Elective Pelvic Lymph Node Radiation Therapy and the Risk of Death in Patients With Unfavorable-Risk Prostate Cancer: A Postrandomization Analysis.

PURPOSE: Although a contemporary randomized clinical trial has led to the use of whole-pelvic radiation therapy (WPRT), long-term data evaluating a potential reduction in mortality are lacking and are addressed in the current study. MATERIALS AND METHODS: From 2005 to 2015, 350 men with localized, unfavorable-risk prostate cancer (PC) were randomly assigned to receive androgen deprivation therapy (ADT) and RT plus docetaxel versus ADT and RT. Treatment of the pelvic lymph nodes was at the discretion of the treating physician. Multivariable Cox and Fine and Grays regression analyses were performed to assess whether a significant association existed between radiation treatment volume and all-cause mortality (ACM) and PC-specific mortality (PCSM), respectively, adjusting for known PC prognostic factors and comorbidity. An interaction term between age (categorized by dichotomization at 65 years to enable clinical interpretation and applicability of the results and which approximates the median (66 years [IQR, 61-70]) and radiation treatment volume was included in the analysis. RESULTS: After a median follow-up of 10.20 years (IQR, 7.96-11.41), 89 men died (25.43%); of these, 42 died of PC (47.19%). Of the 350 randomly assigned patients, 88 (25.14%) received WPRT. In men younger than 65 years, WPRT was associated with a significantly lower ACM risk (adjusted hazard ratio [AHR], 0.33 [95% CI, 0.11 to 0.97]; P = .04) and lower PCSM risk (AHR, 0.17 [95% CI, 0.02 to 1.35]; P = .09) after adjusting for covariates, whereas this was not the case for men 65 years or older. CONCLUSION: WPRT has the potential to reduce mortality in younger men with unfavorable-risk PC.

Prognostic Significance of the Cribriform Pattern in Prostate Cancer: Clinical Outcomes and Genomic Alterations.

PURPOSE: Given the diverse clinical progression of prostate cancer (PC) and the evolving significance of histopathological factors in its management, this study aimed to explore the impact of cribriform pattern 4 (CP4) on clinical outcomes in PC patients and examine its molecular characteristics. METHODS: This retrospective study analyzed data from The Cancer Genome Atlas (TCGA) database and included PC patients who underwent radical prostatectomy (RP) and had pathology slides available for the assessment of CP4. A multivariable competing risk regression analysis was used to assess the association between CP4 and progression-free survival (PFS) while adjusting for established PC prognostic factors. The frequency of genomic alterations was compared between patients with and without CP4 using the Fisher's exact test. RESULTS: Among the 394 patients analyzed, 129 (32.74%) had CP4. After a median follow-up of 40.50 months (IQR: 23.90, 65.60), the presence of CP4 was significantly associated with lower PFS (AHR, 1.84; 95% CI, 1.08 to 3.114; p = 0.023) after adjusting for covariates. Seven hub genes-KRT13, KRT5, KRT15, COL17A1, KRT14, KRT16, and TP63-had significantly lower mRNA expression levels in patients with CP4 compared to those without. CONCLUSIONS: PC patients with CP4 have distinct genomic alterations and are at a high risk of disease progression following RP. Therefore, these patients may benefit from additional post-RP treatments and should be the subject of a prospective randomized clinical trial.

Prognostic Impact of Prostate-Specific Antigen at 6 Months After Radiotherapy in Localized Prostate Cancer: An Individual Patient Data Analysis of Randomized Trials.

