Risk Prediction Models for Contrast-associated Acute Kidney Injury After Percutaneous Coronary Intervention: A Systematic Review

Abstract

The aim of this review was to systematically review published studies on risk prediction models for contrast-associated acute kidney injury (CA-AKI) in patients with ST-segment elevation myocardial infarction (STEMI) after percutaneous coronary intervention (PCI). We searched PubMed, Embase, Web of Science, Scopus, Medline, Cumulative Index to Nursing and Allied Health Literature (CINAHL), and Chinese databases from inception to July 1, 2024. The Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) was used to extract data and The Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias and applicability. A total of 2784 publications were retrieved; 16 studies were included. The models’ area under the curve (AUC) or C-index ranged from 0.719 to 0.877. Commonly used predictors included age, diabetes, Killip class, and use of intra-aortic balloon pump (IABP). Thirteen studies were determined to be at high risk of bias, while three were unclear, but their applicability was satisfactory. The models’ clinical utility was still up for debate. Future development or validation of models should focus on methodology and combine machine learning and natural language processing to analyze data to improve the predictive ability and clinical applicability of models.