Enhanced Brain Stroke Prediction: An Ensemble of Random Forest, Logistic Regression and XGBoost

Stroke, a leading cause of disability and mortality globally, necessitates early prediction and intervention to mitigate its devastating effects. Recognizing the challenges faced by stroke survivors, the focus shifts to the crucial role of rehabilitation and lifestyle changes in optimizing recovery and quality of life. Machine learning (ML) algorithms emerges as a powerful tool for predicting stroke risk and enhancing patient outcomes. ML algorithms, by analysing extensive datasets, can identify patterns and early warning signs, enabling more personalized treatment plans. To enhance prediction accuracy, an ensemble model is proposed, leveraging Random Forest (RF), Logistic Regression (LR) and XGBoost techniques. The ensemble model exhibits an impressive accuracy rate of 97.4%, exceeding other models.