Performance evaluation of machine learning classifiers for brain stroke prediction
by Drishti Arora; Rakesh Garg; Farhan Asif; Ritvik Garg; Neetu Singla
International Journal of Bioinformatics Research and Applications (IJBRA), Vol. 20, No. 1, 2024

Abstract: A cerebral vascular accident, commonly known as a stroke, is a pathological condition that impacts the brain due to the rupture of capillaries. It occurs when there is a disturbance in the typical blood circulation and essential physiological processes of the brain. As per the WHO, stroke is the foremost aetiology of mortality, a significant public health concern. While there has been considerable research on the prognosis of heart attacks, investigating the risk factors associated with strokes has been relatively limited. Considering this, a plethora of advanced machine learning models has been leveraged to prognosticate the probability of an impending stroke event. The prime focus of this study is the performance evaluation of eight distinct machine learning classification models as support vector classifier, K-nearest neighbour, logistic regressor, decision tree classifier, random forest classifier, Naïve Bayes classifier, AdaBoost classifier, and XGBoost classifier used for brain stroke prediction. The performance statistics obtained through experimental setup shows that the XGBoost algorithm demonstrated remarkable accuracy, yielding prediction results of approximately 92.75%, making it the preeminent model for precise and reliable stroke prediction.

Online publication date: Thu, 14-Mar-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Bioinformatics Research and Applications (IJBRA):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com