Related Experiment Video
Updated: Feb 14, 2026
Ischemia-reperfusion Model of Acute Kidney Injury and Post Injury Fibrosis in Mice
Published on: August 9, 2013
Predicting recovery from acute kidney injury in critically ill patients: development and validation of a prediction
Theis S Itenov1, Rasmus Ehrenfried Berthelsen2, Jens-Ulrik Jensen3
1Department of Anaesthesiology, Nordsjællands Hospital, University of Copenhagen, Denmark. Theis.skovsgaard.itenov@regionh.dk.
Objective:
Intensive care unit (ICU) patients with acute kidney injury (AKI) who recover kidney function within 28 days experience less severe chronic kidney impairment and have increased long term survival. The aims of this study were to develop and validate a risk prediction model to identify these patients.
Design:
Observational study with development and validation of a risk prediction model.
Setting:
Nine academic ICUs in Denmark.
Participants:
Development cohort of critically ill patients with AKI at ICU admission from the Procalcitonin and Survival Study cohort (n = 568), validation cohort of adult patients with AKI admitted to two university hospitals in Denmark in 2012-13 (n = 766).
Interventions:
None.
Main Outcome Measures:
Recovery of kidney function was defined as living for 5 consecutive days with no renal replacement therapy and with creatinine plasma levels below 1.5-fold the levels determined before ICU admission.
Results:
A total of 266 patients (46.8%) recovered prior kidney function in the development cohort, and 453 patients (59.1%) in the validation cohort. The prediction model included elevation in creatinine, urinary output, sex and age. In the validation cohort, 69 patients (9.0%) had a predicted chance of recovery < 25%, and their observed rate of recovery was 21.5%. This observed rate of recovery was 81.7% among the 325 patients who had a predicted chance > 75%. The area under the receiver operations curves for predicting recovery in the validation cohort was 73.1%.
Conclusion:
We constructed and validated a simple model that can predict the chance of recovery from AKI in critically ill patients.
Related Concept Videos
02:27Predicting Molecular Geometry
01:22Acute Kidney Injury I: Introduction
01:29Acute Kidney Injury II: Pathophysiology
01:03Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
01:22Acute Kidney Injury VI: Nursing Management
01:20Acute Kidney Injury V: Interprofessional Care