Prediction of Bailout Mechanical Circulatory Support Use for Hemodynamic Collapse During Percutaneous Coronary Intervention (PCI): The ORACLE Score
Authors' conclusion
ORACLE is a simple score to estimate the risk of bailout MCS use for hemodynamic collapse during PCI, which may support preprocedural risk assessment.
Study context
- Population
- Consecutive patients undergoing PCI at a tertiary hospital between 2018 and 2025, after excluding cases of salvage PCI and procedures performed with pre-existing or prophylactic mechanical circulatory support (MCS); external validation in PCIs from the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) registryderivation cohort, external validation performed in 214,877 PCIs · Derivation cohort 6,931 · External validation, BMC2 registry (PCIs) 214,877
- Participants
- 6,931 patientsEvents: 1.4% in the derivation cohort
- Predictors
- Non-elective presentation, systolic blood pressure, chronic heart failure, prior PCI, rotational/orbital atherectomy, and left main PCI; multivariable Firth logistic regression model translated into a simplified integer-based risk score (ORACLE)
- Predicted outcome
- Bailout MCS use for hemodynamic collapse during PCI
Methodological detailsconsecutive patients, tertiary hospital, multivariable Firth logistic regression model, internally validated, simplified integer-based risk score
- Consecutive patients
- Tertiary hospital
- Multivariable Firth logistic regression model
- Internally validated
- Simplified integer-based risk score
Model performance
As reported in the abstract
AUC
Regression model, derivation cohort
0.817; 95% CI 0.774-0.860
Regression model, external validation cohort
0.761; 95% CI 0.753-0.770
ORACLE score, derivation cohort
0.791
ORACLE score, external validation cohort
0.718
Further findings
Observed bailout MCS rates by ORACLE risk category
- Low-risk category
- 0.4%
- High-risk group
- 8.7%
- With similar findings in the external validation cohort
Discrimination across clinically relevant subgroups
- Discrimination was consistent across clinically relevant subgroups
Negative predictive value
- Negative predictive value in both the derivation and external validation cohorts
- >99%
Original publication
Prediction of Bailout Mechanical Circulatory Support Use for Hemodynamic Collapse During PCI: The ORACLE Score. Circ Cardiovasc Interv. Published 3 November 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →