ENHANCED PREDICTION OF HEART DISEASE WITH FEATURE SUBSET SELECTION USING GENETIC ALGORITHM

摘要: Clinical diagnosis is done mostly by doctor’s expertise and experience. But still cases are reported of wrong treatment. Patients asked to take number tests for diagnosis. In many cases, not all the contribute towards effective a disease. The objective our work predict more accurately presence heart disease with reduced attributes. Originally, thirteen attributes were involved in predicting work, Genetic algorithm used determine which ailments indirectly reduces needed be taken patient. Thirteen 6 using genetic search. Subsequently, three classifiers like Naive Bayes, Classification clustering Decision Tree patients same accuracy as obtained before reduction Also, observations exhibit that data mining technique outperforms other two techniques after incorporating feature subset selection relatively high model construction time. Bayes performs consistently via poor compared methods.