Investigators developed ORACLE to predict bailout mechanical circulatory support for haemodynamic collapse during PCI, using 6,931 patients and excluding salvage procedures and pre-existing or prophylactic support. Bailout support occurred in 1.4% of the derivation cohort; external validation included 214,877 PCIs. The full model’s external-validation AUC was 0.761 (95% confidence interval 0.753–0.770), while the simplified score’s AUC was 0.718. Observed bailout support rates ranged from 0.4% in the low-risk category to 8.7% in the high-risk category, with similar findings reported in external validation.
ORACLE provides externally validated risk stratification for bailout MCS use during PCI. These findings do not establish that score-guided planning improves patient outcomes.
Study limitation: The endpoint was bailout MCS use, not survival or benefit from score-guided management.
AI-generated from the published abstract with automated source checks. For research discovery; consult the original paper before applying findings.