Paper Title
A Support System for Clinically Detecting Heart Disease Predictions Using Deep Learning

Abstract
Since cardiovascular disease ranks as one of the top causes of death globally, timely identification is essential for effective treatment. Predictive healthcare products often incorporate machine learning (ML) approaches. The accuracy of most traditional ML models is however below 80%, and that is not sufficient for reliable medical assessments. To enhance the precision of the predictions, this study proposes combining Random Forest-CNN (RFCNN) with other ensemble methods as Voting Classifier, XGBoost, and Extra Tree Classifier. The system aims to provide trustworthy and precise cardiac disease prediction using CNN's pattern detection ability and Random Forest's feature selection ability. With a heart disease dataset, the model has been trained and evaluated, showing notable enhancements in accuracy and location accuracy when compared to current techniques. Keywords - Heart Disease Classification, Machine Learning, Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbors Clinical Data Analysis, Healthcare Automation)