A nomogram for predicting the risk of tracheostomy following surgical procedures treatment of aneurysmal subarachnoid hemorrhage.

Objective: Effective and timely airway management is particularly crucial for recovery in patients with aneurysmal subarachnoid hemorrhage following surgical procedures treatment. This study aimed to develop a stable nomogram model to predict the likelihood of postoperative tracheostomy in these patients. Methods: The clinical data and imaging findings of 249 patients with aneurysmal subarachnoid hemorrhage (aSAH) by microsurgical clipping or endovascular treatment on admission from January 2021 to October 2023 were retrospectively analyzed. Least absolute shrinkage and selection operator (LASSO), logistic regression analyses, and a nomogram were used to develop the prognostic models. Receiver operating characteristic (ROC) curves and Hosmer–Lemeshow tests were used to assess discrimination and calibration. The bootstrap method (1,000 repetitions) was used for internal validation. Decision curve analysis (DCA) was conducted to evaluate the clinical validity of the nomogram. Results: The following four independent influencing factors were selected by LASSO-Logistic regression: the GCS score, preoperative pulmonary infection, operation method, and mechanical ventilation. The area under curve (AUC) was 0.928 in the training set and 0.878 in the internal validation set. Calibration curves and Hosmer–Lemeshow tests indicated that the nomogram demonstrated strong calibration ability. Additionally, the DCA curve revealed enhanced clinical utility of the nomogram. Conclusion: This study introduces a reliable and valuable nomogram model that is both applicable and user-friendly, facilitating accurate predictions of tracheostomy risk following surgical interventions for aneurysmal subarachnoid hemorrhage. This model aids clinicians in making timely and informed decisions, thereby significantly enhancing patient outcomes.