Heart Failure Prediction Using Variational Auto-Encoder and Extreme Gradient Boosted Neural Network

This paper pioneers the integration of Variational Auto-encoder (VAE) techniques into the XGBNet 
model for heart failure prediction, leveraging the largest combined heart failure dataset from Kaggle. 
Through rigorous evaluation over 100 epochs, the model achieved a 92% prediction accuracy in 
distinguishing patients with potential heart failure. Comparative analysis revealed a 2-3% increase in 
accuracy over previous methodologies, highlighting the efficacy of VAE in tandem with XGBoost. These 
findings underscore the superiority of the conjugate gradient algorithm as an optimizer and its potential 
implications for healthcare providers, promising enhanced accuracy in early heart failure prediction for 
proactive intervention strategies and improved patient care

Download Paper