1
|
Zhang A, Yang X, Li T, Dou M, Yang H. Classification Method of ECG Signals Based on RANet. Cardiovasc Eng Technol 2024:10.1007/s13239-024-00730-5. [PMID: 38653933 DOI: 10.1007/s13239-024-00730-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Accepted: 04/05/2024] [Indexed: 04/25/2024]
Abstract
BACKGROUND Electrocardiograms (ECG) are an important source of information on human heart health and are widely used to detect different types of arrhythmias. OBJECTIVE With the advancement of deep learning, end-to-end ECG classification models based on neural networks have been developed. However, deeper network layers lead to gradient vanishing. Moreover, different channels and periods of an ECG signal hold varying significance for identifying different types of ECG abnormalities. METHODS To solve these two problems, an ECG classification method based on a residual attention neural network is proposed in this paper. The residual network (ResNet) is used to solve the gradient vanishing problem. Moreover, it has fewer model parameters, and its structure is simpler. An attention mechanism is added to focus on key information, integrate channel features, and improve voting methods to alleviate the problem of data imbalance. RESULTS Experiments and verifications are conducted using the PhysioNet/CinC Challenge 2017 dataset. The average F1 value is 0.817, which is 0.064 higher than that for the ResNet model. Compared with the mainstream methods, the performance is excellent.
Collapse
Affiliation(s)
- Aoxiang Zhang
- Faculty of Information, Beijing University of Technology, Beijing, China
| | - Xinwu Yang
- Faculty of Information, Beijing University of Technology, Beijing, China.
| | - Tong Li
- Faculty of Information, Beijing University of Technology, Beijing, China
| | - Mengfei Dou
- Faculty of Information, Beijing University of Technology, Beijing, China
| | - Hongxiao Yang
- Faculty of Information, Beijing University of Technology, Beijing, China
| |
Collapse
|
2
|
Mandala S, Rizal A, Adiwijaya, Nurmaini S, Suci Amini S, Almayda Sudarisman G, Wen Hau Y, Hanan Abdullah A. An improved method to detect arrhythmia using ensemble learning-based model in multi lead electrocardiogram (ECG). PLoS One 2024; 19:e0297551. [PMID: 38593145 PMCID: PMC11003640 DOI: 10.1371/journal.pone.0297551] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2023] [Accepted: 01/09/2024] [Indexed: 04/11/2024] Open
Abstract
Arrhythmia is a life-threatening cardiac condition characterized by irregular heart rhythm. Early and accurate detection is crucial for effective treatment. However, single-lead electrocardiogram (ECG) methods have limited sensitivity and specificity. This study propose an improved ensemble learning approach for arrhythmia detection using multi-lead ECG data. Proposed method, based on a boosting algorithm, namely Fine Tuned Boosting (FTBO) model detects multiple arrhythmia classes. For the feature extraction, introduce a new technique that utilizes a sliding window with a window size of 5 R-peaks. This study compared it with other models, including bagging and stacking, and assessed the impact of parameter tuning. Rigorous experiments on the MIT-BIH arrhythmia database focused on Premature Ventricular Contraction (PVC), Atrial Premature Contraction (PAC), and Atrial Fibrillation (AF) have been performed. The results showed that the proposed method achieved high sensitivity, specificity, and accuracy for all three classes of arrhythmia. It accurately detected Atrial Fibrillation (AF) with 100% sensitivity and specificity. For Premature Ventricular Contraction (PVC) detection, it achieved 99% sensitivity and specificity in both leads. Similarly, for Atrial Premature Contraction (PAC) detection, proposed method achieved almost 96% sensitivity and specificity in both leads. The proposed method shows great potential for early arrhythmia detection using multi-lead ECG data.
