Acute kidney injury is a common complication in hospitalized patients，and it has both short-and long⁃term consequences. To improve patient outcomes，methods for identifying patients at risk for acute kidney injury and diagnosing subclinical acute kidney injury must be developed. Rapid advances in risk estimation in acute kidney injury have been enabled by advances in clinical informatics and the growing popularity of electronic medical records. We summarize the research progress of acute kidney injury risk prediction from four perspectives in this review：Biomarkers，risk scores，automatic electronic alerts，and artificial intelligence.

"> acute kidney injury, risk prediction, biomarkers, risk scores, automated electronic alerts, artificial intelligence