Key result
Eight-variable model predicts acute kidney injury in STEMI with ~0.85 AUC.
Why the study?
Acute kidney injury is a frequent complication in patients with acute ST-segment elevation myocardial infarction associated with adverse in-hospital outcomes, and early identification of high-risk patients via a practical prediction model may facilitate timely prevention and individualized management.
Observational (n=265)
No
Answers are grounded in this paper and cite their sources.
A clinical prediction model incorporating age, diabetes, cardiac and renal function, hemodynamic status, albumin, and emergency PCI showed good discrimination (AUC 0.851) for identifying acute STEMI patients at high risk of in-hospital acute kidney injury.
Acute kidney injury is a frequent and clinically significant complication in patients with acute ST-segment elevation myocardial infarction and is associated with adverse in-hospital outcomes. Early identification of high-risk patients may facilitate timely prevention and individualized management. This study aimed to investigate the clinical risk factors for acute kidney injury in patients with acute ST-segment elevation myocardial infarction and to develop a practical prediction model. This retrospective study included consecutive patients with acute ST-segment elevation myocardial infarction treated at our institution between January 2022 and December 2025. Acute kidney injury was defined according to the Kidney Disease: Improving Global Outcomes criteria. Demographic data, comorbidities, admission clinical characteristics, laboratory findings, imaging parameters, and treatment-related variables were collected. Univariate and multivariable logistic regression analyses were performed to identify independent predictors of acute kidney injury. A logistic regression model was subsequently established, and its performance was assessed using receiver operating characteristic curve analysis. A total of 265 patients were included, of whom 58 (21.9%) developed acute kidney injury during hospitalization. Multivariable logistic regression analysis identified age ≥65 years, diabetes mellitus, Killip class III–IV, cardiogenic shock, left ventricular ejection fraction <50%, serum creatinine >100 μmol/L, and albumin <38 g/L as independent risk factors for acute kidney injury, whereas emergency percutaneous coronary intervention was an independent protective factor. The prediction model constructed from these variables showed good discrimination, with an area under the curve of 0.851 (95% confidence interval: 0.797–0.905). At the optimal cutoff value of 0.238, the sensitivity and specificity were 79.3% and 78.7%, respectively. Acute kidney injury in patients with acute ST-segment elevation myocardial infarction was independently associated with advanced age, diabetes mellitus, impaired cardiac and renal function, hemodynamic instability, and hypoalbuminemia. The proposed logistic prediction model demonstrated good predictive performance and may be useful for early risk stratification in clinical practice.
No takes yet. Share an insight, caveat, or question.
Qiao et al. (2026) conducted an observational in Acute ST-segment elevation myocardial infarction (n=265). Multivariable logistic regression prediction model for acute kidney injury was evaluated on Acute kidney injury during hospitalization (KDIGO criteria) (AUC 0.851, 95% CI 0.797-0.905). A logistic prediction model incorporating 8 clinical variables predicted acute kidney injury in STEMI patients with an AUC of 0.851.
Synapse has enriched 10 related papers. Consider them for comparative context: