Validation of a genomic classifier that predicts metastatic disease progression in men with biochemical recurrence post radical prostatectomy.
Bibliographic record
Abstract
5033 Background: Almost 50,000 men per year will present with biochemical recurrence (BCR) following local treatment for prostate cancer. These men with rising PSAs as the lone indicator of recurrence present a management dilemma due to their varied outcomes with only a proportion developing subsequent metastatic disease. Thus, there is a clear need to improve patient risk stratification in this context. Here, we evaluate Decipher, a genomic classifier (GC) in men with BCR following radical prostatectomy (RP) for its ability to predict metastasis. Methods: The 22-marker GC was validated in a prospectively designed case-cohort study of 1,010 clinically high-risk RP patients. 219 patients, including 85 who developed BCR at least 6 months post-RP were subjected to microarray analysis and GC scores were generated. Survival ROC curves, weighted Cox proportional hazards, and decision curves were used to compare the performance of the GC to Gleason score (GS), PSA doubling time (PSAdT) and time to BCR (ttBCR). Results: GC scores significantly stratified these men into those who would or would not develop metastasis after BCR (8% versus 40% of patients developed metastasis at 3 years following BCR depending on GC score category, p<0.001). The AUC for GC was 0.82 (95% CI, 0.76-0.86), compared to that of GS 0.64 (0.58-0.70), PSAdT 0.69 (0.61-0.77) and ttBCR 0.52 (0.46-0.59). In decision curve analysis, the GC had the highest overall ‘net benefit’ and in multivariable modeling with clinicopathologic variables, only GC (p=0.006) and GS (p=0.046) scores were significant predictors of metastasis. Conclusions: When compared to clinicopathologic variables, the GC better predicted metastatic progression among men with BCR following RP. While confirmatory studies in additional patient populations are required, these results suggest that use of the GC can allow for better selection of men requiring additional treatment at the time of BCR.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".