{"title":"Robust Detection of Cardiac Disease Using Machine Learning Algorithms: Robust Detection","authors":"Anas Domyati, Q. Memon","doi":"10.1145/3561613.3561622","DOIUrl":null,"url":null,"abstract":"The contribution of the current work is to facilitate diagnose the heart disease based on contemporary machine learning algorithms. The performances of the classifiers are tested on feature spaces selected through various feature selection algorithms. The relief feature selection algorithm was selected for vital and more correlated features. The models were trained and tested on the Cleveland (S1) and Hungarian (S2) heart disease datasets. Several performance measures such as accuracy, sensitivity, specificity, and F1 score are used to observe the effectiveness of the selected models. It is found out that SVM and random forest achieved very promising results with both full feature space and selected feature space, specifically with relief feature selection algorithm.","PeriodicalId":348024,"journal":{"name":"Proceedings of the 5th International Conference on Control and Computer Vision","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 5th International Conference on Control and Computer Vision","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3561613.3561622","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
The contribution of the current work is to facilitate diagnose the heart disease based on contemporary machine learning algorithms. The performances of the classifiers are tested on feature spaces selected through various feature selection algorithms. The relief feature selection algorithm was selected for vital and more correlated features. The models were trained and tested on the Cleveland (S1) and Hungarian (S2) heart disease datasets. Several performance measures such as accuracy, sensitivity, specificity, and F1 score are used to observe the effectiveness of the selected models. It is found out that SVM and random forest achieved very promising results with both full feature space and selected feature space, specifically with relief feature selection algorithm.