Brain Stroke Prediction and Analysis Using Machine Learning

Gunupuru Vamsi 1, Karri Divya 2

1Assistant Professor, 2 MCA Final Semester, Master of

Computer Applications, Sanketika Vidya Parishad Engineering College, Vishakhapatnam,

Andhra Pradesh, India

 karridivya790@gmail.com

ABSTRACT:

Stroke is one of the most serious diseases worldwide and is directly or indirectly responsible for a significant number of deaths. It is a neurological disorder that occurs when brain cells die due to a lack of oxygen and nutrients. Early detection of stroke within the first few hours can significantly improve treatment outcomes, reduce complications, and enhance patient care and management. According to the World Health Organization (WHO), stroke is one of the leading causes of death and disability globally. Early recognition of warning signs can help reduce the severity of stroke and save lives.

Machine Learning plays a vital role in predicting the risk of stroke at an early stage. In this project, we have used several machine learning algorithms such as Support Vector Machine (SVM), Random Forest, Decision Tree, K-Nearest Neighbors (KNN), and Logistic Regression. We worked with a healthcare stroke dataset that consists of parameters such as age, gender, hypertension, heart disease, work type, BMI, smoking status, average glucose level, marital status, residence type, and stroke occurrence.

After preprocessing the data, we evaluated and compared the accuracy of each algorithm. Based on the comparison, the best-performing model was selected for prediction. Finally, we developed a Graphical User Interface (GUI) that allows users to enter manual inputs, and the system predicts whether a person is at risk of having a stroke or not.