feature extraction or selection steps.

RESULTS

Promising results of 98.67% accuracy, 99.03% sensitivity, 98.11% specificity, 98.79% precision and 98.91% F1-score for subject based testing were achieved using the proposed convolutional neural network (CNN) model.

CONCLUSIONS

This is the first study on the analysis of MER signals to detect STN using deep CNN. Traditional machine learning (ML) algorithms are often cumbersome and suffer from subjective evaluation. Though, the developed 10-layered CNN model has the capability of extracting substantial features at the convolution stage. Hence, the proposed model has the potential to deliver high performance on STN region detection which shows perspective in aiding the neurosurgeon intraoperatively.

Development and Validation of an Automated Algorithm to Detect Atrial Fibrillation Within Stored Intensive Care Unit Continuous Electrocardiographic Data: Observational Study

Background

Atrial fibrillation (AF) is the most common arrhythmia during critical illness, representing a sepsis-defining cardiac dysfunction associated with adverse outcomes. Large burdens of premature beats and noisy signal during sepsis may pose unique challenges to automated AF detection.

Objective

The objective of this study is to develop and validate an automated algorithm to accurately identify AF within electronic health care data among critically ill patients with sepsis.

Methods

This is a retrospective cohort study of patients hospitalized with sepsis identified from Medical Information Mart for Intensive Care (MIMIC III) electronic health data with linked electrocardiographic (ECG) telemetry waveforms. Within 3 separate cohorts of 50 patients, we iteratively developed and validated an automated algorithm that identifies ECG signals, removes noise, and identifies irregular rhythm and premature beats in order to identify AF. We compared the automated algorithm to current methods of AF identification in large databases, including ICD-9 (International Classification of Diseases, 9th edition) codes and hourly nurse annotation of heart rhythm. Methods of AF identification were tested against gold-standard manual ECG review.

Results

AF detection algorithms that did not differentiate AF from premature atrial and ventricular beats performed modestly, with 76% (95% CI 61%-87%) accuracy. Performance improved (P=.02) with the addition of premature beat detection (validation set accuracy: 94% [95% CI 83%-99%]). Median time between automated and manual detection of AF onset was 30 minutes (25th-75th percentile 0-208 minutes). The accuracy of ICD-9 codes (68%; P=.002 vs automated algorithm) and nurse charting (80%; P=.02 vs algorithm) was lower than that of the automated algorithm.

Conclusions

An automated algorithm using telemetry ECG data can feasibly and accurately detect AF among critically ill patients with sepsis, and represents an improvement in AF detection within large databases.

Artificial intelligence for a personalized diagnosis and treatment of atrial fibrillation

Although atrial fibrillation (AF) is the most common cardiac arrhythmia, its early identification, diagnosis, and treatment is still challenging. Due to its heterogeneous mechanisms and risk factors, targeting an individualized treatment of AF demands a large amount of patient data to identify specific patterns. Artificial intelligence (AI) algorithms are particularly well suited for treating high-dimensional data, predicting outcomes, and eventually, optimizing strategies for patient management. The analysis of large patient samples combining different sources of information such as blood biomarkers, electrical signals, and medical images opens a new paradigm for improving diagnostic algorithms. In this review, we summarize suitable AI techniques for this purpose. In particular, we describe potential applications for understanding the structural and functional bases of the disease, as well as for improving early noninvasive diagnosis, developing more efficient therapies, and predicting long-term clinical outcomes of patients with AF.

