Impact of a genomic classifier of metastatic risk on treatment recommendations post-radical prostatectomy: Report from the DECIDE study group.
Bibliographic record
Abstract
e16044 Background: Only a minority of prostate cancer patients with adverse pathology and biochemical recurrence (BCR) post radical prostatectomy (RP) experience metastasis and die from prostate cancer. Improved risk prediction models using genomic information may enable clinicians to better weigh the risk of metastasis and the morbidity and costs of treatment in a clinically heterogeneous population. We present a clinical utility study that evaluates the influence on urologist treatment recommendations for patients at risk of metastasis using a genomic-based prediction model (Decipher). Methods: A prospective, pre-post design was used to assess urologist treatment recommendations following RP in both the adjuvant (without any evidence of PSA rise) and salvage (BCR) settings. Urologists were presented de-identified pathology reports and genomic classifier (GC) test results for 24 patients from a previously conducted GC validation study in high-risk post RP men. Participants were fellowship trained, high-volume urologic oncologists (n=21) from 18 US institutions. Treatment recommendations for secondary therapy were made based solely on clinical information (pre-GC) and then with genomic biomarker information (post-GC). This study was approved by an independent IRB. Results: Treatment recommendations changed from pre-GC to post- GC in 43% of adjuvant, and in 53% of salvage setting case evaluations. In the adjuvant setting, urologists changed their treatment recommendations from treatment (i.e. radiation and/or hormones) to close observation post-GC in 27% of cases. However, for cases with low GC risk (<3% risk of metastasis), 79% of these men were recommended for observation post-GC. Consistent trends were observed in the salvage setting including 24% patients with low GC risk recommended for observation even after BCR. Conclusions: These results indicate that urologists across a range of practice settings are likely to change many treatment decisions when presented with genomic biomarker information following RP. Implementation of the GC test into routine clinical practice may better direct treatment decision-making post-RP.
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 | 0.017 | 0.044 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".