HYBRID MACHINE LEARNING CLASSIFICATION TECHNIQUE FOR IMPROVING THE ACCURACY OF THE HEART DISEASE

COMPUTER SCIENCE(MACHINE LEARNING)

Multiple Chronic disease are available especially Heart disease is the foremost reasons of death in modern world. Machine learning (ML) is useful for making conclusions and predictions based on a huge volume of data formed by the healthcare industry. The proposed approach uses machine learning techniques to find heart disease in this study. The prediction model, which employs classification techniques, is based on the Cleveland heart database. The Random Forest and Decision Tree machine learning techniques are used. This model for heart ailment with hybrid methodology has an accuracy level of 97%, according to experimental study. The boundary is determined as an input parameter from the user to predict heart disease using a Decision Tree method and Random Forest hybrid methodology. When compared to employing either the Random Forest or Decision Tree algorithms alone, the hybrid technique considerably improved prediction accuracy for heart disease. his method improves accuracy while lowering false positives and false negatives, resulting in more accurate diagnoses Finally, it can be said that the hybrid machine learning classification method has improved the precision of diagnosing cardiac disease.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.