Prostate cancer (PCa) is the second most common malignancy and a leading cause of cancer-related mortality among men worldwide [1]. Advances in diagnostic tools and therapeutic interventions, including robot-assisted radical prostatectomy (RARP), have significantly enhanced the precision and outcomes of PCa treatment [2]. Nevertheless, accurate risk stratification remains a cornerstone of optimal patient management, particularly in predicting critical oncological outcomes such as biochemical failure (BCF) [3,4]

The need for refined risk stratification has become even more evident in the wake of the COVID-19 pandemic, which disrupted healthcare systems globally and challenged traditional management paradigms [5,6]. Delays in surgical treatments due to resource constraints and patient prioritization during the pandemic emphasized the importance of individualized treatment planning. Clinicians were compelled to weigh the risks of postponing surgery against the potential progression of cancer, underscoring the value of tools capable of predicting patient-specific risks [7]. This period highlighted the pressing need for robust and adaptable models incorporating both preoperative and postoperative variables to guide surgical timing and treatment decisions effectively.

To fill this gap, this study aims to address this unmet need by developing and internally validating novel nomograms for predicting 3-year BCF in PCa patients undergoing RARP. Leveraging data from a large cohort treated at a single tertiary referral center, we designed two complementary predictive models. The preoperative model offers early-stage risk stratification to inform initial treatment planning, while the postoperative model refines predictions using definitive pathological data. Together, these tools aim to empower clinicians with actionable insights to optimize surgical timing and personalize treatment strategies.