Development and Validation of an Early Postoperative Risk Stratification Model for Hydrocephalus Following Aneurysmal Subarachnoid Hemorrhage

BACKGROUND: Hydrocephalus is a common complication after aneurysmal subarachnoid hemorrhage (aSAH). This study aimed to identify perioperative risk factors and develop an early postoperative risk stratification model to support postoperative monitoring rather than purely preoperative prediction. METHODS: Employing a retrospective case-control design, clinical data from 331 patients with aSAH treated at the First Affiliated Hospital of Henan Medical University between August 1, 2018, and December 31, 2024, were collected and analyzed. The primary endpoint was postoperative hydrocephalus occurring within 3 weeks after aneurysm treatment, diagnosed according to combined radiological and clinical criteria. The least absolute shrinkage and selection operator regression method was employed to screen risk factors. Multiple machine-learning models were compared, and Shapley additive explanations (SHAP) analysis was used for individualized model interpretation. RESULTS: The admission Glasgow Coma Scale score, intraoperative external ventricular drainage/lateral ventricular drainage, and intraventricular hemorrhage were identified as key variables associated with postoperative hydrocephalus. The logistic regression model emerged as the optimal model; locked test set area under the curve (95% CI): 0.891 (0.739-1.000); accuracy: 0.720 (0.688-0.775); sensitivity: 0.899 (0.823-0.987); specificity: 0.683 (0.635-0.740). CONCLUSION: The logistic regression model with SHAP-based interpretation may support early postoperative risk stratification for hydrocephalus after aSAH. Given its modest positive predictive value, the model should be used to triage patients for intensified monitoring and timely reassessment.