Heart Disease Classification Using Machine Learning Techniques: An Impact Analysis of GridSearchCV-based Optimization

At present, cardiovascular disease has the potential to affect a substantial portion of the global population. The study performs the heart disease classification using several machine-learning algorithms. This study implements numerous machine learning machine learning techniques, such as Logistic Regression, K-Nearest Neighbors (KNN), Decision Tree, Extreme Gradient Boosting (XGBoost), Naïve Bayes, Support Vector Classifier (SVC), and Ensemble models. Additionally, the identification of the most effective parameters is essential for the development of a high-accuracy model and the improvement of predictive performance. Consequently, this study implements GridSearchCV for optimization. It assesses all parameters of the chosen model that have been specified and determines the optimal parameters by analyzing the data. The results suggest that GridSearchCV improves the efficacy of various machine-learning models. The performance assessment in the research was conducted using accuracy, F1 score, and AUC score. Using GridSearchCV, the majority of models maintained their accuracy. Nevertheless, the accuracy of the Decision Tree and Random Forest has improved, with the Random Forest experiencing a +0.0492 increase. KNN experienced a modest boost of +0.0128, while Decision Tree and Random Forest experienced considerable enhancements (+0.0733 and +0.0414, respectively) in the F1 Score, which exhibited the most variability. GridSearchCV demonstrated marginal improvements in the AUC Score of Random Forest (+0.0185) and SVC (+0.0039). Conversely, XGBoost experienced a slight decrease in its AUC Score (-0.0038), while KNN experienced a slight decrease of -0.0114. The results suggest that GridSearchCV improves the efficacy of these models.