Abstract: Electrolyte disorders in chronic kidney disease patients are critical issues in nephrology research, with hyperkalemia being one of the most life-threatening electrolyte disturbances. This review examines the risk factors for hyperkalemia in chronic kidney disease patients, compares the differences in predictive models constructed by traditional statistical methods and machine learning approaches, and analyzes the predictive performance of various models in depth, aiming to provide a theoretical basis for the development of more precise risk prediction tools for clinical applications.

Key words: Chronic kidney disease, Hyperkalemia, Machine learning, Prediction model