PURPOSE: We sought to evaluate the prognostic impact of prostate-specific antigen (PSA) at 6 months after completion of radiotherapy (RT) in patients treated with RT alone, RT plus short-term (st; 3-6 months), and RT plus long-term (lt; 24-36 months) androgen-deprivation therapy (ADT). PATIENTS AND METHODS: Individual patient data were obtained from 16 randomized trials evaluating RT ± ADT for localized prostate cancer (PCa) between 1987 and 2011. The lowest PSA recorded within 6 months after RT completion was identified and categorized as < or ≥0.1 ng/mL. The primary outcomes were metastasis-free survival (MFS), PCa-specific mortality (PCSM), and overall survival (OS), from 12 months after random assignment. RESULTS: Ninety-eight percent (n = 2,339/2,376) of patients allocated to RT alone, 84% (n = 4,756/5,658) allocated to RT + stADT, and 77% (n = 1,258/1,626) allocated to RT + ltADT had PSA ≥0.1 ng/mL within 6 months after completing RT. PSA ≥0.1 ng/mL was associated with lower MFS and OS and higher PCSM among patients allocated to RT ± ADT (RT - MFS: hazard ratio [HR], 2.24 [95% CI, 1.21 to 4.16]; PCSM: subdistribution hazard ratio [sHR], 1.82 [0.51 to 6.49]; OS: HR, 1.72 [0.97 to 3.05]; RT + stADT - MFS: HR, 1.27 [1.12 to 1.44]; PCSM: sHR, 2.10 [1.52 to 2.92]; OS: HR, 1.26 [1.11 to 1.44]; RT + ltADT - MFS: HR, 1.58 [1.27 to 1.96]; PCSM: sHR, 1.97 [1.11 to 3.49]; OS: HR, 1.59 [1.27 to 1.99]). Five-year MFS rates among patients allocated to RT, RT + stADT, and RT + ltADT were 91% versus 79%, 83% versus 76%, and 87% versus 74%, respectively, based on PSA < or ≥0.1 ng/mL. CONCLUSION: PSA ≥0.1 ng/mL within 6 months after RT completion was prognostic for lt outcomes in patients treated with RT ± ADT for localized PCa. This can be used to counsel patients treated with RT ± ADT and in guiding clinical trial design evaluating novel systemic therapies with RT + ADT as well as (de)intensification strategies.

Secondary analysis of late major gastrointestinal and genitourinary toxicities in unfavorable-risk prostate cancer patients receiving docetaxel: Insights from a randomized trial.

BACKGROUND: This study sought to evaluate the late toxicity associated with neoadjuvant and concurrent docetaxel and radiation therapy in patients with prostate cancer. METHODS: A secondary analysis was performed of the phase 3 multicenter randomized trial (Dana-Farber Cancer Institute 05-043) including 350 patients with nonmetastatic unfavorable-risk prostate cancer. Patients were randomized 1:1 to receive androgen deprivation therapy, radiation therapy, and docetaxel versus androgen deprivation therapy and radiation therapy. The study assessed the cumulative incidence rates of grade 2 and grade 3 or higher gastrointestinal, genitourinary, and sexual toxicity. A multivariable Fine and Gray's competing risks regression model adjusted for age at randomization and pelvic lymph node radiation therapy was used to evaluate the treatment effect of docetaxel on time to late genitourinary and gastrointestinal toxicities. RESULTS: The study included 338 patients who primarily had minimal or no comorbidity (74.9%) and median age 66 years (interquartile range: 61,71). At a median follow-up of 10.2 years, docetaxel was not associated with increased risk of any grade 3 or higher (adjusted hazard ratio [AHR], 0.98; 95% confidence interval [CI], 0.36-2.67; p = .96) or grade 2 gastrointestinal (p = .75), genitourinary (p = .44), and sexual (p = .29) toxicity. Age was associated with increased grade 3 or higher (AHR, 1.08; 95% CI, 1.01-1.16; p = .03) and grade 2 gastrointestinal toxicity (AHR, 1.11; 95% CI, 1.03-1.20; p = .005). A nonsignificant trend (p = .09) toward increased late grade 3 or higher toxicity was observed for pelvic radiation therapy use. CONCLUSIONS: Docetaxel combined with radiotherapy has an acceptable long-term toxicity profile.

Multi-institutional Development and External Validation of a Machine Learning Model for the Prediction of Distant Metastasis in Patients Treated by Salvage Radiotherapy for Biochemical Failure After Radical Prostatectomy.

