Automatic Identification of Abnormalities in 12-lead ECGs Using Expert Features and Convolutional Neural Networks

被引：22
|
作者：
Liu, Zhongdi [1 ]
Meng, Xiang'ao [1 ]
Cui, Jiajia [1 ]
Huang, Zhipei [1 ]
Wu, Jiankang [1 ]
机构：
[1] Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing, Peoples R China
来源：
2018 INTERNATIONAL CONFERENCE ON SENSOR NETWORKS AND SIGNAL PROCESSING (SNSP 2018) | 2018年
关键词：
component; ECG classification; cardiac abnormalities; deep learning; Convolutional Neural Network;
D O I：
10.1109/SNSP.2018.00038
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
Automatic identification of the rhythm/morphology abnormalities in ECGs has gained growing attention in various areas and remains a challenge. We propose an algorithm to classify 12-lead ECGs into 9 categories. We extracted expert features including generic features and specific features with statistics and physiology significance. Then a 17-layer Convolutional Neural Network (CNN) was proposed to detect deep features in ECGs. With these features we trained ensemble classifiers to predict labels. Experiment on the training set (5-fold cross-validation) reports 0.81 accuracy score.
引用
收藏
页码：163 / 167
页数：5
相关论文
共 50 条
  • [31] Diagnostic of Multiple Cardiac Disorders from 12-lead ECGs Using Graph Convolutional Network Based Multi-label Classification
    Jiang, Zheheng
    de Almeida, Tiago P.
    Schlindwein, Fernando S.
    Ng, G. Andre
    Zhou, Huiyu
    Li, Xin
    2020 COMPUTING IN CARDIOLOGY, 2020,
  • [32] A Novel Convolutional Neural Network for Arrhythmia Detection From 12-lead Electrocardiograms
    He, Zhengling
    Zhang, Pengfei
    Xu, Lirui
    Bai, Zhongrui
    Zhang, Hao
    Li, Weisong
    Xia, Pan
    Chen, Xianxiang
    2020 COMPUTING IN CARDIOLOGY, 2020,
  • [33] Non-Invasive Identification of Fibrotic Atrial Cardiomyopathy with Neural Networks Based on 642,400 12-Lead Ecgs from an Extensive Cohort Simulation Study
    Nagel, Claudia
    Doessel, Olaf
    Loewe, Axel
    CIRCULATION, 2021, 144
  • [34] Classification of 12-lead ECGs Using Gradient Boosting on Features Acquired With Domain-Specific and Domain-Agnostic Methods
    Uguz, Durmus Umutcan
    Berief, Felix
    Leonhardt, Steffen
    Antink, Christoph Hoog
    2020 COMPUTING IN CARDIOLOGY, 2020,
  • [35] Convolutional Neural Networks for the Automatic Identification of Plant Diseases
    Boulent, Justine
    Foucher, Samuel
    Theau, Jerome
    St-Charles, Pierre-Luc
    FRONTIERS IN PLANT SCIENCE, 2019, 10
  • [36] Automatic identification for field butterflies by convolutional neural networks
    Almryad, Ayad Saad
    Kutucu, Hakan
    ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH, 2020, 23 (01): : 189 - 195
  • [37] A Novel Neural-Network Model for Deriving Standard 12-Lead ECGs From Serial Three-Lead ECGs: Application to Self-Care
    Atoui, Hussein
    Fayn, Jocelyne
    Rubel, Paul
    IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 2010, 14 (03): : 883 - 890
  • [38] A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG
    Lu-di WANG
    Wei ZHOU
    Ying XING
    Na LIU
    Mahmood MOVAHEDIPOUR
    Xiao-guang ZHOU
    Frontiers of Information Technology & Electronic Engineering, 2019, 20 (03) : 405 - 413
  • [39] A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG
    Wang, Lu-di
    Zhou, Wei
    Xing, Ying
    Liu, Na
    Movahedipour, Mahmood
    Zhou, Xiao-guang
    FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2019, 20 (03) : 405 - 413
  • [40] A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG
    Lu-di Wang
    Wei Zhou
    Ying Xing
    Na Liu
    Mahmood Movahedipour
    Xiao-guang Zhou
    Frontiers of Information Technology & Electronic Engineering, 2019, 20 : 405 - 413
12345