Objective To explore the risk factors of hypoxemia in patients during anesthesia recovery and construct a risk prediction model of hypoxemia. Methods A retrospective study was adopted, and 2810 patients in the anesthesia recovery period were selected as the modeling groupfrom February to October 2022. The relevant data were collected through the electronic medical record system, and the risk factors were analyzed using univariate analysis and logistic regression analysis. The nomogram model was drawn; selected 705 patients in the anesthesia recovery period as the validation group for model validationfrom November to December 2022. Results In the modeling group, 365 cases (12.99%) developed hypoxemia during the anesthesia recovery period. The results of logistic regression analysis showed that the surgical method, surgical site, surgical type, surgical level, surgical duration, smoking, and diabetes were risk factors for hypoxemia in patients during the anesthesia recovery period (all P<0.05). The area under the ROC curve of the validation group was 0.824 (95%CI:0.752,0.915), the Youden′s Index was 0.536, the sensitivity was 0.819, and the specificity was 0.717. The accuracy of model validation was 85.95%. Conclusion The nomogram risk prediction model for hypoxemia during anesthesia recovery has good predictive effect, which can provide a reference for medical staff in the anesthesia recovery room to identify high-risk groups of hypoxemia during anesthesia recovery early.