Introduction: The maximal allowable contrast dose (MACD = 5 × body weight/serum creatinine) is an empiric equation that has been used and validated in several studies to mitigate the risk of contrast-induced acute kidney injury (CI-AKI). However, coefficient 5 (referred to as factor K) was empirically devised and never disputed. The aim of this study was to refine the MACD equation for the prediction of CI-AKI following percutaneous coronary interventions (PCIs). Methods: This is a single-center, retrospective cohort study of adults undergoing PCI. Electronic medical records were reviewed to identify patients who underwent PCI between 2010 and 2019, derived from the National Cardiovascular Data Registry Cath-PCI registry for our hospital. Factor K (defined as contrast volume × serum creatinine/body weight) was calculated for every patient. A receiver operating characteristic (ROC) curve was constructed, and the Youden index was used to identify the optimal cut-off value for factor K in predicting severe (stages 2–3) CI-AKI. Results: Of the 3,506 patients undergoing PCI, 255 (7.2%) developed CI-AKI, and 68 (26.7%) of the 255 experienced severe AKI. Factor K predicted all-stage CI-AKI (area under the ROC curve 0.649; 95% CI 0.611, 0.686) but had better performance for predicting severe (stages 2–3) AKI (0.736; 95% CI 0.674, 0.800). The optimal cut-off value for factor K in predicting severe CI-AKI was 2.5, with a corresponding sensitivity of 68.7% and specificity of 70.5%. On subgroup analyses, optimal cut-off values for factor K for high-risk groups were not significantly different from those of low-risk groups. Conclusion: Our study indicates that factor K in the MACD equation is an independent risk factor for the development of severe CI-AKI, with an optimal cut-off value of 2.5. If our findings are validated, the MACD equation should be revised to incorporate the coefficient of 2.5 instead of 5.