Federated Learning for Kidney Disease Prediction using Combined LSTM and MLP Models

Kidney disease (KD) is a prevalent global health issue, and early prediction is critical for improving patient outcomes. In this study, we propose a federated learning approach that combines Long Short-Term Memory (LSTM) networks with Multi-Layer Perceptron (MLP) models for kidney disease prediction. The LSTM component captures temporal dependencies in the data, while the MLP enhances the model’s ability to classify based on learned features. The federated learning framework ensures data privacy by keeping patient information decentralized across multiple hospitals. Experimental results show promising accuracy, precision, recall, and F1 score, demonstrating the potential of combining LSTM and MLP for healthcare applications.