Surgical resection is the standard treatment for nonmetastatic renal cell carcinoma, yet survival outcomes vary significantly among patients. Current prognostic models lack precision and cannot be applied preoperatively. Here we show the development and validation of a preoperative, interpretable machine learning model to estimate cancer-specific mortality. Using real-world clinical data from 2536 patients and an independent external validation cohort of 580 patients, we combine random survival forests with white-box models to ensure clinical transparency. Our survival tree model relies on exactly eight preoperative features, including tumor size, lymph node involvement, and performance status. We demonstrate that this model outperforms the established GRANT model, achieving a C-index of 0.88 and a Brier score of 0.02 on the external cohort, with notable accuracy in the first year postsurgery. Finally, we provide this tool as a web-based application to facilitate personalized, preoperative risk stratification.
Nature communications. 2026 Jun 16 [Epub ahead of print]
Alessandro Larcher, Alberto Traverso, Patrick Scuri, Umberto Capitanio, Giacomo Musso, Daniela Canibus, Simone Barbieri, Luca Caivano, Alan Zambello, Marco Denti, Riccardo Campi, Sergio Serni, Salvatore Granata, Anna Palmisano, Davide Vignale, Fracnesco Montorsi, Antonio Esposito, Carlo Tacchetti, Andrea Salonia
Division of Experimental Oncology/Unit of Urology, URI, IRCCS Ospedale San Raffaele, Milan, Italy., S-RACE (San-Raffaele Ai CEnter), Vita-Salute San Raffaele University, Milan, Italy. ., S-RACE (San-Raffaele Ai CEnter), Vita-Salute San Raffaele University, Milan, Italy., Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy.