عليرضا والهي

In today's world, numerous diseases specifically target human health. Although many of these illnesses such as smallpox, plague, and rabies—now have definitive treatments, there are still certain physical and mental conditions for which, despite recent advancements in healthcare, no reliable and effective treatment has been developed yet. Consequently, extensive research is being conducted in this field. Coronary artery disease is one such condition. These diseases are among the leading causes of death worldwide. Early and accurate diagnosis plays a crucial role in either treating or reducing the complications and medical costs associated with coronary artery disease. This study aims to analyze data from patients suffering from coronary artery disease using machine learning algorithms. A total of 625 CT angiography results from patients referred to the imaging laboratory of Milad Hospital in Tehran were used in this research. Four algorithms—Decision Tree, Random Forest, Support Vector Machine, and Artificial Neural Network—were employed to analyze the data. The results obtained from implementing and eva‎luating these machine learning models demonstrate their high capability in predicting the likelihood of disease occurrence and in recommending treatment plans for patients with coronary artery disease. eva‎luation metrics such as accuracy, sensitivity, and F1-score were used to assess model performance, and the selected algorithms were reported based on these criteria. The findings indicate that some models, particularly Random Forest and Neural Network (Multilayer Perceptron), offer more accurate predictions. The application of various machine learning methods can serve as a valuable supplementary tool in the diagnosis and treatment process of heart diseases, assisting doctors and medical specialists in decision-making. Finally, this research provides recommendations for improving model performance and directions for future studies.

الگوريتم هاي يادگيري ماشين , بيماري عروق كرونري قلب , سي تي آنژيوگرافي , درخت تصميم , جنگل تصادفي , ماشين بردار پشتيبان , شبكه عصبي

Machine Learning Algorithms , Coronary heart disease , CT Angiography , Decision tree , Random forest , Support vector machine , Neural network

Alireza Valehi

Rouzbeh Ghousi