Abstract: Stroke is a medical condition in which the blood vessels in the brain rupture, causing brain damage. If the brain supply of blood and other nutrients is compromised, symptoms could develop. Stroke is the leading cause of death and disability worldwide, according to the World Health Organization (WHO). Early awareness of the numerous stroke warning symptoms can assist to lessen the severity of the stroke. To forecast the likelihood of a stroke happening in the brain, many machine learning (ML) models have been developed. This study uses a variety of physiological characteristics and machine learning methods to train four different models for reliable prediction, including Decision Tree (DT) Classification, Random Forest (RF) Classification, SVM, K-Neighbor classifiers. The datasets downloaded from Kaggle website was used in the development of the approach. The accuracy of the models employed in this study is substantially greater than in earlier studies, showing that the models utilized in this study are more trustworthy. The scheme may be determined from the study analysis, which has been proven by numerous model comparisons.
Keywords: DT, RF, SVM, K-Neighbors, Resnet-34, Vgg-16, Densenet-121.
|
DOI:
10.17148/IJARCCE.2022.116133
