Intra- and Interpatient ECG Heartbeat Classification Based on Multimodal Convolutional Neural Networks with an Adaptive Attention Mechanism

被引:0
|
作者
Di Paolo, italo Flexa [1 ,2 ]
Castro, Adriana Rosa Garcez [1 ]
机构
[1] Fed Univ Para, Postgrad Program Elect Engn, BR-66075110 Belem, PA, Brazil
[2] Para State Univ, Ctr Nat Sci & Technol, Dept Comp Syst & Infrastructure, BR-67125118 Ananindeua, PA, Brazil
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 20期
关键词
arrhythmia classification; electrocardiogram (ECG); multimodal convolutional neural network (CNN); attention mechanism; ARRHYTHMIA DETECTION; RECURRENCE PLOTS; RECOGNITION; CNN; FUSION;
D O I
10.3390/app14209307
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Echocardiography (ECG) is a noninvasive technology that is widely used for recording heartbeats and diagnosing cardiac arrhythmias. However, interpreting ECG signals is challenging and may require substantial time from medical specialists. The evolution of technology and artificial intelligence has led to advances in the study and development of automatic arrhythmia classification systems to aid in medical diagnoses. Within this context, this paper introduces a framework for classifying cardiac arrhythmias on the basis of a multimodal convolutional neural network (CNN) with an adaptive attention mechanism. ECG signal segments are transformed into images via the Hilbert space-filling curve (HSFC) and recurrence plot (RP) techniques. The framework is developed and evaluated using the MIT-BIH public database in alignment with AAMI guidelines (ANSI/AAMI EC57). The evaluations accounted for interpatient and intrapatient paradigms, considering variations in the input structure related to the number of ECG leads (lead MLII and V1 + MLII). The results indicate that the framework is competitive with those in state-of-the-art studies, particularly for two ECG leads. The accuracy, precision, sensitivity, specificity and F1 score are 98.48%, 94.15%, 80.23%, 96.34% and 81.91%, respectively, for the interpatient paradigm and 99.70%, 98.01%, 97.26%, 99.28% and 97.64%, respectively, for the intrapatient paradigm.
引用
收藏
页数:22
相关论文
共 50 条
  • [41] An Improved Convolutional Neural Network Based Approach for Automated Heartbeat Classification
    Haoren Wang
    Haotian Shi
    Xiaojun Chen
    Liqun Zhao
    Yixiang Huang
    Chengliang Liu
    Journal of Medical Systems, 2020, 44
  • [42] An Improved Convolutional Neural Network Based Approach for Automated Heartbeat Classification
    Wang, Haoren
    Shi, Haotian
    Chen, Xiaojun
    Zhao, Liqun
    Huang, Yixiang
    Liu, Chengliang
    JOURNAL OF MEDICAL SYSTEMS, 2019, 44 (02) : 35
  • [43] Lesion Segmentation Framework Based on Convolutional Neural Networks with Dual Attention Mechanism
    Xie, Fei
    Zhang, Panpan
    Jiang, Tao
    She, Jiao
    Shen, Xuemin
    Xu, Pengfei
    Zhao, Wei
    Gao, Gang
    Guan, Ziyu
    ELECTRONICS, 2021, 10 (24)
  • [44] Combining Contextual Information by Self-attention Mechanism in Convolutional Neural Networks for Text Classification
    Wu, Xin
    Cai, Yi
    Li, Qing
    Xu, Jingyun
    Leung, Ho-fung
    WEB INFORMATION SYSTEMS ENGINEERING, WISE 2018, PT I, 2018, 11233 : 453 - 467
  • [45] Inter-patient ECG classification with convolutional and recurrent neural networks
    Guo, Li
    Sim, Gavin
    Matuszewski, Bogdan
    BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2019, 39 (03) : 868 - 879
  • [46] ECG signal classification using Convolutional Neural Networks for Biometric Identification
    Cordos, Claudia
    Mihaila, Laura
    Farago, Paul
    Hintea, Sorin
    2021 44TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP), 2021, : 167 - 170
  • [47] DIAGNOSTIC ECG CLASSIFICATION BASED ON NEURAL NETWORKS
    BORTOLAN, G
    WILLEMS, JL
    JOURNAL OF ELECTROCARDIOLOGY, 1993, 26 : 75 - 79
  • [48] An Automated ECG Beat Classification System Using Convolutional Neural Networks
    Zubair, Muhammad
    Kim, Jinsul
    Yoon, Changwoo
    2016 6TH INTERNATIONAL CONFERENCE ON IT CONVERGENCE AND SECURITY (ICITCS 2016), 2016, : 335 - 339
  • [49] Hyperspectral Image Classification Based on Convolutional Neural Networks With Adaptive Network Structure
    Ding, Chen
    Li, Wei
    Zhang, Lei
    Tian, Chunna
    Wei, Wei
    Zhang, Yanning
    2018 INTERNATIONAL CONFERENCE ON ORANGE TECHNOLOGIES (ICOT), 2018,
  • [50] Convolutional Neural Networks Based Hyperspectral Image Classification Method with Adaptive Kernels
    Ding, Chen
    Li, Ying
    Xia, Yong
    Wei, Wei
    Zhang, Lei
    Zhang, Yanning
    REMOTE SENSING, 2017, 9 (06)