Development and Validation of a Clinical Prediction Model for Stages of Acute Kidney Injury in Critically Ill Patients.

Abstract

Introduction: Among critically ill patients, acute kidney injury (AKI) has a high incidence and leads to poor prognosis. As AKI is often only detected well after onset, early risk stratification is crucial. This study aimed to develop and internally validate the first clinical prediction model for different stages of AKI in critically ill adults.

Methods: We utilized data from the Simple Intensive Care Studies II (SICS-II), a prospective cohort study at the University Medical Center Groningen, the Netherlands. The prognostic outcome was the highest KDIGO-based stage of AKI within the first 7 days of ICU stay. Candidate predictors included fifty-nine readily available variables in critical care. Least absolute shrinkage and selection operator and proportional odds logistic regression were used for variable selection and model estimation, respectively. Receiver operating characteristic (ROC) curve, calibration plot, and decision curve analysis were applied to evaluate model performance and clinical usefulness.

Results: Of the SICS-II cohort, 976 patients were eligible for our analyses (median [interquartile range] age 64 [52-72] years, 38% female). Within 7 days after ICU admission, 29%, 23%, and 14% of patients progressed to their highest severity of AKI at stages 1, 2, and 3, respectively. We derived a 15-variable model for predicting this maximum ordinal outcome with an area under the ROC curve of 0.76 (95% CI, 0.74-0.78) in bootstrap validation. The model showed good calibration and improved net benefit in decision curve analysis over a range of clinically plausible thresholds.

Conclusion: Using readily available predictors in the ICU setting, we could develop a prediction model for different stages of AKI with good performance and promising clinical usefulness. Our findings serve as an initial step towards applying a valid and timely prediction model for AKI severity, possibly helping to limit morbidity and improve patient outcomes.