BACKGROUND: Up to 40% of patients with prostate cancer may develop biochemical recurrence after surgery, with salvage radiation therapy (SRT) being the only curative option. In 2016, Tendulkar et al. (Contemporary update of a multi-institutional predictive nomogram for salvage radiotherapy after radical prostatectomy. J Clin Oncol 2016;34:3648-54) published a nomogram to predict distant metastasis in a cohort of patients treated with SRT with pre-SRT prostate-specific antigen (PSA) of 0.5 ng/ml after radical prostatectomy. In modern practice, SRT is delivered at lower PSA values. OBJECTIVE: To train and externally validate a machine learning model to predict the risk of distant metastasis at 5 yr in a contemporary cohort of patients receiving SRT. DESIGN, SETTING, AND PARTICIPANTS: We trained a machine learning model on data from 2418 patients treated with SRT at one institution, with a median PSA value of 0.27 ng/ml. External validation was done in 475 patients treated at two different institutions. Patients with cM1, pN1, or pT4 disease were excluded, as were patients with PSA >2 ng/ml or PSA 0, and patients with radiation dose <60 or ≥80 Gy. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Model performance was assessed using calibration and time-dependent area under the receiver operating curve (tAUC). RESULTS AND LIMITATIONS: Our model had better calibration and showed improved discrimination (tAUC = 0.72) compared with the Tendulkar model (tAUC = 0.60, p < 0.001). The main limitations of this study are its retrospective design and lack of validation on patients who received hormone therapy. CONCLUSIONS: The updated model can be used to provide more individualized risk assessments to patients treated with SRT at low PSA values, improving decision-making. PATIENT SUMMARY: Up to 40% of patients with prostate cancer may develop biochemical recurrence after surgery, with salvage radiation therapy as the only potentially curative option. We trained and validated a machine learning model using clinical and surgical data to predict a patient's risk of distant metastasis at 5 yr after treatment. Our model outperformed the reference tool and can improve clinical decision-making by providing more personalized risk assessment.

The Association of County-level Prostate-specific Antigen Screening with Metastatic Prostate Cancer and Prostate Cancer Mortality.

BACKGROUND AND OBJECTIVE: There exists ongoing debate about the benefits and harms of prostate-specific antigen (PSA) screening for prostate cancer. This study sought to evaluate the association of county-level PSA screening rates with county-level incidence of metastatic prostate cancer and prostate cancer mortality in the USA. METHODS: This ecological study used data from the 2004-2012 Behavioral Risk Factor Surveillance System (BRFSS) to build a multilevel mixed-effect model with poststratification using US Census data to estimate county-level PSA screening rates for all 3143 US counties adjusted for age, race, ethnicity, and county-level poverty rates. The exposure of interest was average county-level PSA screening rate from 2004 to 2012, defined as the proportion of men aged 40-79 yr who underwent PSA screening within the prior 2 yr. The primary outcomes were county-level age-adjusted incidence of regional/distant prostate cancer during 2015-2019 and age-adjusted prostate cancer mortality during 2016-2020. KEY FINDINGS AND LIMITATIONS: A total of 416 221 male BRFSS respondents aged 40-79 yr met the inclusion criteria and were used in the multilevel mixed-effect model. The model was poststratified using 63.4 million men aged 40-79 yr from all 3143 counties in the 2010 Decennial Census. County-level estimated PSA screening rates exhibited geographic variability and were pooled at the state level for internal validation with direct BRFSS state-level estimates, showing a strong correlation with Pearson correlation coefficients 0.77-0.90. A 10% higher county-level probability of PSA screening in 2004-2012 was associated with a 14% lower county-level incidence of regional/distant prostate cancer in 2015-2019 (rate ratio 0.86, 95% confidence interval [CI] 0.85-0.87, p < 0.001) and 10% lower county-level prostate cancer mortality in 2016-2020 (rate ratio 0.90, 95% CI 0.89-0.91, p < 0.001). CONCLUSIONS AND CLINICAL IMPLICATIONS: In this population-based ecological study of all US counties, higher PSA screening rates were associated with a lower incidence of regional/distant prostate cancer and lower prostate cancer mortality at extended follow-up. PATIENT SUMMARY: US counties with higher rates of prostate-specific antigen (PSA) screening had significantly lower rates of metastatic prostate cancer and prostate cancer mortality in subsequent years. These data may inform shared decision-making regarding PSA screening for prostate cancer.

Mortality Risk for Docetaxel-Treated, High-Grade Prostate Cancer With Low PSA Levels: A Meta-Analysis.

