Detection of myocardial infarction in 12 lead ECG using support vector machine

被引:112
作者
Dohare, Ashok Kumar [1 ]
Kumar, Vinod [2 ]
Kumar, Ritesh [3 ]
机构
[1] Rewa Engn Coll, Elect & Commun Engn Dept, Rewa 486002, MP, India
[2] JAYPEE Univ Informat Technol, Solan 173234, HP, India
[3] Rajendra Inst Med Sci, Ranchi 834009, Jharkhand, India
关键词
Electrocardiogram; Composite lead; Myocardial infarction; Statistical parameters support vector; machine; Principal component analysis (PCA); B-MODE ULTRASOUND; CLASSIFICATION; LESIONS; IMAGES; SYSTEM; PCA;
D O I
10.1016/j.asoc.2017.12.001
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
In this paper, we propose myocardial infarction (MI) detection using 12-lead ECG data and analysis of each lead with the help of composite lead. This composite lead is used to detect ECG wave components and clinical wave intervals in all the 12-lead ECG. The four clinical features such as P duration, QRS duration, ST-T complex interval and QT interval are globally determined from average beats of all the 12-lead ECG. Then peak to peak amplitude, area, mean, standard deviation, skewness and kurtosis are determined for P duration, QRS duration and ST-T complex interval of average beats of all the 12-lead ECG. These 220 (4 + 6 x 3 x 12) parameters are used for myocardial infarction detection. The standard 12-lead ECG data of 60 myocardial infarction subjects and 60 healthy controls (HC) cases are obtained from Physikalisch-Technische Bundesanstalt (PTB) database and tested with support vector machine (SVM) classifier. The MI detection sensitivity, specificity and accuracy are 96.66%, 100% and 98.33% respectively. To reduce the computational complexity, feature dimension reduction is important. Therefore, proposed method applies Principal Component Analysis (PCA) reduction technique. In this proposed method, 220 features are reduced to 14 features, using these 14 features, MI detection achieved by SVM classifier is: sensitivity 96.66%, specificity 96.66% and accuracy 96.66%. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:138 / 147
页数:10
相关论文
共 24 条
[1]
Defining unrecognized myocardial infarction: A call for standardized electrocardiographic diagnostic criteria [J].
Ammar, KA ;
Kors, JA ;
Yawn, BP ;
Rodeheffer, RJ .
AMERICAN HEART JOURNAL, 2004, 148 (02) :277-284
[2]
[Anonymous], J DIGIT IMAGING
[3]
[Anonymous], J ELECTROCARDIOL
[4]
[Anonymous], PHYS TECHNISCHE BUND
[5]
[Anonymous], SAS SUGI 16 C APR 19
[6]
Detection and Localization of Myocardial Infarction using K-nearest Neighbor Classifier [J].
Arif, Muhammad ;
Malagore, Ijaz A. ;
Afsar, Fayyaz A. .
JOURNAL OF MEDICAL SYSTEMS, 2012, 36 (01) :279-289
[7]
Myocardial infarction classification with multi-lead ECG using hidden Markov models and Gaussian mixture models [J].
Chang, Pei-Chann ;
Lin, Jyun-Jie ;
Hsieh, Jui-Chien ;
Weng, Julia .
APPLIED SOFT COMPUTING, 2012, 12 (10) :3165-3175
[8]
PCA and ICA processing methods for removal of artifacts and noise in electrocardiograms: A survey and comparison [J].
Chawla, M. P. S. .
APPLIED SOFT COMPUTING, 2011, 11 (02) :2216-2226
[9]
An efficient new method for the detection of QRS in electrocardiogram [J].
Dohare, Ashok Kumar ;
Kumar, Vinod ;
Kumar, Ritesh .
COMPUTERS & ELECTRICAL ENGINEERING, 2014, 40 (05) :1717-1730
[10]
Detecting acute myocardial infarction in the 12-lead ECG using Hermite expansions and neural networks [J].
Haraldsson, H ;
Edenbrandt, L ;
Ohlsson, M .
ARTIFICIAL INTELLIGENCE IN MEDICINE, 2004, 32 (02) :127-136