Prediction score project for the incidence of long-term cerebrovascular events among patients undergoing primary percutaneous coronary intervention: a retrospective study from the real world

Although the rates of long‑term outcome events are low, stroke is associated with high short- and long‑term mortality and adversely affects the quality of life of patients with a history of primary percutaneous coronary intervention (PCI).We sought to develop and validate a novel marker‑based risk score to improve stroke prognostication in patients with myocardial infarction (MI) undergoing primary PCI.A retrospective study was conducted to internally validate a new biomarker‑based risk score for the incidence of stroke in 4103 patients with MI undergoing primary PCI who were randomized into derivation and validation cohorts.Significant predictors of cerebrovascular events included age, history of atrial fibrillation, history of hypertension, and the target lesion involving branches. The models had good calibration and discrimination in both derivation and internal validation. The areas under the receiver operating characteristic curve for predicting cerebrovascular events were 0.826 (sensitivity, 84.78%; specificity, 65.18%) and 0.846 (sensitivity, 71.43%; specificity, 90.29%) for the derivation and validation cohorts, respectively, at the 5‑year follow‑up. We calculated the total risk score for each participant, and divided them into low- and high‑risk groups according to the median of the total risk score. A Kaplan-Meier survival analysis for the cohort showed significant differences in the total cohort (P <0.001) and derivation cohorts (P = 0.001).The prediction model was internally validated and calibrated in large cohorts of patients with MI receiving primary PCI therapy. This risk score allows re‑evaluation of the risk of cerebrovascular events in patients after primary PCI.