<![CDATA[Heart disease is a leading cause of global mortality, with its prevalence increasing annually. This study aims to develop a heart disease prediction model using a Multilayer Perceptron (MLP) combined with the SMOTE-ENN resampling technique to address data imbalance issues. The dataset used was obtained from the UCI Machine Learning Repository and includes patients' clinical and demographic features. The initial dataset consisted of [number of data] records, with an imbalanced class distribution between patients with and without heart disease. After applying SMOTE-ENN, the class distribution became more balanced, allowing the model to learn patterns more effectively. The MLP model was designed with two hidden layers comprising 64 and 32 neurons, respectively, using the ReLU activation function in the hidden layers and a sigmoid function in the output layer. Evaluation results showed that the model achieved an accuracy of 89.47%, precision of 77.78%, recall of 100%, and an F1-score of 87.5%. To validate the effectiveness of SMOTE-ENN, comparisons were made with other methods such as SMOTE and undersampling, as well as baseline models like Logistic Regression and Decision Tree. The results demonstrate that SMOTE-ENN outperforms other techniques in handling class imbalance, leading to better overall model performance.]]>
Copyrights © 2025
