Heart disease is a highly fatal condition that affects a large number of people worldwide. Unfortunately, many Machine Learning (ML) methods currently in use aren't efficient enough to accurately forecast the diseases caused by heart-related issues. Therefore, there is a crucial need for a system that can effectively predict such diseases. Enter the Deep Learning approach, which has shown promise in predicting diseases stemming from blocked heart conditions. In this research paper, we propose the utilization of a Convolutional Neural Network (CNN) to predict heart disease at an early stage. To gain a comprehensive understanding of the effectiveness of our approach, we conducted a comparative analysis with traditional methods such as Logistic Regression, K-Nearest Neighbors (KNN), Naïve-Bayes (NB), Support Vector Machine (SVM), and Neural Networks (NN). Our focus was to highlight the advantages of our CNN-based prediction model over these conventional techniques. To validate the performance of our model, we used the UCI machine learning repository dataset for experimentation on cardiovascular disease (CVD) predictions. The results were highly encouraging, with our CNN model achieving an impressive accuracy rate of 94%.