Prediction of brain stroke occurrence using support vector machine

Stroke is a serious medical condition identified by an abrupt interruption of blood flow to the brain. Risk factors for stroke include high blood pressure, diabetes, and smoking. Due to their reliance on static risk factors and limited predictive abilities, traditional methods of predicting strokes may not be as effective today because they frequently ignore dynamic factors and individual variations in disease progression and response to treatment. Machine learning has demonstrated the potential for identifying unknown threats, such as brain stroke. This research project focuses on using supervised machine learning methods to improve stroke prediction's precision and efficiency. The chosen method is Support Vector Machine (SVM), which is a popular supervised machine learning method. This research aims to create a predictive model for brain strokes by comparing performance measurement of supervised machine learning Support vector machines (SVM) using a brain stroke dataset. This research used a structured methodology to develop a supervised learning model for predicting brain strokes. The process has 3 phases which involves literature review, data gathering, pre-processing, model development using SVM, and performance evaluation. The performance on the known stroke dataset is then analysed, and the ability to identify brain stroke is evaluated. The results show that the selected classifier effectively detect and predict brain stroke and outperform existing techniques. The results of this research will help in the development of reliable predictive models to evaluate the risk of stroke, allowing healthcare professionals to quickly intervene and put preventive measures into place. Ultimately, the integration of supervised machine learning techniques has the potential to increase the accuracy of stroke prediction and enable early intervention, thereby easing the burden of stroke-related morbidity and mortality.