Abstract. We investigated training therapeutic program effectiveness of the school "Stop a Stroke", which aimed at reducing a risk of a stroke for patients with the atrial fibrillation. On the basis of two feature selection methods using a criterion of the discriminant analysis to determine the best feature subset, we concluded that patients, who trained at the school, in contrast to patients, who have not received training, take anticoagulants for a long time and have a higher level of knowledge about the atrial fibrillation.Keywords: data mining, feature selection, discriminant analysis criterion.Citation: Kutikova VV, Gaidel AV, Khramov AG. Feature selection in the effectiveness research of a training program for patients with the atrial fibrillation. CEUR Workshop Proceedings, 2016; 1638 : 902-908. DOI: 10.18287/1613 -0073-2016 -1638
IntroductionReducing the dimensionality of a feature space is one of the central issues in data mining. For the most classification and recovery regression problems it is necessary to select the best subset from a given feature set. This is because the use of a large feature number is not only computational expensive, but also affects the recognition accuracy, as irrelevant and redundant features, which complicate the decision-making process, can be used. Feature selection methods are commonly used for the biomedical data analysis. In the work [1] using the method based on the ANCOVA an 80-gene biomarker of the smokers lung cancer was identified from 22216 features describing the expression levels of different genes. The accuracy, sensitivity and specificity of this biomarker were 83 %, 80% and 84%, respectively. For the selection of a small number of features one can use the brute force [2]. In biomedical data mining the sequential search algorithms [3] and genetic algorithms [4] are also used. Feature selection methods based on a criterion of the discriminant analysis have showed their effectiveness in [5,6] for the analysis of biomedical images.