CARDIAC ARREST PREDICTION BY MACHINE LEARNING

In this project, I developed a predictive model to identify the likelihood of cardiac arrest with a 92% accuracy rate. Using machine learning algorithms such as SVM, Random Forest, Logistic Regression, Gradient Boosting, and KNN, I optimized the models with advanced feature selection techniques like K-Best and Random Forest-based importance, enhancing prediction accuracy by 30%. This project showcases expertise in healthcare analytics, predictive modeling, and feature engineering to address critical health challenges.