CHRONIC KIDNEY DISEASE DETECTION USING MACHINE LEARNING

Chronic Kidney Disease (CKD) is a progressive disorder that leads to kidney function deterioration over time. It is a common complication among individuals living with Human Immunodeficiency Virus (HIV), largely due to direct viral effects, antiretroviral therapy (ART) toxicity, and coexisting metabolic disorders. Traditional diagnostic methods rely on estimated Glomerular Filtration Rate (eGFR), serum creatinine levels, and urine albumin-to-creatinine ratio; however, these methods often fail to provide early-stage predictions with high accuracy. This study explores the application of Machine Learning (ML) models to classify CKD stages in HIV-infected patients based on clinical and laboratory data. Various ML techniques, including Decision Trees, Random Forest, Support Vector Machines (SVM), Gradient Boosting, and Deep Learning models, are assessed for their predictive performance. The dataset comprises HIV-infected patient records with features such as serum creatinine, blood urea nitrogen (BUN), proteinuria levels, and demographic attributes. Feature importance analysis reveals key biomarkers influencing CKD progression. Keywords: Chronic Kidney Disease (CKD), HIV, Machine Learning, Artificial Intelligence, Stage Identification, Predictive Analytics, Renal Dysfunction, Nephrology, Deep Learning, Early Diagnosis