Cardiovascular diseases is the main cause of death all over the world and becomes severe health threat among higher age people. Early diagnosis of the disease can save lives and medical diagnosis plays key role. the practitioners are applying many advance treatments. The proposed works studies the risk of Cardiovascular diseases prediction based on machine learning and genetic algorithm. This work is an ensemble model of combining the efficacy of genetic algorithm along with decision tree classification. The features determined by the genetic algorithm are used for machine learning classification, which improves the efficacy of proposed prediction system. The dataset provided by UCI repository, named Cleveland dataset is used for the study. The dataset with 303 instances and 14 attributes with five class types are used for the study. The class values range from 0 - Normal to 4- Stoke. The experimental results shows that the Genetic Algorithm based feature selection and classification bring best results on multiple class disease threat prediction. The application is designed that patients can able to predict and discuss with practitioners through the designed web application.