Improving the stratification of intermediate risk prostate cancer
Bibliographic record
Abstract
BACKGROUND: Intermediate risk prostate cancer (IR PCa) may exhibit a wide array of phenotypes, from favorable to unfavorable. NCCN criteria help distinguishing between favorable versus unfavorable subgroups. We studied and attempted to improve this classification. METHODS: Within the SEER database 2010-2016, we identified 19,193 IR PCa patients treated with radical prostatectomy. A multivariable logistic regression model predicting unfavorable IR PCa was developed and externally validated, in addition to a head-to-head comparison with NCCN IR PCa stratification. RESULTS: Model development (development cohort N.=13,436: 3585 unfavorable versus 9851 favorable) rested on age, PSA, clinical T stage, biopsy Gleason Grade Group (GGG) and percentage of positive cores. All were independent predictors of unfavorable IR PCa. In external validation cohort (N.=5757: 1652 unfavorable versus 4105 favorable), NCCN stratification was 61.8% accurate in discriminating between favorable versus unfavorable, compared to 67.6% for nomogram, which exhibited excellent calibration, less pronounced departures from ideal prediction and greater net-benefit in decision curve analyses (DCA) than NCCN stratification. The optimal nomogram cutoff misclassified 312 of 1976 patients (15.8%) versus 598 of 2877 (20.8%) for NCCN stratification. Of NCCN misclassified patients, 90.0% harbored pT3-4 stages versus 84.6% of nomogram. CONCLUSIONS: The newly developed, externally validated nomogram discriminates better between favorable versus unfavorable IR PCa, according to overall accuracy, calibration, DCA, and actual numbers and stage distribution of misclassified 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 | 0.006 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 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".