BACKGROUND Sarcopenia is a common complication in maintenance hemodialysis (MHD) and can increase patient hospitalization and mortality. No simple and reliable tools to identify sarcopenia exist. We aimed to develop a screening tool to predict MHD patients at high risk for sarcopenia. MATERIAL AND METHODS This cross-sectional study included 589 and 216 MHD patients for training and validation sets, respectively. We used diagnostic criteria developed by the Asian Working Group on Sarcopenia to screen for sarcopenia. The risk prediction model was established by univariate and multivariate logistic regression analyses. We used the area under the receiver operating characteristic curve (AUROC), calibration curve, Hosmer-Lemeshow test, and decision curve analysis (DCA) to evaluate the model's discrimination ability, calibration ability, and clinical utility. RESULTS The incidence of sarcopenia was 17.1% in the training set and 18.1% in the validation set. We constructed prediction models applying age, body mass index, calf circumference, and serum creatinine and plotted a nomogram. The training set model had an AUROC of 0.922, sensitivity of 85.1%, specificity of 85.9%, and chi-square value (Hosmer-Lemeshow test) of 5.603 (P>0.05); the DCA diagram showed that when the threshold probability was 0 to 0.95, the model predicted a net benefit for sarcopenia in MHD patients. The validation set model had an AUROC of 0.913, sensitivity of 94.3%, specificity of 82.9%, and chi-square value (Hosmer-Lemeshow test) of 9.822 (P>0.05). CONCLUSIONS The screening tool has good discrimination ability, calibration ability, and clinical utility. It could help to identify MHD patients at a high risk for sarcopenia.