AIM: To develop a nomogram to predict the risk of visual impairment (VI) in patients with chronic kidney disease (CKD). METHODS: Totally 897 patients with CKD were selected from the National Health and Nutrition Examination Survey (NHANES). The training and validation sets were divided in a 7:3 ratio. Multivariate logistic regression and bidirectional stepwise regression was used to select the factor of developing nomogram. The performance of the nomogram was evaluated by receiver operator characteristic curve, calibration curve and decision curve analysis (DCA). RESULTS: Age, diastolic blood pressure, glucose, serum creatinine, income at or above poverty, and history of smoking were included in the nomogram. And the area under the receiver operating characteristic curve of the training and validation sets were 0.684 and 0.640, respectively. The fit of the model was demonstrated the calibration curve, and DCA showed the value of clinical application. CONCLUSION: The nomogram may help to screening the probability of VI in patients with CKD. Larger samples are needed to validate and improve the model to increase its efficacy.