Hybrid Decision Support to Monitor Atrial Fibrillation for Stroke Prevention

In this paper, we discuss hybrid decision support to monitor atrial fibrillation for stroke prevention. Hybrid decision support takes the form of human experts and machine algorithms working cooperatively on a diagnosis. The link to stroke prevention comes from the fact that patients with Atrial Fibrillation (AF) have a fivefold increased stroke risk. Early diagnosis, which leads to adequate AF treatment, can decrease the stroke risk by 66% and thereby prevent stroke. The monitoring service is based on Heart Rate (HR) measurements. The resulting signals are communicated and stored with Internet of Things (IoT) technology. A Deep Learning (DL) algorithm automatically estimates the AF probability. Based on this technology, we can offer four distinct services to healthcare providers: (1) universal access to patient data; (2) automated AF detection and alarm; (3) physician support; and (4) feedback channels. These four services create an environment where physicians can work symbiotically with machine algorithms to establish and communicate a high quality AF diagnosis.

Over-fitting suppression training strategies for deep learning-based atrial fibrillation detection

Nowadays, deep learning-based models have been widely developed for atrial fibrillation (AF) detection in electrocardiogram (ECG) signals. However, owing to the inevitable over-fitting problem, classification accuracy of the developed models severely differed when applying on the independent test datasets. This situation is more significant for AF detection from dynamic ECGs. In this study, we explored two potential training strategies to address the over-fitting problem in AF detection. The first one is to use the Fast Fourier transform (FFT) and Hanning-window-based filter to suppress the influence from individual difference. Another is to train the model on the wearable ECG data to improve the robustness of model. Wearable ECG data from 29 patients with arrhythmia were collected for at least 24 h. To verify the effectiveness of the training strategies, a Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN)-based model was proposed and tested. We tested the model on the independent wearable ECG data set, as well as the MIT-BIH Atrial Fibrillation database and PhysioNet/Computing in Cardiology Challenge 2017 database. The model achieved 96.23%, 95.44%, and 95.28% accuracy rates on the three databases, respectively. Pertaining to the comparison of the accuracy rates on each training set, the accuracy of the model trained in conjunction with the proposed training strategies only reduced by 2%, while the accuracy of the model trained without the training strategies decreased by approximately 15%. Therefore, the proposed training strategies serve as effective mechanisms for devising a robust AF detector and significantly enhanced the detection accuracy rates of the resulting deep networks.

Addressing Noise and Skewness in Interpretable Health-Condition Assessment by Learning Model Confidence

Assessing the health condition has a wide range of applications in healthcare, military, aerospace, and industrial fields. Nevertheless, traditional feature-engineered techniques involve manual feature extraction, which are too cumbersome to adapt to the changes caused by the development of sensor network technology. Recently, deep-learning-based methods have achieved initial success in health-condition assessment research, but insufficient considerations for problems such as class skewness, noisy segments, and result interpretability make it difficult to apply them to real-world applications. In this paper, we propose a K-margin-based Interpretable Learning approach for health-condition assessment. In detail, a skewness-aware RCR-Net model is employed to handle problems of class skewness. Furthermore, we present a diagnosis model based on K-margin to automatically handle noisy segments by naturally exploiting expected consistency among the segments associated with each record. Additionally, a knowledge-directed interpretation method is presented to learn domain knowledge-level features automatically without the help of human experts which can be used as an interpretable decision-making basis. Finally, through experimental validation in the field of both medical and aerospace, the proposed method has a better generality and high efficiency with 0.7974 and 0.8005 F1 scores, which outperform all state-of-the-art deep learning methods for health-condition assessment task by 3.30% and 2.99%, respectively.

Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling

Recognizing specific heart sound patterns is important for the diagnosis of structural heart diseases. However, the correct recognition of heart murmur depends largely on clinical experience. Accurately identifying abnormal heart sound patterns is challenging for young and inexperienced clinicians. This study is aimed at the development of a novel algorithm that can automatically recognize systolic murmurs in patients with ventricular septal defects (VSDs). Heart sounds from 51 subjects with VSDs and 25 subjects without a significant heart malformation were obtained in this study. Subsequently, the soundtracks were divided into different training and testing sets to establish the recognition system and evaluate the performance. The automatic murmur recognition system was based on a novel temporal attentive pooling-convolutional recurrent neural network (TAP-CRNN) model. On analyzing the performance using the test data that comprised 178 VSD heart sounds and 60 normal heart sounds, a sensitivity rate of 96.0% was obtained along with a specificity of 96.7%. When analyzing the heart sounds recorded in the second aortic and tricuspid areas, both the sensitivity and specificity were 100%. We demonstrated that the proposed TAP-CRNN system can accurately recognize the systolic murmurs of VSD patients, showing promising potential for the development of software for classifying the heart murmurs of several other structural heart diseases.

