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

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

The adaptability of heart to external and internal stimuli is reflected by the heart rate variability (HRV). Reduced HRV can be a predictor of negative cardiovascular outcomes. Based on the nonlinear, nonstationary, and highly complex dynamics of the controlling mechanism of the cardiovascular system, linear HRV measures have limited capability to accurately analyze the underlying dynamics. In this study, we propose an automated system to analyze HRV signals by extracting multimodal features to capture temporal, spectral, and complex dynamics. Robust machine learning techniques, such as support vector machine (SVM) with its kernel (linear, Gaussian, radial base function, and polynomial), decision tree (DT), k-nearest neighbor (KNN), and ensemble classifiers, were employed to evaluate the detection performance. Performance was evaluated in terms of specificity, sensitivity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC). The highest performance was obtained using SVM linear kernel (TA = 93.1%, AUC = 0.97, 95% CI [lower bound = 0.04, upper bound = 0.89]), followed by ensemble subspace discriminant (TA = 91.4%, AUC = 0.96, 95% CI [lower bound 0.07, upper bound = 0.81]) and SVM medium Gaussian kernel (TA = 90.5%, AUC = 0.95, 95% CI [lower bound = 0.07, upper bound = 0.86]). The results reveal that the proposed approach can provide an effective and computationally efficient tool for automatic detection of congestive heart failure patients.

/pdf/detecting-congestive-heart-failure-by-extracting-multimodal-7pdh6djz0i.pdf

Detecting Congestive Heart Failure by Extracting Multimodal Features and Employing Machine Learning Techniques.

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

Representation learning is a key issue for most Natural Language Processing (NLP) tasks. Most existing representation models either learn little structure information or just rely on pre-defined structures, leading to degradation of performance and generalization capability. This paper focuses on learning both local semantic and global structure representations for text classification. In detail, we propose a novel Sandwich Neural Network (SNN) to learn semantic and structure representations automatically without relying on parsers. More importantly, semantic and structure information contribute unequally to the text representation at corpus and instance level. To solve the fusion problem, we propose two strategies: Adaptive Learning Sandwich Neural Network (AL-SNN) and Self-Attention Sandwich Neural Network (SA-SNN). The former learns the weights at corpus level, and the latter further combines attention mechanism to assign the weights at instance level. Experimental results demonstrate that our approach achieves competitive performance on several text classification tasks, including sentiment analysis, question type classification and subjectivity classification. Specifically, the accuracies are MR (82.1%), SST-5 (50.4%), TREC (96%) and SUBJ (93.9%).

Adaptive Learning of Local Semantic and Global Structure Representations for Text Classification

In this paper, we present HoloBoard, an interactive large-format pseudo-holographic display system for lecture-based classes. With its unique properties of immersive visual display and transparent screen, we designed and implemented a rich set of novel interaction techniques like immersive presentation, role-play, and lecturing behind the scene that is potentially valuable for lecturing in class. We conducted a controlled experimental study to compare a HoloBoard class with a normal class by measuring students' learning outcomes and three dimensions of engagement (i.e., behavioral, emotional, and cognitive engagement). We used pre-/post- knowledge tests and multimodal learning analytics to measure students' learning outcomes and learning experiences. Results indicated that the lecture-based class utilizing HoloBoard lead to slightly better learning outcomes and a significantly higher level of student engagement. Given the results, we discussed the impact of HoloBoard as an immersive media in the classroom setting and suggest several design implications for deploying HoloBoard in immersive teaching practices.

HoloBoard: a Large-format Immersive Teaching Board based on pseudo HoloGraphics.

In this paper, we present HoloBoard, an interactive large-format pseduo-holographic display system for lecture based classes. With its unique properties of immersive visual display and transparent screen, we designed and implemented a rich set of novel interaction techniques like immersive presentation, role-play, and lecturing behind the scene that are potentially valuable for lecturing in class. We conducted a controlled experimental study to compare a HoloBoard class with a normal class through measuring students’ learning outcomes and three dimensions of engagement (i.e., behavioral, emotional, and cognitive engagement). We used pre-/post- knowledge tests and multimodal learning analytics to measure students’ learning outcomes and learning experiences. Results indicated that the lecture-based class utilizing HoloBoard lead to slightly better learning outcomes and a significantly higher level of student engagement. Given the results, we discussed the impact of HoloBoard as an immersive media in the classroom setting and suggest several design implications for deploying HoloBoard in immersive teaching practices.

Liuxin Zhang

Papers

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

Adaptive Learning of Local Semantic and Global Structure Representations for Text Classification

HoloBoard: a Large-format Immersive Teaching Board based on pseudo HoloGraphics.

HoloBoard: a Large-format Immersive Teaching Board based on pseudo HoloGraphics

Grabbing the Long Tail: A data normalization method for diverse and informative dialogue generation