Objective To develop a nomogram prediction model for the risk of sarcopenia in maintenance hemodialysis (MHD) patients, aiming to provide a reference tool for the early clinical identification of high-risk individuals for sarcopenia. Methods A total of 110 patients who received regular MHD treatment at Yizheng People’s Hospital from January 1, 2024 to September 30 were included as the research subjects. They were divided into the non-sarcopenia group (83 cases) and the sarcopenia group (27 cases) based on whether they had sarcopenia The least absolute shrinkage and selection operator (LASSO) regression combined with multivariate Logistic regression was employed to screen the independent risk factors for sarcopenia in MHD patients. Subsequently, a nomogram model for predicting the risk of sarcopenia was constructed using the screened predictive variables. Results Finally, the four variables of age, white blood cell count (WBC), body mass index (BMI), and combined cardiac valve calcification (CVC) were selected as predictors to successfully establish a column-line graph prediction model for the risk of myasthenia gravis in MHD patients. Clinical decision curve analysis (DCA) indicated that when the predicted probability threshold of the nomogram model was between 0?0.78, the clinical net benefit level of patients was positive. The nomogram was internally validated by Bootstrap resampling 1 000 times. In the validated model, the Bias-corrected calibration curve was closer to the ideal state, and the calibration error was reduced, suggested that the model had good calibration and predictive consistency. Additionally, the area under the curve (AUC) value of the model before validation was 0.913 (95%CI: 0.857?0.972), and the AUC value after validation was 0.914 (95%CI: 0.862?0.971). The sensitivities before and after validation were 0.852 and 0.854, respectively, and the specificities were both 0.855. Conclusion The risk prediction nomogram model for sarcopenia in MHD patients constructed in this study has good discrimination and calibration, and can accurately and efficiently predict the risk of sarcopenia in this population, providing a quantitative reference for early clinical screening of high-risk patients.