Importance: Patients with high-grade prostate cancer with low levels of prostate-specific antigen (PSA; <4 ng/mL) are at high risk of mortality, necessitating an improved treatment paradigm. Objective: To assess for these patients whether adding docetaxel to standard of care (SOC) treatment is associated with decreased prostate cancer-specific mortality (PCSM) and all-cause mortality (ACM). Data Sources: PubMed search from 2000 to 2022. Study Selection: Five prospective randomized clinical trials (RCTs) performed in the US, France, and the United Kingdom evaluating SOC treatment with radiotherapy and androgen deprivation therapy (ADT) or with radical prostatectomy vs SOC plus docetaxel. Data Extraction and Synthesis: Individual data were included from patients with nonmetastatic prostate cancer, a PSA level of less than 4 ng/mL, and a Gleason score of 8 to 10. Patients initiated treatment between February 21, 2006, and December 31, 2015 (median follow-up, 7.1 [IQR, 5.4-9.9] years). Data were analyzed on December 16, 2022. Main Outcomes and Measures: Hazard ratio (HR) of ACM and subdistribution HR (sHR) of PCSM adjusted for performance status (1 vs 0 or good health), Gleason score (9 or 10 vs 8), tumor category (T3-T4 vs T1-T2 or TX), and duration of ADT (2 years vs 4-6 months). Results: From a cohort of 2184 patients, 145 patients (6.6%) in 4 RCTs were eligible (median age, 63 [IQR, 46-67] years). Thirty-one patients died, and of these deaths, 22 were due to prostate cancer. Performance status was 0 for 139 patients (95.9%) and 1 for 6 patients (4.1%). A reduced but nonsignificant risk of ACM (HR, 0.51 [95% CI, 0.24-1.09]) and PCSM (sHR, 0.42 [95% CI, 0.17-1.02]) was associated with patients randomized to SOC plus docetaxel compared with SOC. The risk reduction in ACM (HR, 0.46 [95% CI, 0.21-1.02]) was more pronounced among patients with a performance status of 0 and was significant for PCSM (sHR, 0.30 [95% CI, 0.11-0.86]). Conclusions and Relevance: Adding docetaxel to SOC treatment for patients who are in otherwise good health with a PSA level of less than 4 ng/mL and a Gleason score of 8 to 10 was associated with a significant reduction in PCSM and therefore has the potential to improve prognosis.

Burden of prostate cancer in the Middle East: A comparative analysis based on global cancer observatory data.

BACKGROUND: Prostate cancer represents a significant global health issue, yet our understanding of its impact in the Middle East remains limited. This study aimed to assess the incidence and mortality of prostate cancer in the Middle East, and compare these rates to those in Europe and North America. MATERIALS AND METHODS: We utilized the 2020 Global Cancer Observatory data, compiling incidence and mortality rates of prostate cancer in 20 Middle Eastern countries. We calculated mortality-to-incidence ratios (MIR) and compared the age-standardized incidence rate (ASIR) and MIR between the Middle East and the combined regions of North America and Europe. The countries were further stratified based on the Human Development Index (HDI) and income level for additional analysis. RESULTS: In 2020, the Middle East documented an estimated 51,649 new prostate cancer diagnoses, accounting for 3.7% of global cases. Despite a significantly lower ASIR in the Middle East compared with Europe and North America (10.50 vs. 21.50, p = 0.0087), the region had a higher MIR (12.35 vs. 3.00, p = 0.0476). When stratified based on HDI or income levels, there was no significant difference in MIRs; however, a significant trend of increasing MIR with decreasing HDI (p = 0.028) and income levels (p = 0.016) was observed. CONCLUSIONS: Despite a lower incidence, our analysis showed a significantly higher MIR for prostate cancer in the Middle East compared with Europe and North America. These findings underscore the unique challenges posed by prostate cancer in the Middle East and emphasize the necessity of tailored strategies to address this pressing public health issue.

MR-guided prostate SBRT in prostate cancer patients with low-volume metastatic disease.

