The paper presents a machine learning-based application for predicting the likelihood of ischemic stroke, a leading cause of death globally. The authors, from various institutions in India, collected a dataset containing multiple medical variables such as age, blood pressure, and diabetes, and addressed missing values during data processing. They trained several machine learning algorithms, including Random Forest, Decision Tree classifier, and SVM, to predict stroke risk. The model with the highest accuracy was selected to help patients assess their risk and receive appropriate medical attention. The system includes a user-friendly GUI where users can input their medical information to determine their stroke risk. The proposed system aims to improve stroke prediction accuracy and provide personalized advice for lifestyle changes to reduce stroke risk. Future work will focus on enhancing model accuracy and expanding the dataset to improve performance.The paper presents a machine learning-based application for predicting the likelihood of ischemic stroke, a leading cause of death globally. The authors, from various institutions in India, collected a dataset containing multiple medical variables such as age, blood pressure, and diabetes, and addressed missing values during data processing. They trained several machine learning algorithms, including Random Forest, Decision Tree classifier, and SVM, to predict stroke risk. The model with the highest accuracy was selected to help patients assess their risk and receive appropriate medical attention. The system includes a user-friendly GUI where users can input their medical information to determine their stroke risk. The proposed system aims to improve stroke prediction accuracy and provide personalized advice for lifestyle changes to reduce stroke risk. Future work will focus on enhancing model accuracy and expanding the dataset to improve performance.