According to guidelines published by Kidney Disease: Improving Global Outcomes, patients at risk of acute kidney injury (AKI) should be managed according to their susceptibilities and exposures. Clinical evaluation of a patient's risk of acute loss of renal function is of undisputed importance. However, such evaluations can be hindered by the complex presentations of critically ill patients and the lack of methods to detect early kidney damage. In this regard, a tool for diagnosis and stratification of patients at risk of AKI would complement clinical assessments and enable improved therapeutic decision-making. Emerging evidence suggests that 15-20% of patients who do not fulfil current serum-creatinine-based consensus criteria for AKI are nevertheless likely to have acute tubular damage, which is associated with adverse outcomes. This evidence supports reassessment of the concept and evolution of the definition of AKI to incorporate biomarkers of tubular damage.