PREDICTION OF HEART DISEASE USING MACHINE LEARNING TECHNIQUES
Sridevi1, B. Sathyanarayanan2, J. Sridharan3, S.R. Srimukunth4 , S. Harshvardhan5
1D. Sridevi Information Technology & SRM Valliammai Engineering college
2B. Sathyanarayanan Information Technology & SRM Valliammai Engineering college
3J. Sridharan Information Technology & SRM Valliammai Engineering college
4S.R. Srimukunth Information Technology & SRM Valliammai Engineering college
5S. Harshvardhan Information Technology & SRM Valliammai Engineering college
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The health care diligence collect huge quantities of data that contain some retired information, which is useful for making effective opinions. For furnishing applicable results and making effective opinions on data, some advanced data mining ways are used. In this study, a vaticination of Heart Disease is Using Machine literacy( PHDML) is developed using Random timber and Decision Tree algorithms for prognosticating the threat position of a heart complaint. The system uses 11 medical parameters similar as age, coitus, blood pressure, cholesterol, and rotundity for vaticination. The PHDML predicts the liability of cases getting a heart complaint. The opinion of a heart complaint is a grueling task, which can offer automated vaticination about the heart condition of a case so that farther treatment can be made effective. It enables significant knowledge.E.g. connections between medical factors related to a heart complaint and patterns, to be established. The attained results have illustrated that the designed individual system can effectively prognosticate the threat position of heart conditions. The major thing of this study is to ameliorate on former work by developing a new and unique fashion for creating the model, as well as to make the model applicable and easy to use in real- world situations.
Key Words: Machine learning, heart disease prediction, feature selection, prediction model, classification algorithms, cardiovascular disease (CVD).