AI / Machine Learning
Stroke Prediction
Objective
Develop a robust stroke prediction model using machine learning algorithms and SMOTE oversampling to address data imbalance, enabling early identification of high-risk individuals to improve clinical intervention outcomes.
About the Project
Stroke, a critical medical condition resulting from disrupted blood flow to the brain, stands as a global health concern and a leading cause of death and disability according to the WHO. Early identification of stroke warning symptoms is crucial to mitigate its severity.
This project leverages advanced machine learning techniques to develop a predictive model for forecasting the likelihood of a stroke based on diverse symptoms and risk factors. To address the challenge of imbalanced data, the Synthetic Minority Over-sampling Technique (SMOTE) is employed to enhance the dataset.
Multiple ML algorithms are evaluated — including Random Forest, Support Vector Machines, Decision Trees, and Neural Networks — with rigorous performance evaluation using accuracy, precision, recall, and F1 score metrics.
