کنفرانس بین المللی فناوری اطلاعات و دانش

صفحه اصلی / شانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

An Optimized GBDT-Based Model Using SMOTE for Effective Diagnosis of Coronary Heart Disease

نویسندگان :

Elahe Moradi¹ Mohammad Javadian²

1- دانشگاه آزاد اسلامی واحد شهرر 2- دانشگاه شهید بهشتی

کلمات کلیدی :

Gradient Boosting،SMOTE،Machine Learning

چکیده :

In recent years, artificial intelligence (AI) techniques have played an important role in the timely diagnosis and treatment of various diseases. Early diagnosis of diseases significantly improves recovery outcomes and reduces medical expenses. Of them, coronary heart disease (CHD) continues to rank among the world's top causes of death. A publicly accessible CHD dataset from Kaggle, which exhibits an imbalanced class distribution, is utilized in this work. To solve this problem, the dataset is balanced by leveraging the Synthetic Minority Oversampling Technique (SMOTE). Subsequently, a Gradient Boosting Decision Tree (GBDT)-based model is developed for CHD diagnosis and compared with several machine learning methods, including Support Vector Classifier (SVC), Adaptive Boosting (AdaBoost), and Linear Discriminant Analysis (LDA). The GBDT model consistently delivers superior results in predictive performance compared to the other approaches. Furthermore, Bayesian optimization is applied for hyperparameter tuning, enhancing the model’s accuracy to 93.05%. All experiments and simulations are conducted using Python.