Chronic Kidney Disease Prediction Using Deep Neural Network Architectures: A Comparative Study of ANN and CNN Approaches

Chronic kidney disease (CKD) is a major public health problem that requires early and accurate diagnosis for ef- fective treatment. This project compares a Convolutional Neural Network (CNN) and an Artificial Neural Network (ANN) for the prediction of Chronic Kidney Disease (CKD) using clinical and laboratory data. Both models undergo preprocessing, including missing value handling, normalization, oversampling for class imbalance, and feature selection. CNN uses convolutional layers for pattern recognition, while ANN uses a simpler architecture with selected features. The performance of the model is evaluated using accuracy, confusion matrices and classification reports. The study aims to identify the most effective approach for pre- dicting CKD, improving early diagnosis and optimizing patient outcomes.