Remote Atrial Fibrillation Burden Estimation Using Deep Recurrent Neural Network

OBJECTIVE

The atrial fibrillation burden (AFB) is defined as the percentage of time spent in atrial fibrillation (AF) over a long enough monitoring period. Recent research has suggested the added prognostic value of using the AFB compared to a binary diagnosis. We evaluate, for the first time, the ability to estimate the AFB over long-term continuous recordings, using a deep recurrent neutral network (DRNN) approach.

METHODS

The models were developed and evaluated on a large database of p = 2,891 patients, totaling t = 68,800 hours of continuous electrocardiography (ECG) recordings from the University of Virginia. Specifically, 24h beat-to-beat time series were obtained from a single portable ECG channel. The network, denoted ArNet, was benchmarked against a gradient boosting (XGB) model, trained on 21 features including the coefficient of sample entropy (CosEn) and AFEvidence that is derived from the number of irregular points revealed by the Lorenz plot. The generalizations of ArNet and XGB were also evaluated on the independent PhysioNet LTAF test database.

RESULTS

the absolute AF burden estimation error [Formula: see text], median and interquartile, on the test set, was 1.2 (0.1-6.7) for ArNet and 2.8 (0.9-11.7) for XGB for AF individuals. Generalization results on LTAF were consistent with [Formula: see text] of 2.7 (1.1-14.7) for ArNet and 3.6 (1.0-16.7) for XGB.

CONCLUSION

This research demonstrates the feasibility of AFB estimation from 24h beat-to-beat interval time series utilizing DRNNs.

SIGNIFICANCE

The novel data-driven approach enables robust remote diagnosis and phenotyping of AF.

Linear and nonlinear analyses of normal and fatigue heart rate variability signals for miners in high-altitude and cold areas

BACKGROUND AND OBJECTIVE

Fatigue is an important cause of operational errors, and human errors are the main cause of accidents. This study is an exploratory study in China. Field tests were conducted on heart rate variability (HRV) parameters and physiological indicators of fatigue among miners in high-altitude, cold and low-oxygen areas. This paper studies heart activity patterns during work fatigue in miners.

METHODS

Fatigue affects both the sympathetic and parasympathetic nervous systems, and it is expressed as an abnormal pattern of HRV parameters. Thirty miners were selected as subjects for a field test, and HRV was extracted from 60 groups of electrocardiography (ECG) datasets as basic signals for fatigue analysis. Then, we analyzed the HRV signals of the miners using linear (time domain and frequency domain) and nonlinear dynamics (Poincaré plot and sample entropy (SampEn)), and a Pearson's correlation coefficient analysis and t-tests were performed on the measured indices.

RESULTS

The results showed that the time-domain indices (SDNN, RMSSD, SDSD, pNN50, RRn, heart rate (HR), R-wave humps (RH)) and the coefficient of variation (CV)) and the frequency-domain indices (low frequency/high frequency (LF/HF), LFnorm and HFnorm) clearly changed after fatigue. These features were selected using a Poincaré plot, sample entropy, Pearson's correlation coefficient and a t-test for further analysis. The fatigue characteristics and sensitivity parameters of miners in a high-altitude, cold and hypoxic environment were obtained.

CONCLUSIONS

This study provides deep insight into the use of linear and nonlinear fatigue characteristics to effectively and reliably identify miner fatigue. Furthermore, the study provides a reference for clinical studies of acute mountain sickness in high-altitude, cold and hypoxic environments.

