Heart disease prediction using distinct artificial intelligence techniques: performance analysis and comparison

Consolidated efforts have been made to enhance the treatment and diagnosis of heart disease due its detrimental effects on society. As technology medical diagnostics become more synergistic, data mining storing information can improve patient management opportunities. Therefore, it is crucial examine interdependence risk factors in patients' histories comprehend their respective contributions prognosis disease. This research aims analyze numerous components for accurate prediction. The most significant attributes prediction determined using Correlation-based Feature Subset Selection Technique with Best First Search. It has found that diagnosing are age, gender, smoking, obesity, diet, physical activity, stress, chest pain type, previous pain, blood pressure diastolic, diabetes, troponin, ECG, target. Distinct artificial intelligence techniques (logistic regression, Naïve Bayes, K-nearest neighbor (K-NN), support vector machine (SVM), decision tree, random forest, multilayer perceptron (MLP)) applied compared two types datasets (all features selected features). Random forest achieved highest accuracy rate (90%) employing all input other techniques. proposed approach could be utilized as an assistant framework predict at early stage.