A Hybrid CNN-LSTM Approach for Enhanced Prediction of Chronic Kidney Disease Using Deep Learning and Big Data

Abstract

Chronic Kidney Disease (CKD) is a significant global health issue requiring timely diagnosis and intervention. Traditional approaches have shown limitations in predictive accuracy and scalability, particularly when dealing with large-scale datasets. This study proposes a hybrid framework that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks for CKD prediction, augmented by the Map Reduce distributed computing paradigm to handle big data. Detailed algorithms and mathematical models are presented to explain the architecture and functionality, and diagrams are included to visualize data processing and model workflow. Experimental results highlight the framework’s superior performance, achieving a prediction accuracy of 94% with significant reductions in processing time.