An Enhanced Stroke Prediction Scheme Using SMOTE and Machine Learning Techniques
Ferdib-Al Islam, Mounita Ghosh
Abstract
Stroke is the second driving reason for death worldwide, answerable for around 11% of all out passings. Throughout the long term, scientists are attempting to connect up various elements to the onset of stroke. Early awareness of various threat issues of stroke can limit the chance of stroke. The prediction of stroke is essential to counter health damage or passing. In this research, machine learning has been utilized to predict stroke inpatients. A popular oversampling method called SMOTE with several machine learning classifiers (Logistic Regression, Random Forest, and XGBoost) has been applied to the dataset to predict the consequence. The random forest model achieved better performance among these algorithms with 99.07% of accuracy, 99.0% of precision and recall. The feature importance scores have been shown to understand the feature's impact on the model development. The proposed model outperformed the existing works with higher accuracy.