Prediction of Cardiac Arrest using Multiple Learning Algorithm

Abstract

Cardiac arrest (CA) is a leading cause of death worldwide and often occurs without warning. Early detection and intervention are critical to saving lives. Because there are no clear warning indicators, traditional methods for predicting CA have not been effective. When machine learning (ML) techniques are integrated, survival rates may increase since these techniques provide additional information that can lead to faster detection and treatment.
Objective: This research proposes rapid, early detection methods for Cardiovascular Diseases (CVD). The reason behind CA is an irregular lifestyle, eating habits, smoking and several other factors. This study addresses the handling and prediction of complex cardiac-related diseases using machine learning.
Method and Materials: This study plans to utilise the following machine learning and soft computing tools: Rough Set Theory (RST), Artificial Neural Network (ANN), Random Forest (RF), Support Vector Machine (SVM), and Modified Feature Elimination (MREF).