A Smart Service Platform for Cost Efficient Cardiac Health Monitoring

AIM

In this study we have investigated the problem of cost effective wireless heart health monitoring from a service design perspective.

SUBJECT AND METHODS

There is a great medical and economic need to support the diagnosis of a wide range of debilitating and indeed fatal non-communicable diseases, like Cardiovascular Disease (CVD), Atrial Fibrillation (AF), diabetes, and sleep disorders. To address this need, we put forward the idea that the combination of Heart Rate (HR) measurements, Internet of Things (IoT), and advanced Artificial Intelligence (AI), forms a Heart Health Monitoring Service Platform (HHMSP). This service platform can be used for multi-disease monitoring, where a distinct service meets the needs of patients having a specific disease. The service functionality is realized by combining common and distinct modules. This forms the technological basis which facilitates a hybrid diagnosis process where machines and practitioners work cooperatively to improve outcomes for patients.

RESULTS

Human checks and balances on independent machine decisions maintain safety and reliability of the diagnosis. Cost efficiency comes from efficient signal processing and replacing manual analysis with AI based machine classification. To show the practicality of the proposed service platform, we have implemented an AF monitoring service.

CONCLUSION

Having common modules allows us to harvest the economies of scale. That is an advantage, because the fixed cost for the infrastructure is shared among a large group of customers. Distinct modules define which AI models are used and how the communication with practitioners, caregivers and patients is handled. That makes the proposed HHMSP agile enough to address safety, reliability and functionality needs from healthcare providers.

Profiling of pornography addiction among children using EEG signals: A systematic literature review

Nowadays human behavior has been affected with the advent of new digital technologies. Due to the rampant use of the Internet by children, many have been addicted to pornography. This addiction has negatively affected the behaviors of children including increased impulsiveness, learning ability to attention, poor decision-making, memory problems, and deficit in emotion regulation. The children with porn addiction can be identified by parents and medical practitioners as third-party observers. This systematic literature review (SLR) is conducted to increase the understanding of porn addiction using electroencephalogram (EEG) signals. We have searched five different databases namely IEEE, ACM, Science Direct, Springer and National Center for Biotechnology Information (NCBI) using addiction, porn, and EEG as keywords along with 'OR 'operation in between the expressions. We have selected 46 studies in this work by screening 815,554 papers from five databases. Our results show that it is possible to identify children with porn addiction using EEG signals.

Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review

BACKGROUND

The electrocardiogram (ECG) is one of the most commonly used diagnostic tools in medicine and healthcare. Deep learning methods have achieved promising results on predictive healthcare tasks using ECG signals.

OBJECTIVE

This paper presents a systematic review of deep learning methods for ECG data from both modeling and application perspectives.

METHODS

We extracted papers that applied deep learning (deep neural network) models to ECG data that were published between January 1st of 2010 and February 29th of 2020 from Google Scholar, PubMed, and the Digital Bibliography & Library Project. We then analyzed each article according to three factors: tasks, models, and data. Finally, we discuss open challenges and unsolved problems in this area.

RESULTS

The total number of papers extracted was 191. Among these papers, 108 were published after 2019. Different deep learning architectures have been used in various ECG analytics tasks, such as disease detection/classification, annotation/localization, sleep staging, biometric human identification, and denoising.

CONCLUSION

The number of works on deep learning for ECG data has grown explosively in recent years. Such works have achieved accuracy comparable to that of traditional feature-based approaches and ensembles of multiple approaches can achieve even better results. Specifically, we found that a hybrid architecture of a convolutional neural network and recurrent neural network ensemble using expert features yields the best results. However, there are some new challenges and problems related to interpretability, scalability, and efficiency that must be addressed. Furthermore, it is also worth investigating new applications from the perspectives of datasets and methods.

SIGNIFICANCE

This paper summarizes existing deep learning research using ECG data from multiple perspectives and highlights existing challenges and problems to identify potential future research directions.

