Renal cell carcinoma (RCC) is most often diagnosed at a localized stage, where surgery is the standard of care. Existing prognostic scores provide moderate predictive performance, leading to challenges in establishing follow-up recommendations after surgery and in selecting patients who could benefit from adjuvant therapy. In this study, we developed a model for individual postoperative disease-free survival (DFS) prediction using machine learning (ML) on real-world prospective data. Using the French kidney cancer research network database, UroCCR, we analyzed a cohort of surgically treated RCC patients. Participating sites were randomly assigned to either the training or testing cohort, and several ML models were trained on the training dataset. The predictive performance of the best ML model was then evaluated on the test dataset and compared with the usual risk scores. In total, 3372 patients were included, with a median follow-up of 30 months. The best results in predicting DFS were achieved using Cox PH models that included 24 variables, resulting in an iAUC of 0.81 [IC95% 0.77–0.85]. The ML model surpassed the predictive performance of the most commonly used risk scores while handling incomplete data in predictors. Lastly, patients were stratified into four prognostic groups with good discrimination (iAUC = 0.79 [IC95% 0.74–0.83]). Our study suggests that applying ML to real-world prospective data from patients undergoing surgery for localized or locally advanced RCC can provide accurate individual DFS prediction, outperforming traditional prognostic scores.

Recent studies suggested that the neutrophil-to-lymphocyte ratio (NLR) could play a key role in tumor initiation, progression and response to treatments. The main objective was to assess the prognostic value of the pre-operative NLR on recurrence-free survival (RFS) in patients with non-hereditary localized renal cell carcinoma. From the UroCCR database (NCT03293563), factors influencing the disease recurrence of consecutive patients who underwent nephrectomy for cT1-T4 N0M0 were analyzed using multi-variate cox regression and log-rank methods. We included 786 patients, among which 135 (17.2%) experienced a recurrence at a median time of 23.7 [8.5–48.6] months. RFS for patients with a pre-operative NLR of <2.7 was 94% and 88% at 3 and 5 years, respectively, versus 76% and 63% for patients with a NLR of ≥2.7 (p < 0.001, log-rank test). To predict the risk of post-operative recurrence, the NLR was combined with the UCLA integrated staging system (UISS), and we defined four groups of the UroCCR-61 predictive model. The RFS rates at 3 and 5 years were 100% and 97% in the very-low-risk group, 93% and 86% in the low-risk group, 78% and 68% in the intermediate-risk group and 63% and 46% in the high-risk group (p < 0.0001). The pre-operative NLR seems to be an inexpensive and easily accessible prognostic bio-marker for non-metastatic RCCs.

Background/Objectives: Three-dimensional (3D) image-guided robotic-assisted partial nephrectomy (3D-IGRAPN) integrates patient-specific anatomical models to optimize surgical planning and intraoperative guidance in the management of renal tumors. This study aimed to assess medium-term functional and oncologic outcomes of 3D-IGRAPN in a large, prospective cohort. Methods: All consecutive patients undergoing 3D-IGRAPN between January 2016 and March 2023 at a tertiary referral center were prospectively included in the UroCCR database (NCT03293563). Patient-specific 3D models were generated from preoperative CT scans and used intraoperatively. The primary endpoint was trifecta achievement, defined as an absence of major complications (Clavien–Dindo ≥ 3), negative surgical margins for malignant tumors, and ≥90% preservation of baseline renal function at 3 months. Secondary endpoints included functional outcomes, complication rates, local recurrence, and metastasis rates, as well as cancer-specific and overall survivals. Results: Among 568 patients (586 surgeries), the trifecta was achieved in 55.2% of evaluable malignant cases. Severe complications occurred in 33 cases (5.6%), and positive surgical margins were reported in 27 cases (5.1%) out of 528 surgeries involving malignant lesions. Renal function was preserved in 59.9% of patients at 3 months. At a mean follow-up of 31.5 months, recurrence and metastasis rates were 7.4% and 8.6%, respectively. Cancer-specific and overall survival at follow-up were 96.5% and 89%. Conclusions: 3D-IGRAPN demonstrates favorable functional and oncologic outcomes, even in complex tumors. These results support the integration of 3D modeling as a standard tool in image-guided nephron-sparing surgery.

Robot-assisted partial nephrectomy (RAPN) is the standard of care for small, localized kidney tumors. This surgery is conducted within a short hospital stay and can even be performed as outpatient surgery in selected patients. In order to allow early rehabilitation of patients, an optimal control of postoperative pain is necessary. High-pressure pneumoperitoneum during surgery seems to be the source of significant pain during the first hours postoperatively. Our study is a prospective, randomized, multicenter, controlled study which aims to compare post-operative pain at 24 h between patients undergoing RAPN at low insufflation pressure (7 mmHg) and those operated on at standard pressure (12 mmHg) using the AirSeal system.This trial is registered in the US National Library of Medicine Trial Registry (NCT number: NCT05404685).