Deep Learning Approaches for Cardiovascular Disease Prediction

Cardiovascular diseases (CVDs) rank among the world's leading causes of death, and their effective treatments depend on early and precise diagnosis. Conventional diagnostic techniques can be time-consuming and frequently require a high level of medical skill, which limits their effectiveness in real-time applications. Therefore, thorough research is conducted by various researchers and scholars, using machine learning and deep learning algorithms to foretell heart diseases by using datasets and working on attributes related to the same. In our research, we looked over a dataset from Kaggle which contains attributes related to cardiovascular diseases, and explore the potential of deep learning methods in predicting cardiovascular diseases by comparing the accuracy of Deep learning algorithms such as Support vector machine (SVM), Decision tree (DT), K-nearest neighbour (KNN), ADA Boost, and XG Boost with hyperparameter optimization.