Automatic Detection of Atrial Fibrillation Based on CNN-LSTM and Shortcut Connection

Atrial fibrillation (AF) is one of the most common persistent arrhythmias, which has a close connection to a large number of cardiovascular diseases. However, if spotted early, the diagnosis of AF can improve the effectiveness of clinical treatment and effectively prevent serious complications. In this paper, a combination of an 8-layer convolutional neural network (CNN) with a shortcut connection and 1-layer long short-term memory (LSTM), named 8CSL, was proposed for the Electrocardiogram (ECG) classification task. Compared with recurrent neural networks (RNN) and multi-scale convolution neural networks (MCNN), not only can 8CSL extract features skillfully, but also deal with long-term dependency between data. In particular, 8CSL includes eight shortcut connections that can improve the speed of the data transmission and processing as a result of the shortcut connections. The model was evaluated on the base of the test set of the Computing in Cardiology Challenge 2017 dataset with the F1 score. The ECG recordings were cropped or padded to the same length. After 10-fold cross-validation, the average test F1 score was 84.89%, 89.55%, and 85.64% when the segment length was 5, 10, 20 s, respectively. The experiment results demonstrate excellent performance with potential practical applications.

SS-SWT and SI-CNN: An Atrial Fibrillation Detection Framework for Time-Frequency ECG Signal

Atrial fibrillation is the most common arrhythmia and is associated with high morbidity and mortality from stroke, heart failure, myocardial infarction, and cerebral thrombosis. Effective and rapid detection of atrial fibrillation is critical to reducing morbidity and mortality in patients. Screening atrial fibrillation quickly and efficiently remains a challenging task. In this paper, we propose SS-SWT and SI-CNN: an atrial fibrillation detection framework for the time-frequency ECG signal. First, specific-scale stationary wavelet transform (SS-SWT) is used to decompose a 5-s ECG signal into 8 scales. We select specific scales of coefficients as valid time-frequency features and abandon the other coefficients. The selected coefficients are fed to the scale-independent convolutional neural network (SI-CNN) as a two-dimensional (2D) matrix. In SI-CNN, a convolution kernel specifically for the time-frequency characteristics of ECG signals is designed. During the convolution process, the independence between each scale of coefficient is preserved, and the time domain and the frequency domain characteristics of the ECG signal are effectively extracted, and finally the atrial fibrillation signal is quickly and accurately identified. In this study, experiments are performed using the MIT-BIH AFDB data in 5-s data segments. We achieve 99.03% sensitivity, 99.35% specificity, and 99.23% overall accuracy. The SS-SWT and SI-CNN we propose simplify the feature extraction step, effectively extracts the features of ECG, and reduces the feature redundancy that may be caused by wavelet transform. The results shows that the method can effectively detect atrial fibrillation signals and has potential in clinical application.

A Review of Atrial Fibrillation Detection Methods as a Service

Atrial Fibrillation (AF) is a common heart arrhythmia that often goes undetected, and even if it is detected, managing the condition may be challenging. In this paper, we review how the RR interval and Electrocardiogram (ECG) signals, incorporated into a monitoring system, can be useful to track AF events. Were such an automated system to be implemented, it could be used to help manage AF and thereby reduce patient morbidity and mortality. The main impetus behind the idea of developing a service is that a greater data volume analyzed can lead to better patient outcomes. Based on the literature review, which we present herein, we introduce the methods that can be used to detect AF efficiently and automatically via the RR interval and ECG signals. A cardiovascular disease monitoring service that incorporates one or multiple of these detection methods could extend event observation to all times, and could therefore become useful to establish any AF occurrence. The development of an automated and efficient method that monitors AF in real time would likely become a key component for meeting public health goals regarding the reduction of fatalities caused by the disease. Yet, at present, significant technological and regulatory obstacles remain, which prevent the development of any proposed system. Establishment of the scientific foundation for monitoring is important to provide effective service to patients and healthcare professionals.