Objective To compare the value of two models in predicting the risk of post-neurosurgical nausea and vomiting (PONV). Methods A total of 652 patients undergoing elective neurosurgery were selected as the study subjects. The risk of postoperative nausea and vomiting in patients was predicted using the post-neurosurgical nausea and vomiting (PNSNV) prediction model and the Apfel score prediction model, respectively. The incidence of nausea and vomiting events within 24 hours after surgery was recorded, and the predictive efficacy of the two models for PONV in neurosurgical patients was evaluated. Results The incidence of PONV in patients was 30.83%. The Youden index of the Apfel prediction model was 0.189, and the area under the receiver ope-rating characteristic curve was 0.627 (95% CI 0.588-0.664); the Youden index of the PNSNV prediction model was 0.335, and the area under the receiver operating characteristic curve was 0.727 (95% CI 0.691-0.761). Conclusion The PNSNV prediction model has better overall predictive performance than the Apfel score model.