USE OF ARTIFICIAL INTELLIGENCE IN RISK PREDICTION FOR ACUTE KIDNEY INJURY IN CLINICAL SETTINGS: A Scoping Review

This scoping review aims to analyze the extent of evidence regarding the application of artificial intelligence (AI) in predicting the risk of Acute Kidney Injury (AKI) in clinical settings. The guiding question of this study was structured following the mnemonic PCC: Population: patients without a diagnosis of AKI; Concept of interest: application of artificial intelligence models for risk prediction; Context: risk for AKI. Thus, the research question developed was: “How can artificial intelligence be used to predict the risk of developing Acute Kidney Injury?” Additionally, six specific questions were established. The literature search will be conducted across the following electronic platforms: PubMed, BVS, IEEE, and ACM. The studies resulting from the searches in the databases will be exported to the Rayyan software and selected in two phases based on previously established criteria. Stage I will consist of screening the articles based on their title and abstract, and Stage II will be carried out by reading the full text of the articles selected in Stage I. A qualitative synthesis will be provided based on the data selected in the studies. The extracted data will also be summarized in a descriptive table, containing concise answers to all the specific questions.