Brain Stroke Prediction Using Machine Learning and Power BI

In recent years, machine learning and artificial intelligence have played a transformative role in the healthcare sector, especially in disease prediction and diagnosis. Among various health conditions, stroke remains one of the leading causes of death and long-term disability worldwide. Early prediction and timely intervention are critical to reducing its impact. Leveraging machine learning for strokeprediction offers a promising approach to analyze medical data and identify high-risk individuals before the onset of a stroke. This project, titled “Brain Stroke Prediction Using Machine Learning,” focuses on building an intelligent system that can analyze patient health data to predict the likelihood of a stroke. By using a supervised machine learning approach, the system learns from historical medical records and identifies patterns and correlations between different health factors such as age, hypertension, heart disease, and body mass index. The goal is to assist healthcare professionals in making faster and more informed decisions by providing a risk score based on the input parameters. The development of this model involves preprocessing patient datasets, feature selection, model training, and performance evaluation using metrics such as accuracy, precision, recall, and F1-score. Various algorithms like Logistic Regression, Random Forest, and Support Vector Machine have been explored to determine the most effective mhod for stroke prediction.