Creatinine clearance in critically ill adults: prospective comparison of prediction by intensive care unit physicians and machine learning models.

This document is a letter published in the journal Intensive Care Medicine. The letter discusses the development and validation of prediction models for urinary creatinine clearance (CrCl) in critically ill adults. The models were compared to predictions made by intensive care unit (ICU) physicians. The study found that the CrCl predictors performed well and were comparable to the predictions made by physicians. The authors suggest that these predictors could potentially assist physicians at the bedside, but further research is needed to evaluate their impact on clinical outcomes. [Extracted from the article]