A genomic classifier independently prognostic of prostate cancer death in a high-risk surgical cohort.
Bibliographic record
Abstract
60 Background: Biomarkers may improve ascertainment of progression risk after radical prostatectomy (RP). We compared two validated post-RP classifiers: the Decipher genomic classifier (GC) and CAPRA-S (based on standard clinicopathologic parameters), to predict prostate cancer-specific mortality (CSM) in a contemporary cohort of RP patients. Methods: From a cohort of 1,010 RP patients treated from 2000-06, a case-cohort design was used to analyze a subset of 219 men with one or more high risk features and available paraffin-embedded tissue. Median follow-up was 6 years. The GC, derived from expression levels of 22 biomarkers and dichotomized to denote low- and high-risk, and CAPRA-S, calculated from preoperative PSA and pathologic grade and staging variables, scores were determined. The scores were evaluated individually and in combination using concordance index, decision curve, (DC), re-classification, and Cox analyses for prediction of CSM. Results: 212 men had full data available to calculate the CAPRA-S; 27 experienced CSM. The c-index for GC (0.78) and CAPRA-S (0.76) were similar, although GC showed improved calibration and higher net-benefit on DC analysis. In 103 patients with high-risk CAPRA-S scores (≥6), GC scores were likewise high-risk for 49, among whom 19 had CSM events. The other 54 men were reclassified as low-risk by GC; among these only 1 CSM event was observed. In multivariable Cox analysis both GC and CAPRA-S were independently prognostic of CSM, with hazard ratios of 1.62 (p<0.001) and 1.22 (p=0.01), respectively for unit score increases. A combined model defined based on the Cox model as (0.20*CAPRA-S + 5.68*GC) was more accurate than either score alone (p<0.001 by likelihood ratio test). DC analysis indicated greater net benefit for the combined model than for either score alone. Conclusions: In men treated with RP at high risk of recurrence based on clinical and pathologic variables, both GC and CAPRA-S were significant predictors of CSM. Notably, GC was able to 'down-risk' >50% of men stratified to high risk based on CAPRA-S alone. Thus the GC provides independent prognostic information, and a model integrating GC and CAPRA-S may further improve the prediction of lethal prostate cancer.
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 | 0.001 | 0.003 |
| 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 | 0.000 | 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".