Chen Z, Chen L, Yao G, et al. - The identification of severe cardiac surgery‐associated acute kidney injury is delayed when monitoring alterations in serum creatinine levels. Hence, researchers sought for novel predictive tools to provide timely diagnosis. They conducted a prospective observational study consisting of a screening cohort (n = 204) and a validation cohort (n = 198). Using a multiplex cytokine assay, 32 inflammatory cytokines were measured. Conducting least absolute shrinkage and selection operator regression, the cytokine signatures of severe cardiac surgery‐associated acute kidney injury was selected. Thereafter, they integrated the significant candidates including interferon‐γ, interleukin‐16, and MIP‐1α (macrophage inflammatory protein‐1 alpha) into the logistic regression model to create a predictive model. Decision curve analysis suggested a superior net benefit of the cytokine‐based model over both the clinical factor‐based model and the established plasma biomarker‐based model for predicting severe acute kidney injury. Furthermore, raised concentrations of each cytokine were linked with longer mechanical ventilation times, intensive care unit stays, and hospital stays. They were strongly predictive of the risk of composite events (defined as treatment with renal replacement therapy and/or in‐hospital death)