Contrast-induced nephropathy (CIN) is a common cause of hospital-acquired acute renal failure and related with prolonged hospitalization, increased morbidity, mortality, and economic costs. 1 Given that inflammation plays a significant role in the pathophysiology of CIN and acute coronary syndrome (ACS), inflammation-related biomarkers have been investigated for the prediction of CIN. 2 Among these biomarkers, hematological parameters have been the focus of research due to fact that they are cheap, simple to calculate, and easily accessible. Zorlu and Koseoglu 3 compared several admission hematological inflammatory markers for the prediction of CIN in ACS patients who underwent percutaneous coronary intervention (PCI). Among several inflammatory parameters including mean platelet volume (MPV), lymphocyte count, platelet to lymphocyte ratio (PLR), neutrophil to lymphocyte ratio, and mean platelet volume to lymphocyte ratio (MPVLR), only the MPVLR remained as an independent predictor of CIN. Although this study has several limitations (eg, retrospective and observational design as well as the number of patients) as described by the authors, it has several "take home messages." In this context, we would like to comments on the study design and statistical analysis. The authors 3 performed multiple linear regression analysis to investigate predictors of CIN. In addition to various hematological and inflammatory markers, they also included clinical variables into regression model such as age, left ventricular ejection fraction (LVEF), and diabetes mellitus, which are associated with CIN development. 4,5 Multivariate analysis demonstrated that age and LVEF are also independent predictors of CIN in addition to hematological parameters including hemoglobin and lymphocyte counts and MPVLR. Moreover, there were significant differences between the 2 study groups in terms of these clinical variables. Making a firm conclusion about the superiority and predictive power of these inflammatory markers for CIN may not be possible in the light of these results. From a biomarker perspective, it would be preferable if the authors had performed a propensity score matching analysis