Personalized risk stratification for patients with early prostate cancer (PRONTO): A Canadian team biomarker project.
Bibliographic record
Abstract
109 Background: Current practice stratifies men with prostate cancer into risk groups based primarily on Gleason grade. When applied to biopsy samples, the Gleason grading is inaccurate due to sampling error and inter-observer variation. The result is that men either receive unnecessary surgical treatment, or they don’t receive adequate treatment, leading to worse outcomes. Previously published genomic tests have not successfully distinguished indolent low grade (G6 or GG1) cancers from their more aggressive intermediate grade (G7 or GG2 and 3) counterparts. PRONTO is specifically aimed at creating a multi-modal risk stratification tool to improve treatment stratification following a core biopsy diagnosis. Methods: PRONTO links 7 projects, each with novel diagnostic assays for risk stratification that focus on analysis of copy number variations (CNV), DNA hypermethylation, trans-differentiation, cancer metabolism, or the tumor microenvironment. We merged the best transcripts from each project into a single NanoString gene expression assay, measuring 393 transcripts, in a cohort of 365 cases of radical prostatectomy from low-to-intermediaterisk patients. To minimize sampling error, we took multiple samples, and obtained high grade, low grade and benign areas for each radical prostatectomy case. Results: Our primary goal was to develop a multivariate molecular classifier of grade that distinguished G6 from G7 (3+4 or 4+3). Cases were randomly partitioned into five equally sized groups. A supervised machine learning algorithm (random forests) was trained on samples from four of the groups, and then evaluated by testing on the fifth group. This process was repeated for each of the five groups, yielding a combined clinical and molecular classifier. DNA methylation profiles and CNV profiles are currently being integrated into our classifier Conclusions: We have developed a multivariate classifier that distinguishes low grade from intermediate grade prostate cancer. It will be clinically validated in biopsy samples from large cohorts of early prostate cancer 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 | 0.009 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".