Automatic prediction of coronary artery disease using differential evolution-based support vector machine

Autor: Ammara Idrees, S.A.M. Gilani, Irfan Younas
Rok vydání: 2022
Předmět:
Zdroj: Journal of Intelligent & Fuzzy Systems. 43:5023-5034
ISSN: 1875-8967
1064-1246
Popis: Coronary artery disease (CAD) is a common heart disease that causes the blockage of coronary arteries. To reduce fatality, an accurate diagnosis of this disease is very important. Angiography is one of the most trustworthy and conventional methods for CAD diagnosis however, it is risky, expensive, and time-consuming. Therefore in this study, we proposed a differential evolution-based support vector machine (SVM) for early and accurate detection of CAD. To improve the accuracy, different data preprocessing techniques such as one-hot encoding and normalization are also used with differential evolution for feature selection before performing classification. The proposed approach is benchmarked with the Z-Alizadeh Sani and Cleveland datasets against four state-of-the-art machine learning algorithms, and a highly cited genetic algorithm-based SVM (N2GC-nuSVM). The experimental results show that our proposed differential evolution-based SVM outperforms all the compared algorithms. The proposed method provides accuracies of 95±1% and 86.22% for predicting CAD on the benchmark datasets.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje