Smart Healthcare: Brain Stroke Prediction using Machine Learning

Abstract

The brain, which comprises of the cerebrum, cerebellum, and brainstem and is covered by the skull, is a very complex and intriguing organ in the human body. Stroke is the world’s second-leading cause of mortality; as a result, it requires prompt treatment to avoid brain damage. Early detection of a brain stroke can help to prevent or lessen the severity of the stroke, which can lower death rates. Using machine learning algorithms to identify risk variables is a promising method. This paper proposed a model that included a methodology to achieve an accurate brain stroke forecast. Efficient data collection, data pre-processing, and data transformation methods have been applied to provide reliable information for our proposed model to be successful. A “brain stroke dataset” was employed to build up the model. The standardization technique is used to standardize data. In the training and testing procedure, Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), K-Nearest Neighbors (KNN) and Decision Tree (DT) classifiers are applied. The performance of each classifier has been estimated by adopting performance evaluation metrics such as accuracy, f1-score, precision, recall etc. The dataset was preprocessed by deleting unnecessary columns, dropping null values, removing outliers and by comencoding the categorical values using One Hot Encoding. Oversampling technique is used to balance the dataset as it was highly unbalanced. After evaluation the findings reveal that the proposed stacking ensemble approach performs better than the single models, achieving an accuracy rate of nearly 99%.

Keywords: Brain stroke, Disease prediction, Machine learning, Random forest.

View PDF