Abstract
Myocardial infarction (MI) is one of the most common cardiovascular diseases threatening human life. In order to accurately distinguish myocardial infarction and have a good interpretability, the classification method that combines rule features and ventricular activity features is proposed in this paper. Specifically, according to the clinical diagnosis rule and the pathological changes of myocardial infarction on the electrocardiogram, the local information extracted from the Q wave, ST segment, and T wave is computed as the rule feature. All samples of the QT segment are extracted as ventricular activity features. Then, in order to reduce the computational complexity of the ventricular activity features, the effects of Discrete Wavelet Transform (DWT), Principal Component Analysis (PCA), and Locality Preserving Projections (LPP) on the extracted ventricular activity features are compared. Combining rule features and ventricular activity features, all the 12 leads features are fused as the ultimate feature vector. Finally, eXtreme Gradient Boosting (XGBoost) is used to identify myocardial infarction, and the overall accuracy rate of 99.86% is obtained on the Physikalisch-Technische Bundesanstalt (PTB) database. This method has a good medical diagnosis basis while improving the accuracy, which is very important for clinical decision-making.
Highlights
Myocardial infarction (MI) [1] refers to a cardiovascular disease in which the coronary blood supply is drastically reduced or interrupted, causing serious and long-lasting ischemia of myocardial cells and leading to myocardial cell damage and even necrosis. erefore, early detection and prevention of MI are of great significance, which can ensure the safety of patients’ lives [2]
The performances of the ventricular activity features with the best compression effect and the rule features and their combination on the classification effect are compared. is paper uses the Physikalisch-Technische Bundesanstalt (PTB) database. e focus is on the analysis and classification of 8 kinds of myocardial infarction, as well as health and other diseases data
Accurate identification of myocardial infarction based on medical principles is very important for the treatment of patients. erefore, a classification method of myocardial infarction based on the ventricular fusion rule features and the XGBoost algorithm is proposed this paper
Summary
MI [1] refers to a cardiovascular disease in which the coronary blood supply is drastically reduced or interrupted, causing serious and long-lasting ischemia of myocardial cells and leading to myocardial cell damage and even necrosis. erefore, early detection and prevention of MI are of great significance, which can ensure the safety of patients’ lives [2]. Myocardial enzymes usually are the main indicator for diagnosing MI. E electrocardiogram is a key indicator for early warning and diagnosis of MI [4, 5]. Applying computer-assisted intelligent detection to the classification of MI can help doctors diagnose MI more accurately and reduce the burden on doctors. A variety of classification algorithms for identifying MI have been proposed, which are mainly divided into deep learning and feature engineering according to the research direction. Deep learning is classified in an end-to-end manner and has high performance, so it is widely used for MI classification. It does not pay attention to data processing and is dedicated to the performance of the classifier, so it cannot analyze the impact of specific features on the classification performance. It does not pay attention to data processing and is dedicated to the performance of the classifier, so it cannot analyze the impact of specific features on the classification performance. e
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call