The Acute Kidney Injury Network (AKIN) criteria applied in burns

Abstract

In 2007, the Acute Kidney Injury Network (AKIN) developed a modified standard for diagnosing and classifying acute kidney injury (AKI). This classification system is a modification of the previously described risk, injury, failure, loss, and end-stage (RIFLE) criteria. Among other modifications, the AKIN staging requires an absolute serum creatinine change of 0.3 mg/dl in a 48-hour period to establish the diagnosis of AKI. The purpose of this study was to apply these new criteria in the severely burned population and to compare the prevalence, stage, and mortality impact of these criteria to the RIFLE criteria. The authors performed a retrospective analysis of consecutive patients with burns admitted to their burn center for at least 24 hours from June 2003 through December 2008. Each patient was classified by both the AKIN and RIFLE criteria by three referees. Both univariate and multivariate analyses were performed to determine the impact of the various AKI stages on mortality. A total of 1973 patients met inclusion and exclusion criteria and were included in the analysis. The average age, %TBSA, injury severity score, and percent with smoke inhalation injury were 36 ± 16, 16 ± 18, 10 ± 12, and 13%, respectively. Overall, the prevalence of AKI was 33% using the AKIN criteria and 24% using the RIFLE criteria with an associated mortality of 21 and 25%, respectively. Of those meeting criteria for AKIN stage 1 (N = 434), 41% (N = 180) would have been categorized as not having AKI on the basis of the RIFLE criteria. In this cohort of patients, mortality increased by almost 8-fold when compared with those without AKI (odds ratio 7.8 [95% confidence interval (CI) 3.7-16.2], P < .0001). The area under the receiver operator characteristic curve for in-hospital mortality was significantly higher for the AKIN criteria at 0.877 (95% CI 0.848-0.906) when compared to the RIFLE criteria at 0.838 (95% CI 0.801-0.874; P = .0007). Burn patients identified as having AKI by the AKIN criteria missed by RIFLE appear to be an important cohort. On the basis of our study, AKIN criteria may be more precise and are more predictive of death than the RIFLE criteria in this population. Prospective validation is needed.