Machine learning-based prediction of ischemic cardio-cerebrovascular events after endovascular or microsurgical treatment of unruptured intracranial aneurysms and risk stratification by the early post-treatment triglyceride-glucose index

1

The study aimed to predict ischemic cardio-cerebrovascular events (ICCEs) within 6 months post-treatment for unruptured intracranial aneurysms (UIAs).
2

A total of 1,954 patients with UIAs were analyzed, with 240 experiencing ICCEs, highlighting the significant risk following treatment interventions.
3

The CatBoost model demonstrated the highest predictive accuracy for ICCEs, achieving an accuracy of 0.875 and an AUROC of 0.945.
4

The early post-treatment triglyceride-glucose (TyG) index was identified as a significant predictor, with each 1-unit increase correlating to a 2.61-fold increased risk of ICCEs.
5

The findings suggest that the TyG index could serve as a practical metabolic indicator for personalized perioperative risk assessment in UIA patients.

1