<![CDATA[Heart disease, a major global cause of mortality, necessitates a swift and precise diagnostic approach for effective prevention and management. In the era of information technology, probabilistic comparison methods such as Naïve Bayes and KNN offer a fresh perspective on assessing the risk and diagnosis of heart disease. This research, based on a dataset of 300 records with 14 attributes indicating the presence of heart disease, implements and compares these algorithms. The study reveals that Naïve Bayes, with or without normalization, achieves an accuracy of 92.67%, while normalized KNN outperforms with 93.33% accuracy, compared to 79.33% without normalization. Conclusively, the study supports the significant potential of probabilistic data analysis methods, emphasizing the integration of these techniques in the healthcare system for more accurate risk classification, early detection, and efficient management of heart disease.]]>
Copyrights © 2024
