Model uses acute kidney injury to predict chronic kidney disease
Routine laboratory data from patients with kidney damage were used to predict chronic kidney disease.
(HealthDay News) — A multivariable model that uses routine laboratory data is able to predict advanced chronic kidney disease after hospitalization with acute kidney injury, according to a study published online Nov. 14 in the Journal of the American Medical Association.
In order to derive and validate multivariable prediction models, Matthew T. James, MD, PhD, from Foothills Medical Center in Canada, and colleagues used data from two population-based cohorts of patients with a prehospitalization estimated glomerular filtration rate of ≥45 mL/min/1.73m2 who had survived hospitalization with acute kidney injury. Risk models were derived from 9,973 patients hospitalized in Alberta and externally validated with data from 2,761 patients hospitalized in Ontario.
The researchers found that 6 variables were independently associated with progression of acute kidney injury to advanced chronic kidney disease: older age, female sex, higher baseline serum creatinine value, albuminuria, greater severity of acute kidney injury, and higher serum creatinine value at discharge. Inclusion of these factors in a multivariable model had a C statistic of 0.81 and improved discrimination and reclassification in the external validation cohort compared with reduced models that included age, sex, and discharge serum creatinine value alone or age, sex, and acute kidney injury stage alone.
"This model was able to predict advanced chronic kidney disease following hospitalization with acute kidney injury but requires evaluation of its utility in a clinical setting," conclude the authors.
One author disclosed financial ties to the pharmaceutical industry.
James MT, Pannu N, Hemmelgarn BR, et al. Derivation and External Validation of Prediction Models for Advanced Chronic Kidney Disease Following Acute Kidney Injury. JAMA. 2017 Nov 14. doi:10.1001/jama.2017.16326