Collapse
Affiliation(s)
- Satria Mandala
- Human Centric (HUMIC) Engineering, Telkom University, Bandung, Indonesia
- School of Computing, Telkom University, Bandung, Indonesia
| | - Ardian Rizal
- Department of Cardiology and Vascular Medicine, Faculty of Medicine, Universitas Brawijaya, Malang, East Java, Indonesia
| | - Adiwijaya
- Human Centric (HUMIC) Engineering, Telkom University, Bandung, Indonesia
- School of Computing, Telkom University, Bandung, Indonesia
| | - Siti Nurmaini
- Intelligent System Research Group, Universitas Sriwijaya, Palembang, South Sumatra, Indonesia
| | | | | | - Yuan Wen Hau
- IJN-UTM Cardiovascular Engineering Centre, Faculty of Electrical Engineering, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia
| | - Abdul Hanan Abdullah
- Human Centric (HUMIC) Engineering, Telkom University, Bandung, Indonesia
- Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Johor, Malaysia
| |
Collapse
|
3
|
Huang Y, Li H, Yu X. A novel time representation input based on deep learning for ECG classification. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2023.104628] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/16/2023]
|
4
|
Jekova I, Christov I, Krasteva V. Atrioventricular Synchronization for Detection of Atrial Fibrillation and Flutter in One to Twelve ECG Leads Using a Dense Neural Network Classifier. SENSORS (BASEL, SWITZERLAND) 2022; 22:6071. [PMID: 36015834 PMCID: PMC9413391 DOI: 10.3390/s22166071] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Revised: 08/10/2022] [Accepted: 08/10/2022] [Indexed: 06/01/2023]
Abstract
This study investigates the use of atrioventricular (AV) synchronization as an important diagnostic criterion for atrial fibrillation and flutter (AF) using one to twelve ECG leads. Heart rate, lead-specific AV conduction time, and P-/f-wave amplitude were evaluated by three representative ECG metrics (mean value, standard deviation), namely RR-interval (RRi-mean, RRi-std), PQ-interval (PQi-mean, PQI-std), and PQ-amplitude (PQa-mean, PQa-std), in 71,545 standard 12-lead ECG records from the six largest PhysioNet CinC Challenge 2021 databases. Two rhythm classes were considered (AF, non-AF), randomly assigning records into training (70%), validation (20%), and test (10%) datasets. In a grid search of 19, 55, and 83 dense neural network (DenseNet) architectures and five independent training runs, we optimized models for one-lead, six-lead (chest or limb), and twelve-lead input features. Lead-set performance and SHapley Additive exPlanations (SHAP) input feature importance were evaluated on the test set. Optimal DenseNet architectures with the number of neurons in sequential [1st, 2nd, 3rd] hidden layers were assessed for sensitivity and specificity: DenseNet [16,16,0] with primary leads (I or II) had 87.9-88.3 and 90.5-91.5%; DenseNet [32,32,32] with six limb leads had 90.7 and 94.2%; DenseNet [32,32,4] with six chest leads had 92.1 and 93.2%; and DenseNet [128,8,8] with all 12 leads had 91.8 and 95.8%, indicating sensitivity and specificity values, respectively. Mean SHAP values on the entire test set highlighted the importance of RRi-mean (100%), RR-std (84%), and atrial synchronization (40-60%) for the PQa-mean (aVR, I), PQi-std (V2, aVF, II), and PQi-mean (aVL, aVR). Our focus on finding the strongest AV synchronization predictors of AF in 12-lead ECGs would lead to a comprehensive understanding of the decision-making process in advanced neural network classifiers. DenseNet self-learned to rely on a few ECG behavioral characteristics: first, characteristics usually associated with AF conduction such as rapid heart rate, enhanced heart rate variability, and large PQ-interval deviation in V2 and inferior leads (aVF, II); second, characteristics related to a typical P-wave pattern in sinus rhythm, which is best distinguished from AF by the earliest negative P-peak deflection of the right atrium in the lead (aVR) and late positive left atrial deflection in lateral leads (I, aVL). Our results on lead-selection and feature-selection practices for AF detection should be considered for one- to twelve-lead ECG signal processing settings, particularly those measuring heart rate, AV conduction times, and P-/f-wave amplitudes. Performances are limited to the AF diagnostic potential of these three metrics. SHAP value importance can be used in combination with a human expert's ECG interpretation to change the focus from a broad observation of 12-lead ECG morphology to focusing on the few AV synchronization findings strongly predictive of AF or non-AF arrhythmias. Our results are representative of AV synchronization findings across a broad taxonomy of cardiac arrhythmias in large 12-lead ECG databases.
