Aneurysmal subarachnoid hemorrhage (aSAH) is a life-threatening medical condition with a high fatality and morbidity rate. There was a substantial link between the modified Fisher grade of aSAH and the neurological function deficit. This study aimed to analyze the factors associated with the modified Fisher grade of aSAH using a machine learning approach.
A multi-center observational study was conducted. The patients with aSAH were recruited from five tertiary hospitals in China. The volume of hemorrhage in aSAH was measured using the modified Fisher grade scale. The risk factors responsible for the modified Fisher grade of aSAH were analyzed, which include sociodemographic factors, clinical factors, blood index, and ruptured aneurysm characteristics. We built several tree-based machine learning models (XGBoost, CatBoost, LightGBM) for prediction and used grid search to optimize model parameters. To comprehensively evaluate the model, we used Accuracy, Precision, Area Under the Receiver Operating Characteristic Curve (AUROC), Area Under the Precision-Recall Curve (AUPRC), and Brier as evaluation indicators to assess the model performance and select the best model.
A total of 888 patients with aSAH were recruited, of whom 305 with modified Fisher grade of 3 and 4. The results show that the XGBoost model has the highest AUROC of 0.772, and the indicators are better than CatBoost and LightGBM. The feature importance graph shows that the top feature variables include platelet, thrombin time, fibrinogen, preadmission systolic blood pressure, activated partial thromboplastin time, and the time interval between the onset of aSAH and the first-time CT examination.
The factors responsible for the modified Fisher grade of aSAH were identified, which offered valuable insights for future research and clinical intervention. These risk factors should be controlled in the treatment of unruptured aneurysms, and appropriate treatment can be given if necessary to reduce the risk of severe hemorrhage after aneurysm rupture.