STROKE PREDICTION USING MACHINE LEARNING TECHNIQUES

ABSTRACT

The majority of strokes are caused by unexpected obstruction of pathways by the heart and brain. The severity of a stroke can be reduced by identifying several stroke warning signs. By combining the prevalence of hypertension, BMI, heart disease, average glucose level, smoking status, prior stroke, and age with various machine learning algorithms, this research suggests an early diagnosis of stroke disorders. Seven separate classifiers were trained to predict strokes using these high-quality features. The classification methods employed in the study included Logistics Regression, Decision Tree Classifier, AdaBoost Classifier, Gaussian Classifier, K-Nearest Neighbor Classifier, Random Forest Classifier, and XGBoost Classifier. The accuracy percentage for the proposed study was 94%, with the Random Forest classifier beating other classifiers. With the help of this model, which finest precision. When compared to other approaches, Random Forest offers the lowest rates of false positive and false negative results. Because of this, Random Forest is almost the perfect classifier for predicting stroke, allowing doctors and patients to prescribe and identify a possible stroke early on.

STROKE PREDICTION USING MACHINE LEARNING TECHNIQUES.  DOWNLOAD THE SOURCE CODE NOW

Sharing is caring!