Collapse
|
5
|
Jiang M, Qiu Y, Zhang W, Zhang J, Wang Z, Ke W, Wu Y, Wang Z. Visualization deep learning model for automatic arrhythmias classification. Physiol Meas 2022; 43. [PMID: 35882225 DOI: 10.1088/1361-6579/ac8469] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2022] [Accepted: 07/26/2022] [Indexed: 11/11/2022]
Abstract
With the improvement of living standards, heart disease has become one of the common diseases that threaten human health. As a widely used reliable, non-invasive technology, the Electrocardiography (ECG) data has been increasingly used for diagnosing cardiovascular diseases. With the rapid growth of ECG examinations and the shortage of cardiologists, accurate and automatic recognition of ECG patterns has become a research hotspot. In order to improve the accuracy in detecting abnormal ECG patterns, this paper proposes a hybrid 1D Resnet-GRU consisting of the Resnet and gated recurrent unit (GRU) modules to implement classification of arrhythmias from 12-lead ECG recordings. In addition, the focal Loss function is used to solve the problem of unbalanced datasets. Based on the proposed 1D Resnet-GRU model, the Grad-CAM++ mechanism, one of class-discriminative visualization methods, has been employed to the trained network model and generate thermal images superimposed on raw signals, so as to improve interpretability and transparency for arrhythmia classification. Experimental results show the proposed Resnet-GRU method can improve the F_1 score and accuracy effectively, and Grad-CAM++ can provide interpretability and clinical information for arrhythmia classification.
Collapse
Affiliation(s)
- Mingfeng Jiang
- School of Information Science and Technology, Zhejiang Sci-Tech University, No. 928, 2th street, Hangzhou, China, Hangzhou, Zhejiang, 310018, CHINA
| | - Yujie Qiu
- School of Information Science and Technology, Zhejiang Sci-Tech University, School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China, Hangzhou, Zhejiang, 310018, CHINA
| | - Wei Zhang
- Zhejiang Sci-Tech University, School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China, Hangzhou, Zhejiang, 310018, CHINA
| | - Jucheng Zhang
- Department of Clinical Engineering, Zhejiang University School of Medicine Second Affiliated Hospital, Hangzhou, Zhejiang, Hangzhou, Zhejiang, 310009, CHINA
| | - Zefeng Wang
- Department of Cardiology, Beijing An Zhen Hospital, No. 2 Anzhen Road, Chaoyang District, Beijing 100029, China, Chaoyang-qu, Beijing, 100029, CHINA
| | - Wei Ke
- School of Applied Sciences, Macau Polytechnic Institute, School of Applied Sciences, Macao Polytechnic Institute, Macao SAR 999078, China, Macau, Macau, 999078, CHINA
| | - Yongquan Wu
- Department of Cardiology,, Beijing An Zhen Hospital, No. 2 Anzhen Road, Chaoyang District, Beijing 100029, China, Chaoyang-qu, Beijing, 100029, CHINA
| | - Zhikang Wang
- Zhejiang University School of Medicine Second Affiliated Hospital, Department of Clinical Engineering, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou 310019, China, Hangzhou, Zhejiang, 310009, CHINA
| |
Collapse
|
6
|
A Data-Driven Adaptive Emotion Recognition Model for College Students Using an Improved Multifeature Deep Neural Network Technology. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE 2022; 2022:1343358. [PMID: 35665293 PMCID: PMC9162810 DOI: 10.1155/2022/1343358] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/22/2022] [Revised: 05/11/2022] [Accepted: 05/13/2022] [Indexed: 11/17/2022]
Abstract
With the increasing pressure on college students in terms of study, work, emotion, and life, the emotional changes of college students are becoming more and more obvious. For college student management workers, if they can accurately grasp the emotional state of each college student in all aspects of the whole process, it will be of great help to student management work. The traditional way to understand students’ emotions at a certain stage is mostly through chats, questionnaires, and other methods. However, data collection in this way is time-consuming and labor-intensive, and the authenticity of the collected data cannot be guaranteed because students will lie out of impatience or unwillingness to reveal their true emotions. In order to explore an accurate and efficient emotion recognition method for college students, more objective physiological data are used for emotion recognition research. Since emotion is generated by the central nervous system of the human brain, EEG signals directly reflect the electrophysiological activity of the brain. Therefore, in the field of emotion recognition based on physiological signals, EEG signals are favored due to their ability to intuitively respond to emotions. Therefore, a deep neural network (DNN) is used to classify the collected emotional EEG data and obtain the emotional state of college students according to the classification results. Considering that different features can represent different information of the original data, in order to express the original EEG data information as comprehensively as possible, various features of the EEG are first extracted. Second, feature fusion is performed on multiple features using the autosklearn model integration technique. Third, the fused features are input to the DNN, resulting in the final classification result. The experimental results show that the method has certain advantages in public datasets, and the accuracy of emotion recognition exceeds 88%. This proves the used emotion recognition is feasible to be applied in real life.
