A Hybrid Machine Learning Framework for Early Diagnosis of Chronic Diseases

Abstract

Abstract

The integration of machine learning (ML) in healthcare has revolutionized diagnostic capabilities by enabling early detection of complex diseases. This study presents a novel hybrid ML framework that combines ensemble learning with deep neural networks for the early diagnosis of chronic illnesses such as diabetes, cardiovascular disease, and chronic kidney disease. The model was trained and validated on publicly available datasets from the UCI Machine Learning Repository. Results demonstrate a significant improvement in prediction accuracy (up to 94.3%) compared to traditional algorithms. The study highlights the potential of hybrid ML techniques in transforming clinical decision-making and improving patient outcomes.