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 Jan. 1st of 2010 and Feb. 29th of 2020 from Google Scholar, PubMed, and the DBLP. 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.

Opportunities and Challenges of Deep Learning Methods for Electrocardiogram Data: A Systematic Review

Obstructive sleep apnea (OSA) is a prevalent sleep disorder and highly affects the quality of human life. Currently, gold standard for OSA detection is polysomnogram. Since this method is time consuming and cost inefficient, practical systems focus on the usage of electrocardiogram (ECG) signals for OSA detection. In this paper, a novel automatic OSA detection method using a single-lead ECG signal has been proposed. A nonlinear feature extraction using wavelet transform (WT) coefficients obtained by an ECG signal decomposition is employed. In addition, different classification methods are investigated. ECG signals are decomposed into eight levels using a Symlet function as a mother Wavelet function with third order. Then, the entropy-based features including fuzzy/approximate/sample/correct conditional entropy as well as other nonlinear features including interquartile range, mean absolute deviation, variance, Poincare plot, and recurrence plot are extracted from WT coefficients. The best features are chosen using the automatic sequential forward feature selection algorithm. In order to assess the introduced method, 95 single-lead ECG recordings are used. The support vector machine classifier having a radial basis function kernel leads to an accuracy of 94.63% (sensitivity: 94.43% and specificity: 94.77%) and 95.71% (sensitivity: 95.83% and specificity: 95.66%) for minute-by-minute and subject-by-subject classifications, respectively. The results show that applying entropy-based features for extracting hidden information of the ECG signals outperforms other available automatic OSA detection methods. The results indicate that a highly accurate OSA detection is attained by just exploiting the single-lead ECG signals. Furthermore, due to the low computational load in the proposed method, it can easily be applied to the home monitoring systems.

Automatic Detection of Obstructive Sleep Apnea Using Wavelet Transform and Entropy-Based Features From Single-Lead ECG Signal

In this study, we propose an automatic system to diagnose congestive heart failure using short-term heart rate variability analysis. The system involves a multi-stage classifier. The features of heart rate variability are computed from time-domain and frequency-domain measures through power spectral density estimations of different transform methods. Nonlinear heart rate variability measures are also calculated by using Poincare plot, symbolic dynamics, detrended fluctuation analysis, and sample entropy. Different combinations of heart rate variability features are selected according to their statistical significance levels and then applied to the classifier. The first two stages of the classifier consist of simple perceptron classifiers that are trained by a genetic algorithm. Five different classifiers, namely k-nearest neighbors, linear discriminant analyses, multilayer perceptron, support vector machines, and radial basis function artificial neuronal network, are tested for the third stage. The proposed system results in a classification performance of an accuracy of 98.8%, specificity of 98.1%, and sensitivity of 100%. We show that our approach provides an effective and computationally efficient tool to automatically diagnose congestive heart failure patients.

Multi-stage classification of congestive heart failure based on short-term heart rate variability

A new automated CNN deep learning approach for identification of ECG congestive heart failure and arrhythmia using constant-Q non-stationary Gabor transform

Congestive heart failure (CHF) is a serious pathophysiological condition with high morbidity and mortality, which is hard to predict and diagnose in early age. Artificial intelligence and deep learning combining with cardiac rhythms and physiological time series provide a potential to help in solving it. In this paper, we proposed a novel method that combines a convolutional neural network (CNN) and a distance distribution matrix (DDM) in entropy calculation to classify CHF patients from normal subjects, and demonstrated the effectiveness of this combination. Specifically, three entropy methods were used to generate the distribution matrixes from a 300-point RR interval (i.e., the time interval between the successive cardiac cycles) time series, which are Sample entropy, fuzzy local measure entropy, and fuzzy global measure entropy. Then, three high representative CNN models, i.e., AlexNet, DenseNet, and SE_Inception_v4 were chosen to learn the pattern of the data distributions hidden in the generated distribution matrixes. All data used in our experiments were gathered from the MIT-BIH RR Interval Databases ( http://www.physionet.org ). A total of 29 CHF patients and 54 normal sinus rhythm subjects were included in this paper. The results showed that the combination of FuzzyGMEn-generated DDM and Inception_v4 model yielded the highest accuracy of 81.85% out of all proposed combinations.

https://northumbria-test.eprints-hosting.org/id/document/267672

Combining Convolutional Neural Network and Distance Distribution Matrix for Identification of Congestive Heart Failure

