Chao-Yuan Huang1, Fabian Güiza2, Greet De Vlieger1,2, Pieter Wouters2, Jan Gunst1,2, Michael Casaer1,2, Ilse Vanhorebeek1, Inge Derese1, Greet Van den Berghe1,2, Geert Meyfroidt3,4. 1. Laboratory of Intensive Care Medicine, Academic Department of Cellular and Molecular Medicine, Katholieke Universiteit Leuven, Louvain, Belgium. 2. Department of Intensive Care Medicine, University Hospitals Leuven, Louvain, Belgium. 3. Laboratory of Intensive Care Medicine, Academic Department of Cellular and Molecular Medicine, Katholieke Universiteit Leuven, Louvain, Belgium. geert.meyfroidt@uzleuven.be. 4. Department of Intensive Care Medicine, University Hospitals Leuven, Louvain, Belgium. geert.meyfroidt@uzleuven.be.
Abstract
PURPOSE: Acute kidney injury (AKI) recovery prediction remains challenging. The purpose of the present study is to develop and validate prediction models for AKI recovery at hospital discharge in critically ill patients with ICU-acquired AKI stage 3 (AKI-3). METHODS: Models were developed and validated in a development cohort (n = 229) and a matched validation cohort (n = 244) from the multicenter EPaNIC database to create prediction models with the least absolute shrinkage and selection operator (Lasso) machine-learning algorithm. We evaluated the discrimination and calibration of the models and compared their performance with plasma neutrophil gelatinase-associated lipocalin (NGAL) measured on first AKI-3 day (NGAL_AKI3) and reference model that only based on age. RESULTS: Complete recovery and complete or partial recovery occurred in 33.20% and 51.23% of the validation cohort patients respectively. The prediction model for complete recovery based on age, need for renal replacement therapy (RRT), diagnostic group (cardiac/surgical/trauma/others), and sepsis on admission had an area under the receiver operating characteristics curve (AUROC) of 0.53. The prediction model for complete or partial recovery based on age, need for RRT, platelet count, urea, and white blood cell count had an AUROC of 0.61. NGAL_AKI3 showed AUROCs of 0.55 and 0.53 respectively. In cardiac patients, the models had higher AUROCs of 0.60 and 0.71 than NGAL_AKI3's AUROCs of 0.52 and 0.54. The developed models demonstrated a better performance over the reference models (only based on age) for cardiac surgery patients, but not for patients with sepsis and for a general ICU population. CONCLUSION: Models to predict AKI recovery upon hospital discharge in critically ill patients with AKI-3 showed poor performance in the general ICU population, similar to the biomarker NGAL. In cardiac surgery patients, discrimination was acceptable, and better than NGAL. These findings demonstrate the difficulty of predicting non-reversible AKI early.
PURPOSE: Acute kidney injury (AKI) recovery prediction remains challenging. The purpose of the present study is to develop and validate prediction models for AKI recovery at hospital discharge in critically ill patients with ICU-acquired AKI stage 3 (AKI-3). METHODS: Models were developed and validated in a development cohort (n = 229) and a matched validation cohort (n = 244) from the multicenter EPaNIC database to create prediction models with the least absolute shrinkage and selection operator (Lasso) machine-learning algorithm. We evaluated the discrimination and calibration of the models and compared their performance with plasma neutrophil gelatinase-associated lipocalin (NGAL) measured on first AKI-3 day (NGAL_AKI3) and reference model that only based on age. RESULTS: Complete recovery and complete or partial recovery occurred in 33.20% and 51.23% of the validation cohort patients respectively. The prediction model for complete recovery based on age, need for renal replacement therapy (RRT), diagnostic group (cardiac/surgical/trauma/others), and sepsis on admission had an area under the receiver operating characteristics curve (AUROC) of 0.53. The prediction model for complete or partial recovery based on age, need for RRT, platelet count, urea, and white blood cell count had an AUROC of 0.61. NGAL_AKI3 showed AUROCs of 0.55 and 0.53 respectively. In cardiac patients, the models had higher AUROCs of 0.60 and 0.71 than NGAL_AKI3's AUROCs of 0.52 and 0.54. The developed models demonstrated a better performance over the reference models (only based on age) for cardiac surgery patients, but not for patients with sepsis and for a general ICU population. CONCLUSION: Models to predict AKI recovery upon hospital discharge in critically ill patients with AKI-3 showed poor performance in the general ICU population, similar to the biomarker NGAL. In cardiac surgery patients, discrimination was acceptable, and better than NGAL. These findings demonstrate the difficulty of predicting non-reversible AKI early.
Authors: Husain N Alshaikh; Nevin M Katz; Faiz Gani; Neeraja Nagarajan; Joseph K Canner; Seema Kacker; Peter A Najjar; Robert S Higgins; Eric B Schneider Journal: Ann Thorac Surg Date: 2017-12-21 Impact factor: 4.330
Authors: Glenn M Chertow; Elisabeth Burdick; Melissa Honour; Joseph V Bonventre; David W Bates Journal: J Am Soc Nephrol Date: 2005-09-21 Impact factor: 10.121
Authors: Henrik Gammelager; Christian Fynbo Christiansen; Martin Berg Johansen; Else Tønnesen; Bente Jespersen; Henrik Toft Sørensen Journal: Crit Care Date: 2012-07-12 Impact factor: 9.097
Authors: Nattachai Srisawat; Raghavan Murugan; Minjae Lee; Lan Kong; Melinda Carter; Derek C Angus; John A Kellum Journal: Kidney Int Date: 2011-06-15 Impact factor: 10.612