Developing a supervised machine learning model for predicting perioperative acute kidney injury in arthroplasty patients.

Background: Perioperative acute kidney injury (AKI) is challenging to predict and a common complication of lower limb arthroplasties. Our aim was to create a machine learning model to predict AKI defined by both serum creatinine (sCr) levels and urine output (UOP) and to investigate which features are important for building the model. The features were divided into preoperative, intraoperative, and postoperative feature sets.

Perioperative acute kidney injury and urine output in lower limb arthroplasties.

Background: This study aimed to evaluate the occurrence and perioperative risk factors of acute kidney injury (AKI) in primary elective hip and knee and emergency hip arthroplasty patients. We also aimed to assess the effect of urine output (UOP) as a diagnostic criterion in addition to serum creatinine (sCr) levels. We hypothesized that emergency arthroplasties are prone to AKI and that UOP is an underrated marker of AKI.