Lymph node yield during radical prostatectomy does not impact rate of biochemical recurrence in patients with seminal vesicle invasion and node-negative disease

Explainable and visualizable machine learning models to predict biochemical recurrence of prostate cancer

PURPOSE

Machine learning (ML) models presented an excellent performance in the prognosis prediction. However, the black box characteristic of ML models limited the clinical applications. Here, we aimed to establish explainable and visualizable ML models to predict biochemical recurrence (BCR) of prostate cancer (PCa).

MATERIALS AND METHODS

A total of 647 PCa patients were retrospectively evaluated. Clinical parameters were identified using LASSO regression. Then, cohort was split into training and validation datasets with a ratio of 0.75:0.25 and BCR-related features were included in Cox regression and five ML algorithm to construct BCR prediction models. The clinical utility of each model was evaluated by concordance index (C-index) values and decision curve analyses (DCA). Besides, Shapley Additive Explanation (SHAP) values were used to explain the features in the models.

RESULTS

We identified 11 BCR-related features using LASSO regression, then establishing five ML-based models, including random survival forest (RSF), survival support vector machine (SSVM), survival Tree (sTree), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), and a Cox regression model, C-index were 0.846 (95%CI 0.796-0.894), 0.774 (95%CI 0.712-0.834), 0.757 (95%CI 0.694-0.818), 0.820 (95%CI 0.765-0.869), 0.793 (95%CI 0.735-0.852), and 0.807 (95%CI 0.753-0.858), respectively. The DCA showed that RSF model had significant advantages over all models. In interpretability of ML models, the SHAP value demonstrated the tangible contribution of each feature in RSF model.

CONCLUSIONS

Our score system provide reference for the identification for BCR, and the crafting of a framework for making therapeutic decisions for PCa on a personalized basis.

The role and controversy of pelvic lymph node dissection in prostate cancer treatment: a focused review

Pelvic lymph node dissection (PLND) is commonly performed alongside radical prostatectomy. Its primary objective is to determine the lymphatic staging of prostate tumors by removing lymph nodes involved in lymphatic drainage. This aids in guiding subsequent treatment and removing metastatic foci, potentially offering significant therapeutic benefits. Despite varying recommendations from clinical practice guidelines across countries, the actual implementation of PLND is inconsistent, partly due to debates over its therapeutic value. While high-quality evidence supporting the superiority of PLND in oncological outcomes is lacking, its role in increasing surgical time and risk of complications is well-recognized. Despite these concerns, PLND remains the gold standard for lymph node staging in prostate cancer, providing invaluable staging information unattainable by other techniques. This article reviews PLND's scope, guideline perspectives, implementation status, oncologic and non-oncologic outcomes, alternatives, and future research needs.

Comparison of robotic-assisted laparoscopic radical prostatectomy: SP versus XI, a single surgeon experience

Currently, there is a paucity of data regarding Single Port (SP) robotic-assisted laparoscopic prostatectomy (RALP). Our objective was to compare our single-institution single-surgeon SP RALP experience to our XI RALP experience with regard to patient selection, perioperative data, and outcomes. Patients who underwent prostatectomy at our institution between August 2019 and April 2021 were selected for analysis. All patients had biopsy confirmed prostate cancer. All surgeries were performed by one urologist at our institution to limit inter-surgeon variability. Demographic and clinical information were extracted from the medical record in standardized fashion. All documented classifications were graded using the Clavien-Dindo classification system. Patients with previous prostate cancer therapies were excluded. Categorical variables were compared using Chi-square or Fisher's exact test where appropriate. Continuous variables were compared using t tests or Wilcoxon rank sum tests where appropriate. Complete records were available for 208 patients. Of the total patient population 127 (61.1%) underwent SP prostatectomy compared to 81 (38.9%) underwent XI prostatectomy. There was no significant difference between the two cohorts in terms of mean age (65 vs. 66 years; p = 0.60), BMI (29.2 vs. 30.1; p = 0.22), preop ASA score ≥ 3 (68.5% vs. 64.2%; p = 0.52), or preop PSA (7.1 vs. 7.4, p = 0.94). There no difference in procedure time for SP prostatectomy (170 vs. 168 min, p = 0.035), estimated blood loss (100 vs. 100 mL; p = 0.14), or average length of stay (1 vs. 1 days; p = 0.22). There was a significant difference in Gleason grade group between the two cohorts with patients undergoing XI RALRP more likely to have higher stage disease (p = 0.025) and a trend towards higher D'Amico risk scores in the XI group (p = 0.053). There was no difference in rate of positive surgical margins (29.9% vs. 29.6%; p = 0.96). There was no difference in the distribution of complications between the two groups (p = 0.99) with 89% of patients having no complication. There was no difference in the number of lymph nodes removed by modality (p = 0.94). To date, this study represents one of the largest cohorts of patients who underwent SP RALP. Importantly, it is among the first studies comparing perioperative variables between the SP and XI platforms. As surgeons become more facile with the SP system there appear to minimal differences in patient factors, perioperative results, or outcomes between the platforms. These findings provide evidence that surgeons who are competent on the XI platform can confidently perform SP RALPs through a single incision without compromising outcomes.

