Zhang Z, et al. - Using a US-based critical care database, researchers intended to develop a model that can allow the prediction of volume responsiveness in acute kidney injury (AKI) cases and can be used to distinguish between volume-responsive (VR) and volume-unresponsive (VU) AKI. AKI patients with urine output < 0.5 ml/kg/h for the first 6 h following intensive care unit (ICU) admission and fluid intake > 5 l in the following 6 h were included. Cases treated with diuretics and had renal replacement on day 1 were excluded. For predicting urine output > 0.65 ml/kg/h during 18 h succeeding the initial 6 h for evaluating oliguria, they developed two predictive models, using either machine learning extreme gradient boosting (XGBoost) or logistic regression. Compared to a traditional logistic regression model, the XGBoost model enabled better differentiation between patients who would and would not respond to fluid intake in urine output.