Kidney cancer is of increasing incidence worldwide. It is most often diagnosed at a localized stage where surgical management is the gold standard. Current available prognostic scores offer moderate predictive performance which leads to difficulties in establishing follow-up recommendations for patients after surgery and selecting patients who could benefit from adjuvant therapy. Our objective is to develop a model for individual prediction of the recurrence risk after surgery using machine learning (ML).
From the french research network on kidney cancer prospectively maintained database UroCCR (NCT 03293563), a cohort of patients undergoing surgery between May 2000 and January 2020 for a localized or locally advanced renal cell carcinoma (pT1-T4, N0, M0) was analyzed. Patients with a genetic cancer, a concomitant malignant disease or a chronic inflammatory disease were excluded. For each patient, clinical, biological, histological, and radiological data were collected. Participating sites were randomly assigned to the training or testing cohort with a 67/33 ratio of patients. Missing data were multiply imputed using the MICE algorithm and gradient boosted trees. Several ML algorithms were trained on the training data set and parameters of each algorithm were optimized using repeated cross-validation procedure (5x10folds). C-index at 5 years was used as optimization metric. The predictive performance of the algorithm was then evaluated on the test dataset using C-index and time-dependent AUC.
ML applied to data from patients undergoing surgery for localized or locally advanced kidney cancer appears to provide good individual DFS predictions comparing to usual scores.