Objective To identify the risk factors for postoperative delayed weaning in patients with intracerebral hemorrhage and to establish a predictive model. Methods A retrospective study was conducted on 207 patients who underwent surgery for intracerebral hemorrhage at the intensive care unit (ICU) of Peking University People's Hospital from October 2014 to October 2021. Utilizing the 2007 European Respiratory Society consensus criteria, patients were divided into delayed weaning group (n=66) and non-delayed weaning group (n=141). The demographic and operation-related conditions of the two groups were compared. Multiple logistic regression analysis was employed to identify the risk factors for delayed weaning, and a risk assessment nomogram was constructed and validated. Results Compared with the non-delayed weaning group, the delayed weaning group exhibited a significantly higher proportion of comorbid cardiovascular and cerebrovascular diseases, a lower Glasgow coma scale (GCS) score on admission, a greater incidence of preoperative brain herniation, a higher proportion of patients undergoing emergency surgeries and decompression craniotomies, and higher postoperative APACHE Ⅱ score, GCS score, incidence of atelectasis, weaning failure rate and mortality rate, and longer ICU stay and hospital stay (P<0.05). Multiple logistic regression analysis indicated that emergency surgery, low postoperative oxygenation index, low postoperative score of highest GCS before weaning, and incidence of atelectasis were independent risk factors for postoperative delayed weaning (P<0.05). A nomogram predictive model was established using these four predictors, with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.855(95%CI 0.804-0.907), and the Hosmer-Lemeshow test showed good model fit (P=0.659). Conclusions Postoperative delayed weaning is associated with extended durations of mechanical ventilation, ICU stay, and hospital stay, as well as an increased risk of weaning failure and in-hospital mortality rate. The nomogram model provides valuable insights for the early recognition of patients at high risk for postoperative delayed weaning, thereby facilitating timely adjustment in ventilation management strategies.