Automated detection of myocardial infarction using robust features extracted from 12-lead ECG
- PDF / 581,644 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 62 Downloads / 147 Views
ORIGINAL PAPER
Automated detection of myocardial infarction using robust features extracted from 12-lead ECG Zhuochen Lin1 · Yongxiang Gao1 · Yimin Chen1 · Qi Ge1 · Gehendra Mahara1 · Jinxin Zhang1 Received: 20 February 2019 / Revised: 11 November 2019 / Accepted: 16 December 2019 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Electrocardiography is a useful diagnostic tool for various cardiovascular diseases, such as myocardial infarction (MI). An electrocardiograph (ECG) records the electrical activity of the heart, which can reflect any abnormal activity. MI recognition by visual examination of an ECG requires an expert’s interpretation and is difficult because of the short duration and small amplitude of the changes in ECG signals associated with MI. Therefore, we propose a new method for the automatic detection of MI using ECG signals. In this study, we used maximal overlap discrete wavelet transform to decompose the data, extracted the variance, inter-quartile range, Pearson correlation coefficient, Hoeffding’s D correlation coefficient and Shannon entropy of the wavelet coefficients and used the k-nearest neighbor model to detect MI. The accuracy, sensitivity and specificity of the model were 99.57%, 99.82% and 98.79%, respectively. Therefore, the system can be used in clinics to help diagnose MI. Keywords Electrocardiograph · Myocardial infarction · Wavelet transform · Feature extraction
1 Introduction Myocardial infarction (MI) happens when the blood supply to part of the heart decreases or stops entirely, initiating damage to the heart muscle and possible death. Globally, about 15.9 million people suffered from MI in 2015 [1]. As MI develops rapidly and initially has no obvious symptoms, detection and treatment are time-critical [2]. The sooner MI is detected, the more means are available to control its effect on left ventricle contractility and function, leading to better therapeutic outcomes and prognosis [3]. Therefore, the development of
B
Zhuochen Lin [email protected] Yongxiang Gao [email protected] Yimin Chen [email protected] Qi Ge [email protected] Gehendra Mahara [email protected] Jinxin Zhang [email protected]
1
School of Public Health, Sun Yat-Sen University, Guangzhou 510080, China
techniques for early and rapid MI detection is a worldwide research goal. Electrocardiography is a diagnostic tool in which electrodes are placed on the skin to collect information about the heart’s electrical activity over time [4]. If the electrical or contractile function of the heart is interrupted due to myocardial ischemia, the whole myocardial electrical signal flow will also be affected. For example, in the case of MI, electrocardiogram (ECG) signals often manifest as S–T segment elevations and Q waves. Twelve-lead electrocardiography is a traditional clinical means of monitoring changes in cardiac electrical activity to assess the risk of MI. Before this technology became popular, clinicians had used Minnesota coding [5] to e
Data Loading...