Collapse
|
7
|
Cheng J, Zou Q, Zhao Y. ECG signal classification based on deep CNN and BiLSTM. BMC Med Inform Decis Mak 2021; 21:365. [PMID: 34963455 PMCID: PMC8715576 DOI: 10.1186/s12911-021-01736-y] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2021] [Accepted: 12/16/2021] [Indexed: 11/18/2022] Open
Abstract
Background Currently, cardiovascular disease has become a major disease endangering human health, and the number of such patients is growing. Electrocardiogram (ECG) is an important basis for {medical doctors to diagnose the cardiovascular disease, which can truly reflect the health of the heart. In this context, the contradiction between the lack of medical resources and the surge in the number of patients has become increasingly prominent. The use of computer-aided diagnosis of cardiovascular disease has become particularly important, so the study of ECG automatic classification method has a strong practical significance. Methods This article proposes a new method for automatic identification and classification of ECG.We have developed a dense heart rhythm network that combines a 24-layer Deep Convolutional Neural Network (DCNN) and Bidirectional Long Short-Term Memory (BiLSTM) to deeply mine the hierarchical and time-sensitive features of ECG data. Three different sizes of convolution kernels (32, 64 and 128) are used to mine the detailed features of the ECG signal, and the original ECG is filtered using a combination of wavelet transform and median filtering to eliminate the influence of noise on the signal. A new loss function is proposed to control the fluctuation of loss during the training process, and convergence mapping of the tan function in the range of 0–1 is employed to better reflect the model training loss and correct the optimization direction in time. Results We applied the dataset provided by the 2017 PhysioNet/CINC challenge for verification. The experiment adopted ten-fold cross validation,and obtained an accuracy rate of 89.3\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\%$$\end{document}% and an F1 score of 0.891. Conclusions This article proposes its own method in the aspects of ECG data preprocessing, feature extraction and loss function design. Compared with the existing methods, this method improves the accuracy of automatic ECG classification and is helpful for clinical diagnosis and self-monitoring of atrial fibrillation.
Collapse
Affiliation(s)
- Jinyong Cheng
- School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
| | - Qingxu Zou
- School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China
| | - Yunxiang Zhao
- School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China.
| |
Collapse
|
8
|
Katoh T, Yashima M, Takahashi N, Watanabe E, Ikeda T, Kasamaki Y, Sumitomo N, Ueda N, Morita H, Hiraoka M. Expert consensus document on automated diagnosis of the electrocardiogram: The task force on automated diagnosis of the electrocardiogram in Japan: Part 2: Current status of inappropriate automated diagnosis is widely used electrocardiographs in Japan. J Arrhythm 2021; 37:1427-1433. [PMID: 34887946 PMCID: PMC8637077 DOI: 10.1002/joa3.12646] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2021] [Revised: 10/05/2021] [Accepted: 10/05/2021] [Indexed: 11/26/2022] Open
Affiliation(s)
- Takao Katoh
- Clinic of Tobu Railway Co. Ltd.Sumida‐kuJapan
- Nippon Medical School Department of CardiologyBunkyo‐kuJapan
| | - Masaaki Yashima
- Nippon Medical School Department of CardiologyBunkyo‐kuJapan
| | - Naohiko Takahashi
- Oita University Department of Cardiology and Clinical ExaminationYufuJapan
| | | | | | - Yuji Kasamaki
- Kanazawa Medical University Himi Medical CenterHimiJapan
| | - Naokata Sumitomo
- Saitama Medical University International Medical CenterSaitamaJapan
| | - Norihiro Ueda
- Nagoya City University Department of Medical EducationNagoyaJapan
| | - Hiroshi Morita
- Graduate School of Medicine Dentistry and Pharmaceutical SciencesOkayama UniversityOkayamaJapan
| | | |
Collapse
|
9
|
Butkuviene M, Petrenas A, Solosenko A, Martin-Yebra A, Marozas V, Sornmo L. Considerations on Performance Evaluation of Atrial Fibrillation Detectors. IEEE Trans Biomed Eng 2021; 68:3250-3260. [PMID: 33750686 DOI: 10.1109/tbme.2021.3067698] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
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.
