The research team conducted a multicenter retrospective analysis to identify risk factors for acute kidney injury (AKI) in elderly patients with severe pneumonia requiring mechanical ventilation. The study included 2025 patients as a training group and 151 patients as a validation group from intensive care units. The researchers identified seven independent risk factors: creatinine (CREA), SOFA score, APACHE II score, driving pressure, mechanical kinetic energy, CRP/ALB ratio, and mean arterial pressure (MAP). Based on these factors, they created a predictive model in the form of a nomogram. The model demonstrated high predictive accuracy with an area under the curve (AUC) of 0.920 in the training group and 0.979 in the validation group. In the training group, the model achieved a specificity of 0.993 and a sensitivity of 0.763, while in the validation group a specificity of 0.952 and a sensitivity of 0.854. Calibration and decision analyzes confirmed that the model has good fit to the data and high clinical utility in predicting AKI in this patient population.