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

被引：23
|
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] Automatic Identification of Local Features Representing Image Content with the Use of Convolutional Neural Networks
    Tarasiuk, Pawel
    Tomczyk, Arkadiusz
    Stasiak, Bartlomiej
    APPLIED SCIENCES-BASEL, 2020, 10 (15):
  • [32] Performance of a Convolutional Neural Network and Explainability Technique for 12-Lead Electrocardiogram Interpretation
    Hughes, J. Weston
    Olgin, Jeffrey E.
    Avram, Robert
    Abreau, Sean A.
    Sittler, Taylor
    Radia, Kaahan
    Hsia, Henry
    Walters, Tomos
    Lee, Byron
    Gonzalez, Joseph E.
    Tison, Geoffrey H.
    JAMA CARDIOLOGY, 2021, 6 (11) : 1285 - 1295
  • [33] 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,
  • [34] 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
  • [35] 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,
  • [36] Reconstructing 12-lead ECG from reduced lead sets using an encoder-decoder convolutional neural network
    Epmoghaddam, Dorsa
    Banta, Anton
    Post, Allison
    Razavi, Mehdi
    Aazhang, Behnaam
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2025, 104
  • [37] 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,
  • [38] 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
  • [39] 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
  • [40] 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
12345