• Vivek Nandanwar
• Hrigved Parundekar

A study of 6 machine learning models for heart disease prediction found that gradient boosting classifier (GBC) achieved the highest average F1 score of 97.15%, followed by logistic regression (LR) with 83.89%. GBC was also the most accurate model across 10 different folds of the data, suggesting that it is not overfitting. Additionally, GBC was the most accurate model for all age groups, gender, and chest pain types. KNN was the most accurate model for patients with high blood pressure, while Naive Bayes was the most accurate model for patients with high cholesterol and SVC-RBF was the most accurate model for patients with diabetes. The findings suggest that machine learning can be used to effectively predict heart disease, and that GBC is a promising model for this purpose. Further research is needed to investigate the suitability of different machine learning models for different types of patient.

Machine learning, Heart disease, Prediction, Cross-validation, F1-Score, RMSE, Gradient boosting classifier, Logistic regression, K nearest neighbors(KNN), Naive Bayes, Support vector classifier (RBF), Age, Gender, Chest pain type, heart disease, High blood pressure, High cholesterol, Diabetes Support Vector Classifier with Radial Basis Function (SVC-RBF), gradient boosting, K Nearest Neighbors (KNN), naive Bayes, and Artificial Neural Network (ANN).

"The Effect of Cross-Validation on the Performance of Machine Learning Models for Predicting Heart Disease", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 8, page no.d75-d80, August-2023, Available :http://www.jetir.org/papers/JETIR2308309.pdf

"The Effect of Cross-Validation on the Performance of Machine Learning Models for Predicting Heart Disease", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 8, page no. ppd75-d80, August-2023, Available at : http://www.jetir.org/papers/JETIR2308309.pdf