Deep Learning Based Patient-Specific Classification of Arrhythmia on ECG signal

Hygeia: A Multilabel Deep Learning-Based Classification Method for Imbalanced Electrocardiogram Data

Electrocardiogram (ECG) is a common diagnostic indicator of heart disease in hospitals. Because of the low price and noninvasiveness of ECG diagnosis, it is widely used for prescreening and physical examination of heart diseases. In several studies on ECG analysis, only rough diagnoses are made to determine whether ECGs are abnormal or on a few kinds of ECG. In actual scenarios, doctors must analyze ECG samples in detail, which is a multilabel classification problem. Herein, we propose Hygeia, a multilabel deep learning-based ECG classification method that can analyze and classify 55 types of ECG. First, a guidance model is constructed to transform the multilabel classification problem into multiple interrelated two-classification models. This method ensures the good performance of each ECG analysis model, and the relationship between various types of ECG can be used in the analysis. The imbalance of samples in ECG datasets makes it difficult to analyze abnormal ECGs with high sensitivity and accuracy. We used data generation and mixed sampling methods for 11 ECG types with imbalanced problems to improve the average accuracy, sensitivity, F1 value, and accuracy from 87.74%, 43.11%, 0.3929, and 0.3929, to 92.68%, 96.92, 0.9287, and 99.47%, respectively. The average accuracy, sensitivity, F1 value, and accuracy of 44 of the 55 tags of the abnormal ECG analysis model are 99.69%, 95.81%, 0.9758, and 99.72%, respectively.

1D U-NET++: AN EFFECTIVE METHOD FOR BALLISTOCARDIOGRAM J-PEAK DETECTION

Heart rate measurement through Ballistocardiogram (BCG) signal is an efficient method for long-term cardiac activity monitoring in real-time, especially for patients with cardiovascular and cerebrovascular disease. In this study, we propose a one-dimensional (1D) U-net++ to identify the position of J-peak in BCG signals automatically. The proposed 1D U-net++ is based on a 1D convolution neural network through dense skip connection backward transfer data features. The low-level and high-level data features of the BCG signals are combined with the last layer features of 1D U-net++ to shorten the semantic gap when the encoder and decoder feature skip connection. The BCG signals of eight healthy subjects were collected for experimental verification, and the accuracy and precision of J-peak detection reached 99.4% and 99.3%, respectively. The experimental results demonstrate that our proposed method can effectively identify J-peak in BCG signal.

SUPRAVENTRICULAR TACHYCARDIA CLASSIFICATION USING ATTENTION-BASED RESIDUAL NETWORKS

Atrioventricular nodal reentrant tachycardia (AVNRT) and atrioventricular reentrant tachycardia (AVRT) are two common arrhythmias with high similarity. Automatic electrocardiogram (ECG) detection using machine learning and neural networks has replaced manual detection, but few studies distinguishing AVNRT from AVRT have been reported. This study proposed a classification algorithm using bottleneck attention module (BAM)-based deep residual network (ResNet) through two-lead ECG records. Specifically, ResNet possessed sufficient network depth to extract abundant features, and BAM was introduced to optimize weight assignment of feature maps by fusing together channel and spatial information. Seven types of ECG signals from four public databases were used to pretrain the proposed classification model, which was then fine-tuned using the experimental dataset. The AVNRT and AVRT detection precisions were 98.95% and 87.47%, sensitivities were 87.52% and 98.58%, and the [Formula: see text]1-scores were 92.82% and 92.68%, respectively. These findings showed that our proposed classification model achieved excellent inter-patient classification performance and can assist doctors in the diagnosis of AVNRT and AVRT.

Identification of Arrhythmia by Using a Decision Tree and Gated Network Fusion Model

In recent years, deep learning (DNN) based methods have made leapfrogging level breakthroughs in detecting cardiac arrhythmias as the cost effectiveness of arithmetic power, and data size has broken through the tipping point. However, the inability of these methods to provide a basis for modeling decisions limits clinicians' confidence on such methods. In this paper, a Gate Recurrent Unit (GRU) and decision tree fusion model, referred to as (T-GRU), was designed to explore the problem of arrhythmia recognition and to improve the credibility of deep learning methods. The fusion model multipathway processing time-frequency domain featured the introduction of decision tree probability analysis of frequency domain features, the regularization of GRU model parameters and weight control to improve the decision tree model output weights. The MIT-BIH arrhythmia database was used for validation. Results showed that the low-frequency band features dominated the model prediction. The fusion model had an accuracy of 98.31%, sensitivity of 96.85%, specificity of 98.81%, and precision of 96.73%, indicating its high reliability and clinical significance.

Deep Multi-instance Networks for Bundle Branch Block Detection from Multi-lead ECG

Bundle branch block (BBB) is one of the most common cardiac disorder, and can be detected by electro-cardiogram (ECG) signal in clinical practice. Conventional methods adopted some kinds of hand-craft features, whose discriminative power is relatively low. On the other hand, these methods were based on the supervised learning, which required the high cost heartbeat annotation in the training. In this paper, a novel end-to-end deep network was proposed to classify three types of heartbeat: right BBB (RBBB), left BBB (LBBB) and others with a multiple instance learning based training strategy. We trained the proposed method on the China Physiological Signal Challenge 2018 database (CPSC) and tested on the MIT-BIH Arrhythmia database (AR). The proposed method achieved an accuracy of 78.58%, and sensitivity of 84.78% (LBBB), 51.23% (others) and 99.72% (RBBB), better than the baseline methods. Experimental results show that our method would be a good choice for the BBB classification on the ECG dataset with record-level labels instead of heartbeat annotations.

Deep Learning in Physiological Signal Data: A Survey

Deep Learning (DL), a successful promising approach for discriminative and generative tasks, has recently proved its high potential in 2D medical imaging analysis; however, physiological data in the form of 1D signals have yet to be beneficially exploited from this novel approach to fulfil the desired medical tasks. Therefore, in this paper we survey the latest scientific research on deep learning in physiological signal data such as electromyogram (EMG), electrocardiogram (ECG), electroencephalogram (EEG), and electrooculogram (EOG). We found 147 papers published between January 2018 and October 2019 inclusive from various journals and publishers. The objective of this paper is to conduct a detailed study to comprehend, categorize, and compare the key parameters of the deep-learning approaches that have been used in physiological signal analysis for various medical applications. The key parameters of deep-learning approach that we review are the input data type, deep-learning task, deep-learning model, training architecture, and dataset sources. Those are the main key parameters that affect system performance. We taxonomize the research works using deep-learning method in physiological signal analysis based on: (1) physiological signal data perspective, such as data modality and medical application; and (2) deep-learning concept perspective such as training architecture and dataset sources.