The following is a summary of “Prognostic model for aneurysmal subarachnoid hemorrhage patients requiring mechanical ventilation,” published in the July 2023 issue of Critical Care by Wan et al.
Aneurysmal subarachnoid hemorrhage (aSAH) is a serious condition that can lead to death or disability. People requiring mechanical ventilation after an aSAH have difficulty predicting long-term outcomes.
Researchers performed a retrospective study to develop a least absolute shrinkage and selection operator (LASSO)-penalized cox regression model for predicting prognosis in mechanically ventilated aSAH patients using common clinical variables. The study used data from the Dryad Digital Repository and applied LASSO regression to select relevant features.
Multiple cox proportional hazards analyses were conducted on the training set to create a predictive model. The model’s accuracy and discriminative power were assessed using receiver operating characteristics and calibration curves. Clinical utility was evaluated through Kaplan-Meier and decision curve analyses (DCA).
Nomoprogram included independent prognostic factors, including the simplified acute physiology score 2, early brain injury, rebleeding, and intensive care unit stay length. The training set showed strong predictive accuracy, with area under the curve values of 0.82, 0.81, and 0.80 for 1-, 2-, and 4-year survival predictions, respectively. The nomogram demonstrated excellent discrimination ability and calibration in the validation set. Additionally, decision curve analysis confirmed its clinical usefulness. Furthermore, a web-based version of the nomogram was created.
The study concluded that, the model predicts long-term outcomes for aSAH patients on ventilation that aids in individualized interventions and improves patient care.