Objective This study aimed to develop and validate a predictive model for sleep disorders in young and middle-aged adults with anemia, providing evidence for early identification, risk stratification, and individualized sleep management. Methods Data in the NHANES were analyzed and randomly divided into development and validation cohorts. LASSO regression was used to screen optimal predictors in the development cohort, followed by univariate and multivariate logistic regression to identify independent predictors and construct a nomogram. Model performance was evaluated using receiver operating characteristic curves, calibration curves, Brier scores, and decision curve analysis. Results The weighted prevalence of sleep disorders among young and middle-aged adults with anemia was 10.19%. Multivariate logistic regression identified seven independent predictors: sex, monocyte count, asthma, overweight, arthritis, congestive heart failure, and hypertension. The model showed good discrimination, with area under the curve values of 0.817 in the development cohort and 0.791 in the validation cohort. Calibration was satisfactory, with Brier scores of 0.074 and 0.075, respectively. Decision curve analysis indicated favorable clinical net benefit in both cohorts. Conclusion The proposed predictive model demonstrated good discrimination, calibration, and may help healthcare providers identify young and middle-aged adults with anemia who are at high risk for sleep disorders.