Prospective analysis of 4,474 prostate biopsies to evaluate potential treatment management impact of combined clinical-genomic risk classification.
Bibliographic record
Abstract
39 Background: Prior studies suggested integrated clinical-genomic risk grouping can more accurately prognosticate prostate cancer (PCa) outcome than NCCN clinical risk. We evaluated the potential for genomic testing to reclassify patients in a manner that could change management compared to NCCN risk groups. Methods: We evaluated 4,474 consecutive patients with PCa who received the Decipher Biopsy test between 01/2016-08/2017 and had information to determine NCCN risk. Genomic categorizations with the potential to change management were defined as NCCN very low/low to genomic intermediate or high (active surveillance to active treatment), NCCN favorable intermediate to genomic high (radiation therapy [RT] alone to RT plus androgen deprivation therapy [ADT]), NCCN unfavorable intermediate to genomic low (RT + ADT to RT alone), NCCN high risk to genomic low (RT + long term ADT to RT + short term ADT). Results: There were 927 NCCN low-risk, 2,427 intermediate, and 1,120 high-risk patients. Among NCCN low-risk, the incidence of genomic low, intermediate, and high risk was 58.7%, 25.0%, and 16.3% respectively, for NCCN intermediate it was 36.5%, 27.6%, and 35.8%, and for NCCN high risk it was 15.9%, 17.1%, and 67.1%. Management could have been changed in the 41.3% of NCCN low risk patients with intermediate or high genomic risk, 26.7% of favorable intermediate risk patients who had high genomic risk, 32.4% of unfavorable intermediate risk patients with low genomic risk, and 15.9% of high risk patients with low genomic risk. Conclusions: A slight majority (54%) of Decipher Biopsy users have NCCN intermediate-risk disease, likely reflecting a need for further prognostic information to refine recommendations in intermediate risk. Reclassification of NCCN groups by genomic risk was common and an integrated clinical-genomic risk system could have altered treatment recommendations in 41.3% of NCCN low, 26.7% of favorable intermediate, 32.4% of unfavorable intermediate risk, and 15.9% of high risk patients.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| 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".