Identification of Trajectory-Based Acute Kidney Injury Phenotypes Among Cardiac Surgery Patients.

ABSTRACT

BACKGROUND: Acute kidney injury (AKI) is a common and serious complication of cardiac surgical procedures for which unrecognized heterogeneity may underpin poor success in identifying effective therapies. We aimed to identify phenotypically similar groups of patients as defined by their postoperative creatinine trajectories. METHODS: This was a retrospective, single-center cohort study in an academic tertiary care center including patients undergoing coronary artery bypass graft procedures. AKI phenotypes were evaluated through latent class mixed modeling of serum creatinine patterns (trajectories). To identify trajectory phenotypes, modeling was performed using postoperative creatinine values from 50% of patients (development cohort) and for comparison similarly conducted for the remaining sample (validation cohort). Subsequent assessments included comparisons of classes between development and validation cohorts for consistency and stability, and among classes for patient and procedural characteristics, complications, and long-term survival. RESULTS: We identified 12 AKI trajectories in both the development (n = 2647) and validation cohorts (n = 2647). Discrimination among classes was good (mean posterior class membership probability, 66%-88%), with differences in rate, timing, and degree of serum creatinine rise/fall, and recovery. In matched class comparisons between cohorts, many other phenotypic similarities were present. Notably, 4 high-risk phenotypes had greater long-term risk for death relative to lower risk classes. CONCLUSIONS: Latent class mixed modeling identified 12 reproducible AKI classes (serum creatinine trajectory phenotypes), including 4 with higher risk of poor outcome, in patients following coronary artery bypass graft procedures. Such hidden structure offers a novel approach to grouping patients for renoprotection investigations in addition to reanalysis of previously conducted trials.