Due to a rise in global mortality rates, heart problems have quickly become among the leading cause of death necessitating early diagnosis to help prevent severe illness. In this article, the focus will be on presenting varied forms of Cardio Vascular Disease (CVD) detection approaches which have diverse performance evaluation measures such as specificity or accuracy levels from ML perspective. Machine learning (ML) possesses the capacity and promise to enhance CVD prognosis, identification, and therapy through the identification of intricate patterns that may include human interpretation and detection and analysis of the patient data. In this paper, many modern Machine Learning architectures such as k nearest neighbor (KNN), standard linear model (SLM), random forest (RF), Naïve Bayes, decision tree (DT), support vector machine (SVM), XGBoost, logistic regression (LG) and artificial neural network (ANN) were applied. This paper uses Exploratory Data Analysis Dataset for the early prognosis of Cardiovascular Disease. These models show that the use of Machine Learning in detecting CVD can help in developing powerful models that can be used to improve forecasting abilities while advocating for the integration of these models in clinics in order to enhance predictive capabilities as well. This connection greatly helps in reducing burden imposed by CVD on health systems. The findings demonstrated that the suggested Artificial Neural Network (ANN) model attains a greater level of Accuracy (93.03%).