Expanding inclusion criteria for active surveillance in intermediate-risk prostate cancer: a machine learning approach.

PURPOSE: To develop new selection criteria for active surveillance (AS) in intermediate-risk (IR) prostate cancer (PCa) patients. METHODS: Retrospective study including patients from 14 referral centers who underwent pre-biopsy mpMRI, image-guided biopsies and radical prostatectomy. The cohort included biopsy-naive IR PCa patients who met the following inclusion criteria: Gleason Grade Group (GGG) 1-2, PSA < 20 ng/mL, and cT1-cT2 tumors. We relied on a recursive machine learning partitioning algorithm developed to predict adverse pathological features (i.e., ≥ pT3a and/or pN + and/or GGG ≥ 3). RESULTS: A total of 594 patients with IR PCa were included, of whom 220 (37%) had adverse features. PI-RADS score (weight:0.726), PSA density (weight:0.158), and clinical T stage (weight:0.116) were selected as the most informative risk factors to classify patients according to their risk of adverse features, leading to the creation of five risk clusters. The adverse feature rates for cluster #1 (PI-RADS ≤ 3 and PSA density < 0.15), cluster #2 (PI-RADS 4 and PSA density < 0.15), cluster #3 (PI-RADS 1-4 and PSA density ≥ 0.15), cluster #4 (normal DRE and PI-RADS 5), and cluster #5 (abnormal DRE and PI-RADS 5) were 11.8, 27.9, 37.3, 42.7, and 65.1%, respectively. Compared with the current inclusion criteria, extending the AS criteria to clusters #1 + #2 or #1 + #2 + #3 would increase the number of eligible patients (+ 60 and + 253%, respectively) without increasing the risk of adverse pathological features. CONCLUSIONS: The newly developed model has the potential to expand the number of patients eligible for AS without compromising oncologic outcomes. Prospective validation is warranted.

What is the optimal definition of misclassification in patients with very low-risk prostate cancer eligible for active surveillance? Results from a multi-institutional series.

BACKGROUND: The risk of unfavorable prostate cancer in active surveillance (AS) candidates is nonnegligible. However, what represents an adverse pathologic outcome in this setting is unknown. We aimed at assessing the optimal definition of misclassification and its effect on recurrence in AS candidates treated with radical prostatectomy (RP). MATERIALS AND METHODS: Overall, 1,710 patients eligible for AS according to Prostate Cancer Research International: Active Surveillance criteria treated with RP between 2000 and 2013 at 3 centers were evaluated. Patients were stratified according to pathology results at RP: organ-confined disease and pathologic Gleason score ≤ 6 (group 1); organ-confined disease and Gleason score 3+4 (group 2); and non-organ-confined disease, Gleason score ≥ 4+3, and nodal invasion (group 3). Biochemical recurrence (BCR) was defined as 2 consecutive prostate-specific antigen (PSA) ≥ 0.2 ng/ml. Kaplan-Meier curves assessed time to BCR. Multivariable Cox regression analyses tested the association between pathologic features and BCR. Multivariable logistic regression analyses identified the predictors of adverse pathologic characteristics. RESULTS: Overall, 926 (54.2%), 653 (33.0%), and 220 (12.9%) patients were categorized in groups 1, 2, and 3, respectively. Median follow-up was 32.2 months. The 5-year BCR-free survival rate was 94.2%. Patients in group 3 had lower BCR-free survival rates compared with those in group 1 (79.1% vs. 97.0%, P<0.001). No differences were observed between patients included in group 1 vs. group 2 (97.0% vs. 94.7%, P = 0.1). These results were confirmed at multivariable analyses and after stratification according to margin status. Older age and PSA density ≥ 10 ng/ml/ml were associated with higher risk of unfavorable pathologic characteristics (i.e., inclusion in group 3; all P<0.001). CONCLUSIONS: Among patients eligible for AS treated with RP, only men with Gleason score ≥ 4+3 or non-organ-confined disease at final pathology were at increased risk of BCR. These individuals represent the real misclassified AS patients, who can be predicted based on older age and higher PSA density.

Clinical Perspectives from Randomized Phase 3 Trials on Prostate Cancer: An Analysis of the ClinicalTrials.gov Database.

BACKGROUND: It is not easy to overview pending phase 3 trials on prostate cancer (PCa), and awareness of these trials would benefit clinicians. OBJECTIVE: To identify all phase 3 trials on PCa registered in the ClinicalTrials.gov database with pending results. DESIGN AND SETTING: On September 29, 2014, a database was established from the records for 175 538 clinical trials registered on ClinicalTrials.gov. A search of this database for the substring "prostat" identified 2951 prostate trials. Phase 3 trials accounted for 441 studies, of which 333 concerned only PCa. We selected only ongoing or completed trials with pending results, that is, for which the primary endpoint had not been published in a peer-reviewed medical journal. RESULTS AND LIMITATIONS: We identified 123 phase 3 trials with pending results. Trials were conducted predominantly in North America (n=63; 51%) and Europe (n=47; 38%). The majority were on nonmetastatic disease (n=82; 67%), with 37 (30%) on metastatic disease and four trials (3%) including both. In terms of intervention, systemic treatment was most commonly tested (n=71; 58%), followed by local treatment 34 (28%), and both systemic and local treatment (n=11; 9%), with seven (6%) trials not classifiable. The 71 trials on systemic treatment included androgen deprivation therapy (n=34; 48%), chemotherapy (n=15; 21%), immunotherapy (n=9; 13%), other systemic drugs (n=9; 13%), radiopharmaceuticals (n=2; 3%), and combinations (n=2; 3%). Local treatments tested included radiation therapy (n=27; 79%), surgery (n=5; 15%), and both (n=2; 2%). A limitation is that not every clinical trial is registered on ClinicalTrials.gov. CONCLUSION: There are many PCa phase 3 trials with pending results, most of which address questions regarding systemic treatments for both nonmetastatic and metastatic disease. Radiation therapy and androgen deprivation therapy are the interventions most commonly tested for local and systemic treatment, respectively. PATIENT SUMMARY: This report describes all phase 3 trials on prostate cancer registered in the ClinicalTrials.gov database with pending results. Most of these trials address questions regarding systemic treatments for both nonmetastatic and metastatic disease. Radiation therapy and androgen deprivation therapy are the interventions most commonly tested for local and systemic treatment, respectively.