BACKGROUND: Recent data have found an overall survival benefit from prostate-directed radiotherapy in patients with low-volume metastatic prostate cancer. Prostate SBRT is an attractive treatment in this setting and may be optimised with MR-guided adaptive treatment. Here, we share our institutional experience delivering stereotactic MR-guided adaptive prostate SBRT (SMART) for patients with low-volume metastatic disease. METHODS: We reviewed patients with low-volume metastatic disease who received prostate SMART from October 2019 to December 2021 on a 0.35T MR-Linac. The cohort included 14 patients. Genitourinary (GU) and gastrointestinal (GI) toxicities were assessed using CTCAE v 5.0. Progression was defined as a change in systemic or hormonal therapy regimen as a result of PSA rise or disease progression. RESULTS: The median follow-up time was 29 months. Seven patients had hormone sensitive prostate cancer and 7 had castrate resistant prostate cancer (CRPC). 13 patients received 36.25 Gy in 5 fractions and one patient received 33 Gy in 5 fractions. At the time of last follow-up, 11 patients had not experienced progression and three patients, all with CRPC, had experienced progression. No patients developed local progression in the prostate after SMART. One patient experienced acute grade 2 urinary toxicity (7%) and no patients experienced acute grade 2 GI toxicity (0%). No grade 3 + acute toxicities were observed. CONCLUSIONS: Prostate SMART was found to be well tolerated and all patients had local control of disease within the prostate at the time of last follow-up. Prostate SMART may represent a low-risk and well-tolerated approach for delivering prostate-directed radiotherapy for patients with limited metastatic disease.

Risk of Short-Term Prostate-Specific Antigen Recurrence and Failure in Patients With Prostate Cancer: A Secondary Analysis of a Randomized Clinical Trial.

Importance: A shorter time interval to prostate-specific antigen (PSA) failure is associated with worse clinical outcomes; however, specific factors defining this state remain unknown. Objective: To evaluate the factors of a short time interval to PSA failure in order to identify patients for treatment escalation randomized clinical trials. Design, Setting, and Participants: This secondary analysis of a randomized clinical trial was a secondary analysis of the Dana-Farber Cancer Institute 05-043 trial and included 350 patients with nonmetastatic unfavorable risk prostate cancer (PC). Interventions: Patients were randomized 1:1 to receive androgen deprivation therapy (ADT) and radiation therapy (RT) plus docetaxel vs ADT and RT. Main Outcomes and Measures: Cumulative incidence rates curves of PSA failure, defined as PSA nadir plus 2 ng/mL or initiation of salvage therapies, and the Fine and Gray competing risks regression was used to assess the prognostic association between these factors and time to PSA failure. Results: The study included 350 males who primarily had a good performance status (330 [94.3%] with Eastern Cooperative Oncology Group score of 0), median (range) age of 66 (43-86) years, with 167 (46.6%) having Gleason scores of 8 to 10, and 195 (55.2%) presenting with a baseline PSA of more than 10 ng/mL. After a median (IQR) follow-up of 10.2 (8.0-11.4) years, having a PSA level of 10 ng/mL to 20 ng/mL (subdistribution hazard ratio [sHR], 1.98; 95% CI, 1.28-3.07; P = .002) and a Gleason score of 8 to 10 (sHR, 2.55; 95% CI, 1.63-3.99; P < .001) were associated with a shorter time to PSA failure, and older age (sHR, 0.82; 95% CI, 0.72-0.93; P = .002) was associated with reduced risk for PSA failure after adjusting for other baseline clinical factors. The high-risk category, defined by these 3 factors, was associated with a shorter time to PSA failure (sHR, 2.69; 95% CI, 1.84-3.93; P < .001). Conclusions and Relevance: In this secondary analysis of a randomized clinical trial of males with unfavorable risk PC, young age, PSA of 10 ng/mL or more, and a Gleason score of 8 to 10 estimated a shorter time to PSA failure. A subgroup of males at very high-risk for early PSA failure, as defined by our study, may benefit from treatment escalation with androgen receptor signaling inhibitors or cytotoxic chemotherapy and should be the subject of a prospective randomized clinical trial. Trial Registration: NCT00116142.

Acute toxicity comparison of magnetic resonance-guided adaptive versus fiducial or computed tomography-guided non-adaptive prostate stereotactic body radiotherapy: A systematic review and meta-analysis.

