An Algorithm to Personalize Nerve Sparing in Men with Unilateral High-Risk Prostate Cancer

Current guidelines do not provide strong recommendations on preservation of the neurovascular bundles during radical prostatectomy in case of high-risk (HR) prostate cancer and/or suspicious extraprostatic extension (EPE). We aimed to evaluate when, in case of unilateral HR disease, contralateral nerve sparing (NS) should be considered or not.Within a multi-institutional data set we selected patients with unilateral HR prostate cancer, defined as unilateral EPE and/or seminal vesicle invasion (SVI) on multiparametric (mp) magnetic resonance imaging (MRI), or unilateral International Society of Urologic Pathologists (ISUP) 4-5 or prostate specific antigen ≥20 ng/ml. To evaluate when to perform NS based on the risk of contralateral EPE, we relied on chi-square automated interaction detection, a recursive machine-learning partitioning algorithm developed to identify risk groups, which was fit to predict the presence of EPE on final pathology, contralaterally to the prostate lobe with HR disease.A total of 705 patients were identified. Contralateral EPE was documented in 87 patients (12%). Chi-square automated interaction detection identified 3 groups, consisting of 1) absence of SVI on mpMRI and index lesion diameter ≤15 mm, 2) index lesion diameter ≤15 mm and contralateral ISUP 2-3 or index lesion diameter >15 mm and negative contralateral biopsy or ISUP 1, and 3) SVI on mpMRI or index lesion diameter >15 mm and contralateral biopsy ISUP 2-3. We named those groups as low, intermediate and high-risk, respectively, for contralateral EPE. The rate of EPE and positive surgical margins across the groups were 4.8%, 14% and 26%, and 5.6%, 13% and 18%, respectively.Our study challenges current guidelines by proving that wide bilateral excision in men with unilateral HR disease is not justified. Pending external validation, we propose performing NS and incremental NS in case of contralateral low and intermediate EPE risk, respectively.