Heart Attack Classification with a Machine Learning Approach Based on the Random Forest Algorithm

Authors : Süleyman Dal, Necmettin Sezgin

Pages : 140-147

Doi:10.17694/bajece.1691905

View : 123 | Download : 198

Publication Date : 2025-06-30

Article Type : Research Paper

Abstract :Heart attack diagnosis delays constitute a critical health problem that increases the risk of mortality. Timely and accurate identification of cardiac events is therefore essential to improve patient outcomes and reduce preventable deaths. This study aims to develop a random forest based classification model using the Heart Disease Classification dataset published on the Kaggle platform to support early diagnosis. This dataset consists of 1319 samples and 8 demographic, clinical and biochemical features for the diagnosis of heart disease. To evaluate the model’s reliability and generalizability, a 10-fold cross-validation technique was employed. Through this method, each data instance contributed to both training and testing phases, enabling a more stable and robust performance assessment. This approach also reduced the risk of overfitting and ensured more representative evaluation metrics. The performance of the model was evaluated with ROC curve, training-validation curves, confusion matrix. In the evaluation process, especially in Fold 6, 100% accuracy, precision, recall and F1 score were obtained and it was revealed that the model showed superior performance in the classification task. In addition, as a result of the feature importance analysis, it was determined that troponin, potassium (kcm) and age variables came to the forefront in the decision process. This study aims to fill an important gap in the literature in terms of both strong classification performance and interpretability in the field of machine learning models for heart attack diagnosis.
Keywords : Kalp Krizi Sınıflandırması, Makine Öğrenmesi, Random Forest Algoritması, Klinik Karar Destek Sistemleri

ORIGINAL ARTICLE URL