BACKGROUND: Stereotactic body radiotherapy (SBRT) is gaining wider adoption for prostate cancer management but there remain significant toxicity risks when delivering prostate SBRT with standard techniques. Magnetic resonance-guided daily adaptive SBRT (MRg-A-SBRT) offers technological advantages in precision of radiation dose delivery, but the toxicity profile associated with MRg-A-SBRT compared to more standardly used fiducial or computed tomography-guided non-adaptive prostate SBRT (CT-SBRT) remains unknown. METHODS: A meta-analysis to compare acute toxicity rates associated with MRg-A-SBRT and CT-SBRT for prostate cancer was performed in compliance with PRISMA guidelines. MEDLINE (PubMed) and Google Scholar were searched for prospective studies of prostate SBRT that were published between January 1, 2018 and August 31, 2022. Random effects and fixed effects models were used to estimate pooled toxicity rates, and meta-regression was performed to compare toxicity between MRg-A-SBRT and CT-SBRT study groups. RESULTS: Twenty-nine prospective studies were identified that met the inclusion criteria and included a total of 2547 patients. The pooled estimates for acute grade 2 or higher (G2+) genitourinary (GU) and gastrointestinal (GI) toxicity for MRg-A-SBRT were 16% (95% confidence interval [CI], 10%-24%) and 4% (95% CI, 2%-7%) and for CT-SBRT they were 28% (95% CI, 23%-33%) and 9% (95% CI, 6%-12%), respectively. On meta-regression, the odds ratios for acute G2+ GU and GI toxicities comparing MRg-A-SBRT and CT-SBRT were 0.56 (95% CI, 0.33-0.97, p = .04) and 0.40 (95% CI, 0.17-0.96, p = .04), respectively. CONCLUSION: MRg-A-SBRT is associated with a significantly reduced risk of acute G2+ GU or GI toxicity compared to CT-SBRT. Longer follow-up will be needed to evaluate late toxicity and disease control outcomes. PLAIN LANGUAGE SUMMARY: Magnetic resonance imaging-guided daily adaptive prostate stereotactic radiation (MRg-A-SBRT) is a treatment that may allow for delivery of prostate radiation more precisely than other radiotherapy techniques, but it is unknown whether this reduces side effects compared to standardly used computed tomography-guided SBRT (CT-SBRT). In this systematic review and meta-analysis combining data from 29 clinical trials including 2547 patients, it was found that the risk of short-term urinary side effects was reduced by 44% and the risk of short-term bowel side effects was reduced by 60% with MRg-A-SBRT compared to CT-SBRT.

Prostate-Specific Antigen Level at the Time of Salvage Therapy After Radical Prostatectomy for Prostate Cancer and the Risk of Death.

PURPOSE: Both the performance characteristics of prostate-specific membrane antigen positron emission tomography and insurance approval improves with increasing prostate-specific antigen (PSA) level causing some physicians to delay post-radical prostatectomy salvage radiation therapy (sRT) after PSA failure. Yet, it is unknown for men with at most one high-risk factor (ie, pT3/4 or prostatectomy [p] Gleason score 8-10) whether a PSA level exists above which initiating sRT is associated with increased all-cause mortality (ACM)-risk and was investigated. METHODS: Using a multinational database of 25,551 patients with pT2-4N0 or NXM0 prostate cancer, multivariable Cox regression analysis evaluated whether an association with a significant increase in ACM-risk existed when sRT was delivered above a prespecified PSA level beginning at 0.10 ng/mL and in 0.05 increments up to 0.50 ng/mL versus at or below that level. The model was adjusted for age at and year of radical prostatectomy, established prostate cancer prognostic factors, institution, and the time-dependent use of androgen deprivation therapy. RESULTS: After a median follow-up of 6.00 years, patients who received sRT at a PSA level >0.25 ng/mL had a significantly higher ACM-risk (AHR, 1.49; 95% CI, 1.11 to 2.00; P = .008) compared with men who received sRT when the PSA was ≤0.25 mg/mL. This elevated ACM-risk remained significant for all PSA cutpoints up to 0.50 ng/mL but was not significant at PSA cutpoint values below 0.25 ng/mL. CONCLUSION: Among patients with at most one high-risk factor, initiating sRT above a PSA level of 0.25 ng/mL was associated with increased ACM-risk.

