A predictive analytics approach of Brain Stoke using machine learning

The word "Stroke" comes from the idea of receiving a ’strike’ or ’blow’ as that is how quickly strokes appear suddenly, people are struck by the illness. Most strokes occur in people over the age of 65, but they can occur in much younger people as well. Brain cells need oxygen, which is provided by the blood, but when the blood flow stops, sudden damage occurs to the brain, causing it to starve of oxygen in the brain cells. Hence, these symptoms refer to "Stroke". This research investigates the development of a novel machine-learning model to predict stroke risk based on the patient’s clinical data. This study used different algorithms like Decision trees, Logistic regression, KNN, SVM, Gradient Boosting, and XGBoost were used to make a comparison and predict the chances of stroke risk. So, by accurately predicting stroke risk, our objective is to empower healthcare professionals with the tools necessary to implement preventive measures and be cautious for immediate diagnosis.