Introduction: Predictive tools can be useful to adapt surveillance or include patients in adjuvant trials after surgical resection of non-metastatic renal cell carcinoma (RCC). Current models have been built using traditional statistical modelling and prespecified variables, which limits their performance.Our aim was To investigate the performance of machine learning (ML) framework to predict recurrence after RCC surgery and compare them with current validated models. Methods: In this observational study, we derived and tested a ensembles of machine learning-based models (Random Survival Forests [RSF], Survival Support Vector Machines [S-SVM], and Extreme Gradient Boosting [XG boost]) of patients who underwent radical or partial nephrectomy for a non-metastatic RCC, between 2013 and 2020, at 21 French medical centres using standard clinicopathological variables.The primary end point of prediction was disease-free survival. Model discrimination was assessed using the concordance index (c-index), and calibration was assessed using the Brier score. ML models were compared with four conventional prognostic models, using decision curve analysis (DCA). Results: 4067 patients were included in this study. ML models obtained higher c-index values than conventional models. The RSF yielded the highest c-index values (0.794) followed by S-SVM (c-index 0.784) and XG boost (c-index 0.782). In addition, all models showed good calibration with low integrated Brier scores (all integrated brier scores <0.1). However, we found calibration drift over time for all models, albeit with a smaller magnitude for ML models. Finally, DCA showed an incremental net benefit from all ML models compared to conventional models currently used in practice. Conclusions: Applying ML approaches to predict recurrence following surgical resection of RCC resulted in better prediction than that of current validated models available in clinical practice. However, there is still room for improvement that may come from the integration of novel biological and/or imaging biomarkers. SOURCE OF Funding: none
