AI and Machine Learning Approaches for Chronic Kidney Disease Progression: A Systematic Review

Abstract

Chronic Kidney Disease also known as CKD is a health issue of the global significance with millions of affected clients across the globe. They result in early CKD progression prediction and monitoring, which is vital for better patient prognosis and inequalities’ decrease with concern to healthcare expenses. Over time however, the terms’ AI and ML have become revolutionary technologies in healthcare by providing better methodologies to diagnose CKD progression with high efficiency. This systematic review therefore aims to use a wide NM touched algorithm, dataset, prediction technologies, and outcomes in relation to AI and ML to define their role in the progression of CKD. Thus, this review focuses on the identification of the state of the art and outstanding issues for future study based on the evaluation of strengths and weaknesses of the different approaches presented in twelve fundamental research papers. Notable methodologies include neural networks, decision trees, and ensemble methods, with datasets sourced from public health databases and clinical trials. Results demonstrate significant improvements in predictive accuracy and robustness; however, challenges remain in terms of data heterogeneity, model interpretability, and clinical integration. This paper concludes by advocating for more comprehensive datasets and explainable AI approaches to enhance CKD prediction and management.