Heart disease is a major global health concern and a primary cause of death and morbidity, affecting millions of people worldwide. Machine learning techniques, such as data mining tools, have been applied to improve the performance of medical diagnosis for heart disease. The complexity of heart disease calls for a thorough investigation of its various facets, including coronary artery disease, heart failure, arrhythmias, valvular heart disorders, and congenital heart defects. Risk factors for heart disease include genetics, environmental influences, nutrition, exercise, smoking, excessive alcohol use, obesity, diabetes, and hypertension. Early detection and risk assessment are made possible by advanced imaging techniques and diagnostic technologies, leading to timely interventions and improved cardiac health. In this work, we proposed both Machine learning algorithms including Support Vector Machine (SVM), Decision Tree, KNN, XGB classifier, and Logistic Regression and Deep learning algorithm based on the CNN model to show some useful results to improve the diagnostics related to cardiac issues. The study aims to explore the prevalence, risk factors, diagnostic techniques, therapeutic approaches, and efforts to lessen the negative effects of heart disease on public health.

      Index Terms- Machine Learning Techniques; Deep Learning Algorithms; Detection; Heart disease classification; Performance Measurements; Feature Selection