TEST:

Decipher Prostate Cancer Test

Unfavourable histology was associated with higher Decipher scores and increased BCR risk. The addition of the histology category improved BCR prediction in a multivariable model.

P2, N=324, Active, not recruiting, NRG Oncology | Trial primary completion date: Mar 2026 --> Mar 2025

Patients with GC low-risk and PSC-LD csPCa may represent the ideal subgroup for FT. Prospective validation in a large cohort is warranted.

A DGC score >0.85 delineates a distinct subgroup with markedly adverse oncologic outcomes. Recognition of this VHR category refines postoperative assessment and supports personalized adjuvant or salvage therapy.

Rationale: The mode of action of [177Lu]Lu-PSMA-617 (LuPSMA) therapy is not fully understood and a relevant fraction of patients show treatment failure...In treatment-naive patient samples, PD-L2 expression was associated with unfavorable, whereas M1/M0 macrophages with favorable outcomes, which might indicate that immune checkpoint inhibition could be a combination partner of LuPSMA therapy. In patient biopsy samples acquired after the start of systemic treatment, AR gene expression and DNA repair signatures appear to be significantly altered and PD-L2 became a protective marker.

Current evidence supports the multidisciplinary integration of these biomarkers to overcome the limitations of PSA, improve biopsy decision-making, better distinguish indolent from aggressive tumors, and optimize therapeutic strategies. Finally, future research directions aimed at validating and incorporating emerging biomarkers into clinical practice are outlined, with the goal of improving outcomes in patients with localized prostate cancer.

The Decipher GC score was independently associated with DM and MFS, and LP tumors may benefit from addition of CT. Validation of these findings may allow more effective use of CT in men with localized PC. The original NRG/RTOG 0521 trial is registered on ClinicalTrials.gov as NCT00288080.

This is the first study to integrate PSMA-PET, MRI, and genomics in ML-based nomogram models for side-specific EPE prediction. XGBoost models demonstrated superior predictive power, especially when combining PET and DGC. These findings highlight the potential of a multi-biomarker, machine learning approach to improve preoperative risk stratification and support personalized treatment planning. Further studies will validate this model in larger cohorts.

Genomic classifiers in GG1 cores did not predict coexisting GG2+ cancer, while dGPS signatures showed some promise in detecting GG3+ cancer elsewhere in the gland. None of the signatures showed a difference between groups when using the highest volume GG1 core, which is the standard practice for genomic classifiers.

These findings independently validate PATHOMIQ_PRAD as a reliable predictor of clinical risk in the postprostatectomy setting. PATHOMIQ_PRAD therefore merits prospective evaluation as a risk stratification tool to select patients for adjuvant or early salvage interventions.

P2, N=40, Not yet recruiting, Icahn School of Medicine at Mount Sinai

In conclusion, the decision to add ADT to sRT in BCR patients should be individualized based on PSA kinetics, imaging, and genomic profiling. Shared decision-making and future biomarker-driven trials will be key to personalizing therapy and improving outcomes while minimizing harm.