Detection of Stroke Disease Using Machine Learning

With the increasing number of fatalities due to heart strokes, it is crucial to develop an accurate and efficient system to predict heart stroke risks. This project aims to build a machine learning model that can precisely anticipate the likelihood of heart strokes, providing healthcare professionals and patients with critical insights for early intervention. Utilizing the Random Forest algorithm, which demonstrated a high accuracy of 99.17% on the Kaggle dataset, the system effectively predicts stroke risks. One of the key advancements of this project is its integration with smartwatch technology, allowing the system to gather real-time health metrics, such as heart rate, blood pressure, and oxygen levels, directly from the user’s smartwatch. By analyzing this live data, the model continuously monitors the user’s condition and, if it detects abnormal patterns associated with stroke risk, it instantly triggers an alert notification to the user and medical professionals. This real-time capability enhances the system's preventive power, helping to significantly reduce the time to intervention. Future improvements of this system could involve scaling the platform for use in mobile and web applications, which would provide a more user-friendly interface and allow healthcare providers to monitor multiple patients more effectively. By expanding the dataset to include more diverse health parameters, the model’s accuracy and reliability in predicting heart strokes could also be further optimized.