Model accurately predicts acute kidney injury after cardiac surgery: JAMA

Cleveland, Ohio: A prediction model based on perioperative basic metabolic panel laboratory values among patients undergoing cardiac surgery performed well for predicting moderate to severe acute kidney injury (AKI) within 72 hours and 14 days following the surgery, says a recent study in JAMA. 

Acute kidney injury is a serious complication of cardiac surgery, and its severe form is tied to significant morbidity and mortality. Effective AKI treatment is predicated on timely diagnosis; however, therapy initiation may be delayed by the lag in the increase in serum creatinine levels after kidney injury. Sevag Demirjian, Department of Nephrology and Hypertension, Cleveland Clinic, Cleveland, Ohio, and colleagues, therefore, aimed to determine the derivation and validation of predictive models for AKI after cardiac surgery. 

For this purpose, the researchers derived multivariable prediction models based on a retrospective observational cohort of adult patients undergoing cardiac surgery between January 2000 and December 2019 from a US academic medical center (n = 58 526). They were subsequently validated on an external cohort from 3 US community hospitals (n = 4734). The final follow-up was done on January 15, 2020.

Exposures were perioperative changes in serum creatinine and postoperative blood urea nitrogen, potassium, serum sodium, albumin, and bicarbonate from the first metabolic panel after cardiac surgery. 

The main outcomes were the area under the receiver-operating characteristic curve (AUC) and calibration measures for moderate to severe AKI, AKI requiring dialysis prediction models within 72 hours and 14 days following surgery, and per Kidney Disease: Improving Global Outcomes (KDIGO). 

"Prediction models based on perioperative basic metabolic panel laboratory values after cardiac surgery were derived and validated to predict the risk of postoperative acute kidney injury within 72 hours and 14 days," wrote the authors. They add, "further research is although required to determine whether the use of the risk prediction tool improves clinical outcomes.

Reference:

Demirjian S, Bashour CA, Shaw A, et al. Predictive Accuracy of a Perioperative Laboratory Test–Based Prediction Model for Moderate to Severe Acute Kidney Injury After Cardiac Surgery. JAMA. 2022;327(10):956–964. doi:10.1001/jama.2022.1751

KEYWORDS: acute kidney injury, cardiac surgery, prediction model, surgery complications, Sevag Demirjian, JAMA, AKI, prediction