Globally, Cardiovascular Disease (CVD) is considered as prominent reason of mortality. More than 80% of CVD-related demises are attributable to heart disease and strokes, with 33% of these unexpected demises occurring in subjects under the age of 70. The accelerated economic transformation, which results in environmental changes and unhealthy lifestyles, enhances cardiovascular disease risk factors and incidence. The most prevalent cardiovascular diseases account for arrhythmia, Coronary Artery Disease (CAD), Congenital Heart Defect (CHD), cardiomyopathy, angina, and mitral regurgitation. For CVDs to have a favorable prognosis, an early and prompt diagnosis is necessary. For identifying and diagnosing CVD, patients must exhibit elated quantities of biomarkers in blood analysis, critical chest pain, and an altered Electrocardiogram (ECG). Unexpectedly, maximum patients of CVD, diagnosis is challenging for physicians as majority of them exhibit a normal ECG pattern. Application of Artificial Intelligence (AI) approaches may considerably advance and augment outcomes in CVD diagnosis. AI can provide novel methods and instruments for gathering and analyzing data to make quicker, and more accurate decisions. This chapter provides a systematic review of disease classification and ECG sensor detection. It also summarizes applications of AI techniques, such as mobile health and computers, IoT, Machine Learning (ML) algorithms such as Decision Tree induction, Support Vector Machine (SVM), Artificial Neural Network (ANN), Clustering, Convolution Neural Network (CNN), Computational Magnetic Resonance (CMR), Deep Neural Network (DNN), and Cardiac Computed Tomography (CMT), that can be employed effectively for prompt and precise diagnosis and detection of CVDs. Furthermore, it emphasizes the drawbacks of AI techniques and their possible prospects for CVDs.