Renal dysfunction, which is associated with bad clinical outcomes, is one of the most common complications of heart failure (HF). Timely prediction of renal dysfunction can help medical staffs intervene early to avoid catastrophic consequences. In this paper, we proposed a multi-task deep and wide neural network (MT-DWNN) for predicting fatal complications during hospitalization. The algorithm was tested on a dataset collected from Chinese PLA General Hospital, which contains 35,101 hospitalizations with HF diagnosis during the last 18 years, and 2,478 hospitalizations with a diagnosis of renal dysfunction. For the renal dysfunction task, the AUC of the proposed method is 0.9393, which is a significant improvement ($p <; 0.01$ ) compared to that of conventional methods, while that of single task deep neural networks is 0.9370, that of random forest is 0.9360, and that of logistic regression is 0.9233. The experimental results show that the proposed MT-DWNN model achieves better prediction performance on renal dysfunction in HF patients than conventional models.

/pdf/a-multi-task-neural-network-architecture-for-renal-35iv6ujrfh.pdf

A Multi-Task Neural Network Architecture for Renal Dysfunction Prediction in Heart Failure Patients With Electronic Health Records

This study aimed to employ the recently developed fuzzy measure entropy (FuzzyMEn) method to compare the difference in heart rate variability (HRV) between rest and exercise states in hypoxic environment. Four healthy male volunteers were enrolled in this study. For each subject, electrocardiography (ECG) and finger pulse were recorded in ten days to obtain the heart rate (HR) time series. For each day, the measurement lasted 150 min and was divided into six consecutive experimental sections: 3 repeat rest sections (each 30 min) and 3 repeat exercise sections (each 20 min). The repeat rest and repeat exercise sections were in turn. In each rest or exercise section, the segment of HR time series from the second 5 min episode (from the 6th min to the 10th min) was selected for the FuzzyMEn calculation. The effects of subject, day, repeat measurement and state (rest or exercise) on the FuzzyMEn were investigated. The mean FuzzyMEn differences among ten days and between rest and exercise states were also analyzed. Results showed that day and state factors have significant effects on FuzzyMEn (both P

Analysis of Heart Rate Variability between Rest and Exercise States in Hypoxic Environment Using Fuzzy Measure Entropy

In this study, changes in heart rate variability (H RV) induced by exposure to hypoxia were evaluate in healthy male. The sample entropy as a non-linear me thod of HRV analysis was used; it’s a powerful way to analyze biological system. Our aim was to investiga te the influence of stepwise hypoxia on HRV using sample entropy, we tested nine healthy yellow males (age=35± 5) at 3600m, 4000m, 4400m, 4800m during rest, these were a part of the acclimation t est. An increase in sample entropy at high altitude compared to 1000m was established in this research. The parameters showed similar tendencies during different altitude, but not so obvious. The changin g of sample entropy in every day was analyzed. Our results indicate that hypoxia exerts an influence o n HRV; it also suggested that acute exposure to normobaric hypoxia induces increases in sympathetic vasomotor activity and cardiac sympathetic dominance resulting in an increased heart rate.

Impact of hypoxia on heart rate variability based on sample entropy

In the field of computer-aided diagnosis (CAD) and treatment evaluation system on hepatic disease diagnosis, the automatic segmentation of the liver from CT volume is the most basic step. It is a difficult task because the shape of liver could be changed by liver tumor, and the intensity of liver is similar to that of other adjacent tissues. In this paper, we proposed a framework based on the U-net architecture, called dense pyramid network to segment the liver from CT images automatically. The main contribution of our network is that, multiple feature maps from the previous level of hierarchy are combined as the input of each layer in the encoding part. This removes the loss of context information between different layers. The model is trained on practical enhanced CT scans, which are gained from People’s Liberation Army General Hospital (PLA). Experimental results demonstrate that our model can effectively improve the segmentation performance of liver, no matter the different shapes between livers. In the experiment, the Dice score of liver segmentation in the arterial phase, venous phase, and delay phase by dense pyramid network was about 95.97%, 96.22%, and 96.16%, respectively, which shows that our model is more suitable for multi-phase liver segmentation.

Binhua Wang

Papers

Combining Convolutional Neural Network and Distance Distribution Matrix for Identification of Congestive Heart Failure

A Multi-Task Neural Network Architecture for Renal Dysfunction Prediction in Heart Failure Patients With Electronic Health Records

Analysis of Heart Rate Variability between Rest and Exercise States in Hypoxic Environment Using Fuzzy Measure Entropy

Impact of hypoxia on heart rate variability based on sample entropy

Automatic Segmentation of Liver CT Image Based on Dense Pyramid Network.