Validation of the Decipher Test for predicting adverse pathology in candidates for prostate cancer active surveillance
Bibliographic record
Abstract
ABSTACT: BACKGROUND: Many men diagnosed with prostate cancer are active surveillance (AS) candidates. However, AS may be associated with increased risk of disease progression and metastasis due to delayed therapy. Genomic classifiers, e.g., Decipher, may allow better risk-stratify newly diagnosed prostate cancers for AS. METHODS: Decipher was initially assessed in a prospective cohort of prostatectomies to explore the correlation with clinically meaningful biologic characteristics and then assessed in diagnostic biopsies from a retrospective multicenter cohort of 266 men with National Comprehensive Cancer Network (NCCN) very low/low and favorable-intermediate risk prostate cancer. Decipher and Cancer of the Prostate Risk Assessment (CAPRA) were compared as predictors of adverse pathology (AP) for which there is universal agreement that patients with long life-expectancy are not suitable candidates for AS (primary pattern 4 or 5, advanced local stage [pT3b or greater] or lymph node involvement). RESULTS: Decipher from prostatectomies was significantly associated with adverse pathologic features (p-values < 0.001). Decipher from the 266 diagnostic biopsies (64.7% NCCN-very-low/low and 35.3% favorable-intermediate) was an independent predictor of AP (odds ratio 1.29 per 10% increase, 95% confidence interval [CI] 1.03-1.61, p-value 0.025) when adjusting for CAPRA. CAPRA area under curve (AUC) was 0.57, (95% CI 0.47-0.68). Adding Decipher to CAPRA increased the AUC to 0.65 (95% CI 0.58-0.70). NPV, which determines the degree of confidence in the absence of AP for patients, was 91% (95% CI 87-94%) and 96% (95% CI 90-99%) for Decipher thresholds of 0.45 and 0.2, respectively. Using a threshold of 0.2, Decipher was a significant predictor of AP when adjusting for CAPRA (p-value 0.016). CONCLUSION: Decipher can be applied to prostate biopsies from NCCN-very-low/low and favorable-intermediate risk patients to predict absence of adverse pathologic features. These patients are predicted to be good candidates for active surveillance.
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 | 0.004 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".