Develop a hybrid improved support vector machine with population and fitness-based eagle optimization technique to detect heart disease at an early stage

Addressing the patterns of rising Chronic Diseases (CD) presents substantial challenges for healthcare systems globally. Moreover, the enormous quantities of data gathered by the healthcare sector have the potential to be valuable for decision-making, diagnosis, and data processing. The diagnosis of cardiovascular diseases (CDs) has been enhanced by utilizing developments in Support Vector Machine (SVM) algorithms, which learn from past datasets. This work introduces a hybrid optimization strategy called Population and Fitness-based Eagle Optimization (PF-EO) for selecting optimal characteristics and categorizing CD. The goal is to enhance the effectiveness and reliability of the strategies. When employing the WEKA data mining tool in the current methodology, decision trees yielded favorable outcomes.