For many years, heart disease has been the leading cause of death worldwide. This highlights the urgent need for reliable, practical methods for early detection of heart disease for early treatment. In the healthcare system, data mining has become a widely used tool for handling massive amounts of data. Researchers are using various data mining and machine learning techniques to analyze complex medical datasets, helping healthcare professionals address heart disease earlier. This study uses different supervised learning to build models for heart conditions. The analysis makes use of a dataset called Cleveland from UCI Machine Learning Repository, which has 303 entries and 76 characteristics. However, only 14 critical attributes are chosen for model evaluation to ensure meaningful performance comparisons. The prime goal of this research is to estimate the likelihood of heart disease in patients. Hybrid techniques such as naïve bayes, support vector machine, and knn can improve prediction performance beyond traditional algorithms.
Madbouly, A. (2025). Effective Heart Disease Diagnosis Accuracy Through Hybrid Machine Learning methods. Advances in Basic and Applied Sciences, 5(1), 29-37. doi: 10.21608/abas.2025.411130.1074
MLA
Ahmed Madbouly. "Effective Heart Disease Diagnosis Accuracy Through Hybrid Machine Learning methods", Advances in Basic and Applied Sciences, 5, 1, 2025, 29-37. doi: 10.21608/abas.2025.411130.1074
HARVARD
Madbouly, A. (2025). 'Effective Heart Disease Diagnosis Accuracy Through Hybrid Machine Learning methods', Advances in Basic and Applied Sciences, 5(1), pp. 29-37. doi: 10.21608/abas.2025.411130.1074
VANCOUVER
Madbouly, A. Effective Heart Disease Diagnosis Accuracy Through Hybrid Machine Learning methods. Advances in Basic and Applied Sciences, 2025; 5(1): 29-37. doi: 10.21608/abas.2025.411130.1074
)
View on SCiNiTO