Development and External Validation of a Machine Learning Model for Prediction of Lymph Node Metastasis in Patients with Prostate Cancer.

BACKGROUND: Pelvic lymph node dissection (PLND) is the gold standard for diagnosis of lymph node involvement (LNI) in patients with prostate cancer. The Roach formula, Memorial Sloan Kettering Cancer Center (MSKCC) calculator, and Briganti 2012 nomogram are elegant and simple traditional tools used to estimate the risk of LNI and select patients for PLND. OBJECTIVE: To determine whether machine learning (ML) can improve patient selection and outperform currently available tools for predicting LNI using similar readily available clinicopathologic variables. DESIGN, SETTING, AND PARTICIPANTS: Retrospective data for patients treated with surgery and PLND between 1990 and 2020 in two academic institutions were used. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: We trained three models (two logistic regression models and one gradient-boosted trees-based model [XGBoost]) on data provided from one institution (n = 20267) with age, prostate-specific antigen (PSA) levels, clinical T stage, percentage positive cores, and Gleason scores as inputs. We externally validated these models using data from another institution (n = 1322) and compared their performance to that of the traditional models using the area under the receiver operating characteristic curve (AUC), calibration, and decision curve analysis (DCA). RESULTS AND LIMITATIONS: LNI was present in 2563 patients (11.9%) overall, and in 119 patients (9%) in the validation data set. XGBoost had the best performance among all the models. On external validation, its AUC outperformed that of the Roach formula by 0.08 (95% confidence interval [CI] 0.042-0.12), the MSKCC nomogram by 0.05 (95% CI 0.016-0.070), and the Briganti nomogram by 0.03 (95% CI 0.0092-0.051; all p < 0.05). It also had better calibration and clinical utility in terms of net benefit on DCA across relevant clinical thresholds. The main limitation of the study is its retrospective design. CONCLUSIONS: Taking all measures of performance together, ML using standard clinicopathologic variables outperforms traditional tools in predicting LNI. PATIENT SUMMARY: Determining the risk of cancer spread to the lymph nodes in patients with prostate cancer allows surgeons to perform lymph node dissection only in patients who need it and avoid the side effects of the procedure in those who do not. In this study, we used machine learning to develop a new calculator to predict the risk of lymph node involvement that outperformed traditional tools currently used by oncologists.

Cribriform morphology is associated with higher risk of biochemical recurrence after radical prostatectomy in patients with Grade Group 5 prostate cancer.

AIMS: Grade Group 5 (GG5) prostate cancer (PCa) is associated with a high risk of disease recurrence after radical prostatectomy (~75% at 5 years). However, this is a heterogeneous category that includes neoplasms with different combinations of Gleason pattern (GP) 4 and 5. Within GP4, large cribriform growth has been associated with adverse disease-specific outcomes in GG2-4 PCa. Less is known about the significance of cribriform morphology and the different histologic patterns of GP5 in GG5 PCa. METHODS AND RESULTS: In this study we evaluated the prognostic implications of cribriform morphology (either invasive or intraductal, henceforth "cribriform") and large solid growth or comedonecrosis (comedo/solid) in patients with GG5 PCa. One-hundred and thirty prostatectomies from a single institution were analysed. The presence of comedo/solid components was associated with a higher frequency of concurrent cribriform PCa (85.7% versus 45.9%, P < 0.001), lymphovascular invasion (44.6% versus 27%, P = 0.04), and biochemical recurrence (48.2% versus 28.4%, P = 0.03). The presence of large cribriform growth was associated with a higher frequency of extraprostatic involvement (i.e. pT3a-b; 85.3% versus 68.7%, P = 0.02), positive surgical margins (47.6% versus 29.2%, P = 0.04) and biochemical recurrence (47.6% versus. 18.7%, P = 0.001). Kaplan-Meier analysis demonstrated that GG5 PCa with cribriform or comedo/solid components had a higher probability of biochemical recurrence. Multivariable analysis showed that only cribriform components were an independent predictor of a higher risk of biochemical recurrence in this series. CONCLUSION: These findings highlight the importance of reporting the presence of cribriform components in GG5 PCa and suggest that cribriform morphology might help decide postsurgical management in these patients.