Attribute Selection for Stroke Prediction
AbstractStroke is the third most common cause of death and the most common cause of long-term disability among adults around theworld. Therefore, stroke prediction and diagnosis is a very important issue. Data mining techniques come in handy to help determine the correlations between individual patient characterisation data, that is, extract from the medical information system the knowledge necessary to predict and treat various diseases. The study analysed the data of patients with stroke using eight known classification algorithms (J48 (C4.5), CART, PART, naive Bayes classifier, Random Forest, Supporting Vector Machine and neural networks Multilayer Perceptron), which allowed to build an exploration model given with an accuracy of over 88%. The potential features of patients, which may be factors that increase the risk of stroke, were also indicated.
|Journal series||Acta Mechanica et Automatica, ISSN 1898-4088, e-ISSN 2300-5319, (N/A 40 pkt)|
|Publication size in sheets||0.5|
|Keywords in English||data mining, classifier, J48 (C4.5), CART, PART, naive Bayes classifier, Random Forest, Support Vector Machine, Multilayer Perceptron, haemorrhagic stroke, ischaemic stroke|
|Internal identifier||ROC 19-20|
|License||Journal (articles only); published final; ; with publication|
|Score||= 40.0, 12-02-2020, ArticleFromJournal|
|Publication indicators||: 2018 = 0.615|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.