Collapse
|
10
|
Krasteva V, Christov I, Naydenov S, Stoyanov T, Jekova I. Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set. SENSORS (BASEL, SWITZERLAND) 2021; 21:6848. [PMID: 34696061 PMCID: PMC8538849 DOI: 10.3390/s21206848] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/14/2021] [Revised: 10/05/2021] [Accepted: 10/13/2021] [Indexed: 11/16/2022]
Abstract
Considering the significant burden to patients and healthcare systems globally related to atrial fibrillation (AF) complications, the early AF diagnosis is of crucial importance. In the view of prominent perspectives for fast and accurate point-of-care arrhythmia detection, our study optimizes an artificial neural network (NN) classifier and ranks the importance of enhanced 137 diagnostic ECG features computed from time and frequency ECG signal representations of short single-lead strips available in 2017 Physionet/CinC Challenge database. Based on hyperparameters' grid search of densely connected NN layers, we derive the optimal topology with three layers and 128, 32, 4 neurons per layer (DenseNet-3@128-32-4), which presents maximal F1-scores for classification of Normal rhythms (0.883, 5076 strips), AF (0.825, 758 strips), Other rhythms (0.705, 2415 strips), Noise (0.618, 279 strips) and total F1 relevant to the CinC Challenge of 0.804, derived by five-fold cross-validation. DenseNet-3@128-32-4 performs equally well with 137 to 32 features and presents tolerable reduction by about 0.03 to 0.06 points for limited input sets, including 8 and 16 features, respectively. The feature reduction is linked to effective application of a comprehensive method for computation of the feature map importance based on the weights of the activated neurons through the total path from input to specific output in DenseNet. The detailed analysis of 20 top-ranked ECG features with greatest importance to the detection of each rhythm and overall of all rhythms reveals DenseNet decision-making process, noticeably corresponding to the cardiologists' diagnostic point of view.
Collapse
Affiliation(s)
- Vessela Krasteva
- Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Acad. G. Bonchev Str. Bl 105, 1113 Sofia, Bulgaria; (V.K.); (I.C.); (T.S.)
| | - Ivaylo Christov
- Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Acad. G. Bonchev Str. Bl 105, 1113 Sofia, Bulgaria; (V.K.); (I.C.); (T.S.)
| | - Stefan Naydenov
- Department of Internal Diseases “Prof. St. Kirkovich”, Medical University of Sofia, 1431 Sofia, Bulgaria;
| | - Todor Stoyanov
- Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Acad. G. Bonchev Str. Bl 105, 1113 Sofia, Bulgaria; (V.K.); (I.C.); (T.S.)
| | - Irena Jekova
- Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Acad. G. Bonchev Str. Bl 105, 1113 Sofia, Bulgaria; (V.K.); (I.C.); (T.S.)
| |
Collapse
|
11
|
Zhang H, Dong Z, Sun M, Gu H, Wang Z. TP-CNN: A Detection Method for atrial fibrillation based on transposed projection signals with compressed sensed ECG. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021; 210:106358. [PMID: 34478912 DOI: 10.1016/j.cmpb.2021.106358] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/29/2021] [Accepted: 08/11/2021] [Indexed: 06/13/2023]
Abstract
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.
