Stroke Disease Prediction Model Using ANOVA with Classification Algorithms, Chapter 8

Simple item page
dc.contributor.authorAbdulsalam, S.O.
dc.contributor.authorArowolo, M.O.
dc.contributor.authorOroghi, R.
dc.date.accessioned2025-10-29T12:14:13Z
dc.date.available2025-10-29T12:14:13Z
dc.date.issued2023
dc.description.abstractStroke is a health ailment where the brain plasma blood vessel is ruptured, triggering impairment to the brain. Symptoms may appear when the brain's blood flow and other nutrients are disrupted. Stroke is the leading cause of bereavement and disability universally, according to the World Health Organization. To predict a patient’s risk of having stroke, this project used machine learning (ML) approach on a stroke dataset obtained from Kaggle, the ANOVA (Analysis of Variance) feature selection method with and without the following four Classification procedures; Logistic Regression, K-Nearest Neighbor, Naïve Bayes, and Decision Tree, after which the dataset was preprocessed. The K-Nearest Neighbor algorithm gave the best performance accuracy of approximately 97% without ANOVA and Decision Tree algorithm with ANOVA method gave 96%. The accuracy of the developed models employed in this study is substantially better, showing that the models employed in this study are much more reliable. And it can be deduced from previous existing works. Keywords: ANOVA, Stroke, KNN, Decision tree, Machine learning
dc.identifier.urihttps://kwasuspace.kwasu.edu.ng/handle/123456789/6288
dc.language.isoen
dc.publisherSpringer Nature Publishing Singapore - Artificial Intelligence in Medical Virology, Springer Nature Singapore, (pp.117 – 134)
dc.titleStroke Disease Prediction Model Using ANOVA with Classification Algorithms, Chapter 8
dc.typeBook chapter
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
20-Springer_AI Medical Virology Sroke Prediction ANOVA.pdf
Size:
560.07 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
Scholarly Publication