Early prediction of chronic diseases using deep learning models assimilated with compound feature selection techniques

Abstract

newline Chronic Kidney Disease (CKD), Liver Disease (LD), and newlineCardiovascular Disease (CVD) represent significant health challenges newlineglobally. CKD, characterized by a gradual loss of kidney function, can lead newlineto severe complications if not managed effectively. CVD, encompassing a newlinerange of heart and blood vessel disorders, remains a leading cause of newlinemortality worldwide. LD, including conditions like hepatitis and cirrhosis, newlinecritically impairs liver function and can have profound health implications. newlineEarly detection and management of these diseases are vital for improving newlinepatient outcomes and reducing the burden on healthcare systems. This newlineresearch explores the capabilities of Machine Learning (ML) as well as Deep newlineLearning (DL) techniques for early detection of CKD, LD, and CVD. Early newlinedetection of these diseases is critical, as timely intervention can significantly newlinereduce mortality rates. By harnessing the advanced analytical capabilities of newlineML and DL, the research aims to enhance the predictive accuracy for these newlinediseases, thereby contributing to improved healthcare outcomes. The newlinefindings of this research have the potential to revolutionize diagnostic newlineapproaches in the healthcare sector, offering a proactive strategy in managing newlineand mitigating the risks associated with CKD, LD, and CVD.