Collapse
Affiliation(s)
- Hongpo Zhang
- State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, Henan 450001, China; Cooperative Innovation Center of Internet Healthcare, Zhengzhou University, Zhengzhou, Henan 450001, China.
| | - Zhongren Dong
- Cooperative Innovation Center of Internet Healthcare, Zhengzhou University, Zhengzhou, Henan 450001, China; School of Information Engineering, Zhengzhou University, Zhengzhou, Henan 450001, China.
| | - Mengya Sun
- Cooperative Innovation Center of Internet Healthcare, Zhengzhou University, Zhengzhou, Henan 450001, China; School of Information Engineering, Zhengzhou University, Zhengzhou, Henan 450001, China.
| | - Hongzhuang Gu
- Cooperative Innovation Center of Internet Healthcare, Zhengzhou University, Zhengzhou, Henan 450001, China; School of Information Engineering, Zhengzhou University, Zhengzhou, Henan 450001, China.
| | - Zongmin Wang
- Cooperative Innovation Center of Internet Healthcare, Zhengzhou University, Zhengzhou, Henan 450001, China.
| |
Collapse
|
12
|
Lee H, Shin M. Learning Explainable Time-Morphology Patterns for Automatic Arrhythmia Classification from Short Single-Lead ECGs. SENSORS 2021; 21:s21134331. [PMID: 34202805 PMCID: PMC8272104 DOI: 10.3390/s21134331] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/16/2021] [Revised: 06/17/2021] [Accepted: 06/21/2021] [Indexed: 11/16/2022]
Abstract
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 F1_NAO of 81.75% and F1_NAOP of 76.87%, which are comparable to those of the state-of-the-art methods for variable-length ECGs.
Collapse
|
13
|
Wesselius FJ, van Schie MS, De Groot NMS, Hendriks RC. Digital biomarkers and algorithms for detection of atrial fibrillation using surface electrocardiograms: A systematic review. Comput Biol Med 2021; 133:104404. [PMID: 33951551 DOI: 10.1016/j.compbiomed.2021.104404] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2021] [Revised: 04/12/2021] [Accepted: 04/12/2021] [Indexed: 10/21/2022]
Abstract
AIMS Automated detection of atrial fibrillation (AF) in continuous rhythm registrations is essential in order to prevent complications and optimize treatment of AF. Many algorithms have been developed to detect AF in surface electrocardiograms (ECGs) during the past few years. The aim of this systematic review is to gain more insight into these available classification methods by discussing previously used digital biomarkers and algorithms and make recommendations for future research. METHODS On the 14th of September 2020, the PubMed database was searched for articles focusing on algorithms for AF detection in ECGs using the MeSH terms Atrial Fibrillation, Electrocardiography and Algorithms. Articles which solely focused on differentiation of types of rhythm disorders or prediction of AF termination were excluded. RESULTS The search resulted in 451 articles, of which 130 remained after full-text screening. Not only did the amount of research on methods for AF detection increase over the past years, but a trend towards more complex classification methods is observed. Furthermore, three different types of features can be distinguished: atrial features, ventricular features, and signal features. Although AF is an atrial disease, only 22% of the described methods use atrial features. CONCLUSION More and more studies focus on improving accuracy of classification methods for AF in ECGs. As a result, algorithms become increasingly complex and less well interpretable. Only a few studies focus on detecting atrial activity in the ECG. Developing innovative methods focusing on detection of atrial activity might provide accurate classifiers without compromising on transparency.
Collapse
Affiliation(s)
- Fons J Wesselius
- Department of Cardiology, Erasmus Medical Center, Rotterdam, the Netherlands
| | - Mathijs S van Schie
- Department of Cardiology, Erasmus Medical Center, Rotterdam, the Netherlands
| | | | - Richard C Hendriks
- Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, the Netherlands
| |
Collapse
|
14
|
Automated Atrial Fibrillation Detection Based on Feature Fusion Using Discriminant Canonical Correlation Analysis. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2021; 2021:6691177. [PMID: 33897806 PMCID: PMC8052181 DOI: 10.1155/2021/6691177] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/21/2020] [Revised: 03/05/2021] [Accepted: 03/26/2021] [Indexed: 11/17/2022]
Abstract
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.
Collapse
|
15
|
Cao XC, Yao B, Chen BQ. Atrial Fibrillation Detection Using an Improved Multi-Scale Decomposition Enhanced Residual Convolutional Neural Network. IEEE ACCESS 2019; 7:89152-89161. [DOI: 10.1109/access.2019.2926749] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/01/2023]
|