Abstract: Acute kidney injury (AKI) is a common complication in hospitalized patients, and is associated with poor outcomes and higher mortality. Early identifying AKI before function loss is crucial to reverse the injury. Therefore, establishing an early-warning system for AKI is essential for clinicians to make the diagnosis and treatment decisions earlier. With the development of artificial intelligence, a variety of electronic alerts and machine learning-based predictive models to predict the risks of AKI have been developed. In the current review, we summarize the advances in the electronic systems based on artificial intelligence for predicting AKI. 

Key words: Acute kidney injury; , Prediction model; , E-alert; , Machine learning