Effect of Parameter Selection on Heart Attack Risk Prediction in an RNN Model

Abstract

Heart attack has become a significant public health issue worldwide, and effective prediction methods, along with early diagnosis, are crucial for the prevention and treatment of this disease. Various machine learning and deep learning techniques have been employed in the literature to predict the risk of heart attack. In this study, the evaluation of heart attack risk was conducted using the Recurrent Neural Network (RNN) classification method with different parameters. By considering various parameters that affect the performance of the RNN model, the impact of proper parameter selection on classification accuracy was investigated. During the data preprocessing stage, the data was appropriately standardized, and 5-fold cross-validation was performed. Eleven RNN models were compared by altering different parameters such as the number of units, the number of training cycles, batch size, dropout rate, activation function, and number of units in the dense layer. The classification performance was evaluated using metrics such as accuracy, precision, recall, and F1 score. The results demonstrate that parameter selection influences the performance of the RNN classification model and that performance improvements can be achieved with appropriate parameter selections.