To develop a predictive tool to assist in predicting the risk of Acute Kidney Injury (AKI) following robot-assisted partial nephrectomy (RAPN).

A retrospective review was performed on the prospectively maintained, IRB-approved database to identify all consecutive patients who underwent RAPN between 2008 and 2023. Patients with end-stage kidney disease (ESKD), horseshoe kidneys, solitary kidneys, and previous renal transplant recipients were excluded. AKI was defined according to the RIFLE (Risk, Injury, Failure, Loss, ESKD) Classification. A nomogram was constructed based on the multivariate logistic regression model comprising the different baseline clinicodemographic and renal tumor characteristics.

Of the 1927 patients included in our series, postoperative AKI was identified in 94 cases (4.9%). On multivariate regression analysis, several variables were identified as significant predictors of AKI, including female gender, African American ethnicity, higher body mass index, higher comorbidity burden, lower preoperative renal function, and renal tumors of higher complexity. Upon internal validation, the model demonstrated strong predictive performance. Long-term follow-ups of at least 5 years were available for 759 patients, with postoperative AKI identified to significantly contribute to the 5-year risk of kidney disease progression (OR 2.513; 95% CI 1.070-6.164, P=.036).

In this study, we have developed a predictive model to predict the risk of postoperative AKI following RAPN based on the baseline preoperative characteristics. The nomogram can provide a valuable tool to identify at-risk patients, hence allowing surgeons to better select appropriate surgical candidates and consider treatment options that best optimize long-term functional outcomes while still ensuring a satisfactory oncological outcome.