Objective To develop and validate a risk prediction model for postoperative dysphagia in patients undergoing anterior cervical spine surgery to facilitate early identification and prevention.Methods A convenience sample of 371 patients who underwent anterior cervical spine surgery from January to December 2023 was used as the modeling cohort, and 111 patients who underwent the procedure from January to May 2024 as the validation cohort.Potential predictors of postoperative dysphagia were screened using LASSO regression.A risk prediction model and a nomogram were constructed in R language.Model performance was assessed by the area under the receiver operating characteristic curve (AUC) and model calibration assessed by using the Hosmer-Lemeshow goodness of fit test.Results Among the 371 patients in the modeling cohort, 107 developed dysphagia (incidence 28.84%).Multivariable logistic regression identified female sex, age ≥60 years, disease duration ＞8 months, upper level surgical segments, use of Zephir or Atlantis titanium fixation devices, anterior cervical soft tissue thickness ＞10 mm, and C2-7 angle change ＞5° as independent risk factors for postoperative dysphagia (all P＜0.05).Perioperative swallowing training was a protective factor (P＜0.05).The prediction model demonstrated good discrimination and calibration in both the modeling and validation cohorts:Hosmer-Lemeshow tests indicated acceptable fit (both P＞0.05), AUCs were 0.830 and 0.825, respectively.Conclusion The risk prediction model can predict the risk of dysphagia in patients undergoing anterior cervical spine surgery, which can provide a reference for healthcare professionals to develop early and targeted interventions.