Tim Coulson1, Michael Bailey2, Dave Pilcher3, Christopher M Reid4, Siven Seevanayagam5, Jenni Williams-Spence6, Rinaldo Bellomo7. 1. Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Australia; Centre for Integrated Critical Care, University of Melbourne, Melbourne, Australia; Department of Anesthesia, Austin Health, Melbourne, Melbourne, Australia. Electronic address: tim.coulson@unimelb.edu.au. 2. Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Australia; Centre for Integrated Critical Care, University of Melbourne, Melbourne, Australia. 3. Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Australia; Department of Intensive Care, Alfred Health, Melbourne, Australia. 4. Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Australia; School of Public Health, Curtin University, Perth, Australia. 5. Department of Anesthesia, Austin Health, Melbourne, Melbourne, Australia. 6. Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Australia. 7. Centre for Integrated Critical Care, University of Melbourne, Melbourne, Australia; Department of Anesthesia, Austin Health, Melbourne, Melbourne, Australia.
Abstract
OBJECTIVE: To develop a simple model for the prediction of acute kidney injury (AKI) and renal replacement therapy (RRT) that could be used in clinical or research risk stratification. DESIGN: Retrospective analysis. SETTING: Multi-institutional. PARTICIPANTS: All cardiac surgery patients from September 2016 to December 2018. INTERVENTIONS: Observational. MEASUREMENTS AND MAIN RESULTS: The study cohort was divided into a development set (75%) and validation set (25%). The following 2 data epochs were used: preoperative data and immediate postoperative data (within 4 h of intensive care unit admission). Univariate statistics were used to identify variables associated with AKI or RRT. Stepwise logistic regression was used to develop a parsimonious model. Model discrimination and calibration were evaluated in the test set. Models were compared with previously published models and with a more comprehensive model developed using the least absolute shrinkage and selection operator. The study included 22,731 patients at 33 hospitals. The incidences of AKI (any stage) and RRT for the present analysis were 5,829 patients (25.6%) and 488 patients (2.1%), respectively. Models were developed for AKI, with an area under the receiver operating curve (AU-ROC) of 0.67 and 0.69 preoperatively and postoperatively, respectively. Models for RRT had an AU-ROC of 0.77 and 0.80 preoperatively and postoperatively, respectively. These models contained between 3 and 5 variables. Comparatively, comprehensive least absolute shrinkage and selection operator models contained between 21 and 26 variables, with an AU-ROC of 0.71 and 0.72 for AKI and 0.84 and 0.87 for RRT respectively. CONCLUSION: In the present study, simple, clinically applicable models for predicting AKI and RRT preoperatively and immediate postoperatively were developed. Even though AKI prediction remained poor, RRT prediction was good with a parsimonious model.
OBJECTIVE: To develop a simple model for the prediction of acute kidney injury (AKI) and renal replacement therapy (RRT) that could be used in clinical or research risk stratification. DESIGN: Retrospective analysis. SETTING: Multi-institutional. PARTICIPANTS: All cardiac surgery patients from September 2016 to December 2018. INTERVENTIONS: Observational. MEASUREMENTS AND MAIN RESULTS: The study cohort was divided into a development set (75%) and validation set (25%). The following 2 data epochs were used: preoperative data and immediate postoperative data (within 4 h of intensive care unit admission). Univariate statistics were used to identify variables associated with AKI or RRT. Stepwise logistic regression was used to develop a parsimonious model. Model discrimination and calibration were evaluated in the test set. Models were compared with previously published models and with a more comprehensive model developed using the least absolute shrinkage and selection operator. The study included 22,731 patients at 33 hospitals. The incidences of AKI (any stage) and RRT for the present analysis were 5,829 patients (25.6%) and 488 patients (2.1%), respectively. Models were developed for AKI, with an area under the receiver operating curve (AU-ROC) of 0.67 and 0.69 preoperatively and postoperatively, respectively. Models for RRT had an AU-ROC of 0.77 and 0.80 preoperatively and postoperatively, respectively. These models contained between 3 and 5 variables. Comparatively, comprehensive least absolute shrinkage and selection operator models contained between 21 and 26 variables, with an AU-ROC of 0.71 and 0.72 for AKI and 0.84 and 0.87 for RRT respectively. CONCLUSION: In the present study, simple, clinically applicable models for predicting AKI and RRT preoperatively and immediate postoperatively were developed. Even though AKI prediction remained poor, RRT prediction was good with a parsimonious model.
Authors: Kang Liu; Xiangzhou Zhang; Weiqi Chen; Alan S L Yu; John A Kellum; Michael E Matheny; Steven Q Simpson; Yong Hu; Mei Liu Journal: JAMA Netw Open Date: 2022-07-01
Authors: Alfredo G Casanova; Sandra M Sancho-Martínez; Laura Vicente-Vicente; Patricia Ruiz Bueno; Pablo Jorge-Monjas; Eduardo Tamayo; Ana I Morales; Francisco J López-Hernández Journal: J Clin Med Date: 2022-08-05 Impact factor: 4.964
Authors: T G Coulson; L F Miles; A Serpa Neto; D Pilcher; L Weinberg; G Landoni; A Zarbock; R Bellomo Journal: Anaesthesia Date: 2022-09 Impact factor: 12.893