Relative impact of lymph-node metastasis and seminal vesical invasion on oncologic outcomes following radical prostatectomy

BACKGROUND

While both seminal vesicle (SVI) and lymph-node invasion (LNI) have been identified as adverse prognostic variables among men undergoing radical prostatectomy (RP), the relative impact of each of these features on subsequent oncologic outcomes has not been well defined. We assessed the impact of LNI on long-term oncologic outcomes among patients with SVI at RP.

METHODS

We reviewed 19,519 patients who underwent RP and identified 2043 with SVI. Metastasis-free (MFS), cancer-specific (CSS), and overall survival (OS) were estimated for patients with SVI, stratified by the presence and number of pelvic lymph node metastases. Cox proportional hazards models were used to evaluate the independent association of the number of metastatic nodes and lymph node density with oncologic outcomes among patients with SVI, controlling for age, year of surgery, margin status, preoperative PSA, pathologic Gleason score, extraprostatic extension, and use of adjuvant therapies.

RESULTS

At a median follow up of 12.1 years (IQR 7.0,18.6), 548 patients developed metastatic disease and 1331 died, including 406 who died from prostate cancer (PCa). We found that, among patients with SVI, the presence of a single positive lymph node was not associated with incrementally adverse oncologic outcomes compared to no nodal metastasis at RP, with 10-year MFS, CSS, and OS rates of 81.3% versus 78.3%(p = 0.18), 86.5% versus 89.8%(p = 0.32), and 72.8% versus 76.7%(p = 0.53), respectively. In contrast, on multivariable analyses, the presence of ≥2 metastatic nodes and a 20% lymph-node density cut off remained independently associated with worse survival.

CONCLUSIONS

SVI represents an adverse pathologic feature such that the presence of a single positive pelvic lymph node did not further adversely impact prognosis. Meanwhile, a significant number of involved nodes was associated with decreased survival. These findings may aid in risk-stratification as well as clinical trial design for such high-risk patients following surgery.

Bilateral Seminal Vesicle Invasion Is Not Associated with Worse Outcomes in Locally Advanced Prostate Carcinoma

Background and Objectives: Patients with seminal vesicle invasion (SVI) are a highly heterogeneous group. Prognosis can be affected by many clinical and pathological characteristics. Our aim was to study whether bilateral SVI (bi-SVI) is associated with worse oncological outcomes. Materials and Methods: This is an observational retrospective study that included 146 pT3b patients treated with radical prostatectomy (RP). We compared the results between unilateral SVI (uni-SVI) and bi-SVI. The log-rank test and Kaplan–Meier curves were used to compare biochemical recurrence-free survival (BCR), metastasis-free survival (MFS), and additional treatment-free survival. Cox proportional hazard models were used to identify predictors of BCR-free survival, MFS, and additional treatment-free survival. Results: 34.93% of patients had bi-SVI. The median follow-up was 46.84 months. No significant differences were seen between the uni-SVI and bi-SVI groups. BCR-free survival at 5 years was 33.31% and 25.65% (p = 0.44) for uni-SVI and bi-SVI. MFS at 5 years was 86.03% vs. 75.63% (p = 0.1), and additional treatment-free survival was 36.85% vs. 21.93% (p = 0.09), respectively. In the multivariate analysis, PSA was related to the development of BCR [HR 1.34 (95%CI: 1.01–1.77); p = 0.03] and metastasis [HR 1.83 (95%CI: 1.13–2.98); p = 0.02]. BCR was also influenced by lymph node infiltration [HR 2.74 (95%CI: 1.41–5.32); p = 0.003]. Additional treatment was performed more frequently in patients with positive margins [HR: 3.50 (95%CI: 1.65–7.44); p = 0.001]. Conclusions: SVI invasion is an adverse pathology feature, with a widely variable prognosis. In our study, bilateral seminal vesicle invasion did not predict worse outcomes in pT3b patients despite being associated with more undifferentiated tumors.

Impact of positive surgical margin status in predicting early biochemical recurrence after robot-assisted radical prostatectomy

BACKGROUND

We investigated the association between positive surgical margin (PSM) status and biochemical recurrence (BCR) after robot-assisted radical prostatectomy (RARP) to develop a prognostic factor-based risk stratification model for BCR.

METHODS

We analyzed the data of 483 patients who underwent RARP at our hospital between October 2010 and April 2019; 435 patients without neoadjuvant therapy were finally included. The BCR-free survival rate was determined using Kaplan-Meier analysis. Effects of the PSM status, including the number of PSMs, Gleason score (GS) at a PSM, and the maximum PSM length for BCR, were investigated using Cox regression analysis.

RESULTS

BCR was confirmed after RARP in 61 patients (14.0%), and PSM was confirmed in 74 patients (17.0%); PSM was a significant predictor of BCR (p < 0.001). The median number of PSMs was 2 (1-6), and the median maximum length of PSM was 6.0 (2.0-17.0) mm. Multivariable analysis showed lymph node invasion (p < 0.001), GS of ≥ 7 at a PSM (p = 0.022) and a maximum PSM length of > 6.0 mm (p = 0.003) were significant predictors of BCR. We classified the patients without lymph node invasion into good-, intermediate-, and poor-risk groups according to the other two risk factors (presence of 0, 1, and 2 factors, respectively) and rates of 1-year BCR-free survival (100.0, 72.7, and 48.1%, respectively).

CONCLUSION

Higher GS at PSM and greater length of PSM were significant predictors of BCR after RARP, and console surgeons should be careful to prevent PSM during RARP.