Cardiovascular diseases are widely acknowledged as highly challenging and contribute significantly to global fatalities. The widespread use of medications has strained healthcare systems worldwide. In this review, we describes a method, Machine Learning-based Cardio Vascular Disease Prediction (ML-CVDP), designed for accurately predicting cardiovascular illnesses. The model addresses issues like missing values using the mean substitution approach and tackles data imbalances with the Synthetic Minority Over-sampling Technique (SMOTE). It employs an ensemble of Logistic Regression (LR), K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Trees (DT), and Artificial Neural Networks (ANN) for categorization. The Feature Significance approach is then applied to select features. Experimental results demonstrate the strategy's superiority over single-modal techniques, achieving an accuracy of 93.2%, precision of 94.1%, specificity of 89.6%, sensitivity of 94.1%, Mean Squared Error (MSE) of 6.3%, and Root Mean Squared Error (RMSE) of 4.8%. The True Positive Rate (TPR) is 91.5%, and the False Positive Rate (FPR) is 92.5%.