Hybrid Artificial Intelligence-Based Algorithm Design For Cardiovascular Disease Detection

Abstract

Objective: Cardiovascular Disease (CVD) is a disease that negatively affects the blood vessel system due to plaque formation as a result of accumulation on the inner wall of the vessels. In the diagnostic phase, angiography results are evaluated by physicians. New diagnostic algorithms based on artificial intelligence, including new technologies, are needed for diagnosing CVD due to the time-consuming and high cost of diagnostic methods. 
 Materials and Methods: The heart disease dataset available on the open-source sharing site Kaggle was used in the study. The dataset includes 14 clinical findings. In the study, after the features were selected with the Fischer feature selection algorithm, they were classified with Ensemble Decision Trees (EDT), k-Nearest Neighborhood Algorithm (kNN), and Neural Networks (NN). A hybrid artificial intelligence algorithm was also created using the three methods. 
 Results: According to the classification results, EDT %96.19, kNN %100, NN %86.17, and hybrid artificial intelligence determined CVD with a %99.3 success rate. 
 Conclusion: According to the obtained results, it is evaluated that the proposed CVD diagnosis hybrid artificial intelligence algorithms can be used in practice