MétaCan
Menu
Back to cohort

Decipher score as a predictor of response to treatment intensification in the NRG Oncology-RTOG 0534 (SPPORT) phase III randomized post-prostatectomy salvage radiotherapy trial.

2025· article· en· W4407699726 on OpenAlexaff
Alan Pollack, Marla Johnson, J. Proudfoot, Elai Davicioni, Alan Dal Pra, Jeff Simko, André‐Guy Martin, Himanshu Lukka, Steve Angyalfi, Jeff M. Michalski, Marie Duclos, George Rodrigues, R. Jeffrey Lee, Kevin S. Roof, Angela Y. Jia, Samantha A. Seaward, Nader Khaouam, Theodore Karrison, Felix Y. Feng, Phuoc T. Tran

Bibliographic record

VenueJournal of Clinical Oncology · 2025
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsPrincess Margaret Cancer CentreUniversity Health NetworkMcMaster UniversityMcGill University Health CentreCentre hospitalier universitaire de Québec
FundersNational Institutes of Health
KeywordsMedicineProstatectomyDECIPHEROncologyInternal medicineRadiation therapyRandomized controlled trialProstate cancerCancerBioinformatics

Abstract

fetched live from OpenAlex

399 Background: The three-arm randomized SPPORT trial (n=1792) examined the effect of treatment intensification on the outcome of men treated with salvage radiotherapy (RT) for a detectable PSA. The arms were prostate bed RT (PBRT) alone (Arm I), PBRT + short term androgen deprivation therapy (STADT; Arm 2), and PBRT + STADT + pelvic lymph node RT (PLNRT; Arm 3). With treatment intensification in Arms 2 and 3, there were significant incremental gains in the primary freedom from progression (FFP) endpoint, but not metastasis free survival (MFS) with about 8 yr median follow-up; although metastatic events were reduced with intensification. Decipher score (DS) is strongly prognostic for metastasis and was hypothesized to be independently significant of clinical-pathologic covariates in predicting the need for treatment intensification. The main objective was to determine if gene expression estimates of metastatic risk using Decipher score result in significant interactions with treatment, especially for PLNRT. Methods: Prospectively collected prostatectomy tissuewas available for RNA extraction and generation of DS (Veracyte, San Diego, CA) in 916 patients. The protocol FFP endpoint included biochemical (nadir+2 ng/mL) failure, clinical failure, or death from any cause. MFS included distant metastasis or death from any cause. Multivariable (MVA) Cox models adjusted for Gleason score, margin status, pT-stage, pre-RT PSA, age, and race. Results: DS (median 0.61; IQR: 0.45-0.79) were obtained for 709 patients (median follow-up 7.9 yr), with 215 in Arm 1, 247 in Arm 2, and 247 in Arm 3. The arms were balanced for key covariates. There were 226 FFP and 136 MFS events. On MVA, DS (per 0.1 unit) was prognostic for FFP (HR 1.10, 95% CI 1.03-1.17, p=0.007) and borderline for MFS (HR 1.08, 95% CI 0.99 - 1.18, p=0.08). There was no significant DS-related benefit to adding STADT to PBRT. Adding PLNRT + STADT to PBRT resulted in a greater benefit in patients with high (>0.60, HR 0.36, 95% CI 0.25-0.54, p<0.001) vs. lower (≤0.60, HR 0.76, 95% CI 0.46-1.26, p=0.29) DSs, with an absolute benefit of 27% vs. 11% in high vs. lower DS, along with a significant treatment interaction on MVA (p-int = 0.04). Relative MFS benefit from adding PLNRT + STADT to PBRT ± STADT was greater in patients with high (HR 0.60, 95% CI 0.37-0.97, p=0.04) vs. lower (HR 1.14, 95% CI 0.66-1.98, p=0.63) DS, with a 10-year absolute benefit of 6% vs. 0%, and a borderline significant treatment interaction on MVA (p-int = 0.06). Conclusions: The unique SPPORT trial intensification design facilitated the discovery that high metastatic risk, as assessed by DS, may be abrogated at least in part by PLNRT, suggesting that lymph node micrometastases are a sole site of metastasis in some patients. Decipher score is a meaningful predictor of gains from PLNRT. Clinical trial information: NCT00567580 .

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.025
metaresearch head score (Gemma)0.048
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Randomized trial · Consensus signal: Randomized trial
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.200
Threshold uncertainty score0.960

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0250.048
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0030.001
Bibliometrics0.0000.000
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.069
GPT teacher head0.506
Teacher spread0.437 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designRandomized trial
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Clinical OncologySame topicRadiomics and Machine Learning in Medical ImagingFrench-language works237,207