The invention provides a chronic kidney disease screening method and system, and particularly relates to a machine learning method for constructing a chronic kidney disease screening model, which comprises the steps of establishing an effective chronic kidney disease screening model, arranging user data to be screened, substituting the user data to be screened into the chronic kidney disease screening model for model calculation, and finally obtaining a kidney disease risk result. Therefore, the chronic kidney disease screening system is efficient, low in cost and high in accuracy. According to the method, a machine learning BP neural network, XGBoost and a random forest integration algorithm are adopted to train a chronic kidney disease screening model; high-risk groups with chronic kidney diseases can be automatically screened out according to basic body measurement information, symptom information, medical examination information, family history, past history, living habits and other data, and the accuracy reaches up to 0.96 or above.