AI-coronary CTA beats GRACE score for 1-year MACE after emergency PCI for STEMI

In a 92-patient prospective STEMI cohort, an AI-driven coronary CTA model predicted 1-year MACE (AUC 0.876) significantly better than the GRACE score (AUC 0.742, p=0.012). Key predictors included total plaque volume >400 mm3, low-attenuation plaque, and LV end-diastolic volume c…

• Prospective cohort: n=92 consecutive STEMI patients with AI-assisted CCTA within 7 days post-emergency PCI; 1-year MACE rate was 25%.
• AI-CCTA model sensitivity/specificity: 87.0%/79.7%; strong negative predictive value (93.6%) may help de-escalate follow-up.
• Single-center study; small sample size and lack of external validation limit generalizability.

RadPigeon summaries are original and for information only. They are not clinical advice.