Prediction of stroke disease using machine learning techniques / Syarifah Adilah Mohamed Yusoff ... [et al.]

Mohamed Yusoff, Syarifah Adilah and Warris, Saiful Nizam and Abu Bakar, Mohd Saifulnizam and Kadar, Rozita (2024) Prediction of stroke disease using machine learning techniques / Syarifah Adilah Mohamed Yusoff ... [et al.]. Navigating the spectrum: the new wave of e-learning innovations, 7. pp. 76-86. ISSN 9786299875512
Abstract

Stroke is a global disease that is reported to increase annually and is a leading cause of mortality worldwide. The advancement of data analytics and machine learning has made it possible to foretell future patterns and insights, which could lead to the discovery of novel treatments for this condition. This study has investigated five commonly used machine learning algorithm to be constructed as potential models for predicting stroke dataset. Jupyter Notebook, a phyton-base engine, was employed as a data analytic tool for the purpose of analysing and evaluating all of the models. The five models were Decision Tree, Logistic Regression, Linear Discriminant Analysis, Gaussian Naïve Bayes and Support Vector Machine, have being implemented to predict binary outcome of stroke and no stroke. The accuracy percentage reported that Logistic regression outperformed other models with 50.93%.

Item Details
Edit Item
Edit Item
Downloads & Files
[thumbnail of 94453.pdf]
Text
94453.pdf
Download (484kB)
Indexing & Metrics