It is observed that every year, cardiovascular disease claims the lives of about 20.5 million individuals. Early detection and treatment of a heart attack can lessen its most severe symptoms. Medical practitioners can prevent complications and save lives by using machine learning to diagnose heart disease earlier and begin therapy. A machine-learning model that forecasts an individual’s risk of heart disease was developed using a variety of characteristics pertinent to heart disease detection. The classification of heart illness on both synthetic and real-time datasets has been the focus of numerous computer science researchers. However, those systems still face difficulties like poor heart severity detection, a high mistake rate, and poor classification accuracy. After recognizing each of these difficulties, we suggested a hybrid machine learning approach for the efficient identification and categorization of heart disease. This study describes how several hybrid machine learning and feature extraction classifiers give accurate heart disease severity on real-time datasets. In this study dataset including 300 samples are used. Module training makes use of a variety of feature extraction and selection techniques. The supervised machine learning algorithms are used, such as Support Vector Machine, convolutional neural network. In this study to achieve more accuracy pipelined approach is given by building Hybrid Machine Learning model. As a result, the proposed system compares with various heart disease predictions using machine learning techniques. This model could play an important role in predicting heart disease and preventing the severe effects of a heart attack.