Confirmatory Clinical Validation of a Serum-Based Biomarker Signature for Detection of Early-Stage Pancreatic Ductal Adenocarcinoma
Bibliographic record
Abstract
Early detection of pancreatic ductal adenocarcinoma (PDAC) could extend patient survival, and biomarkers to facilitate this are urgently needed. Here, we performed a second independent validation of PancreaSure, a 5-plex serum biomarker signature to detect early-stage PDAC in high-risk individuals. In contrast to the first validation, this study’s cohort was preemptively balanced for age and sex and only included samples stored for fewer than 5 years. The primary endpoint was to measure test sensitivity against the performance target of 65%. Measuring specificity against the performance target of 90% and comparing test performance to that of carbohydrate antigen 19-9 (CA 19-9) alone were secondary endpoints. Signature analytes were retrospectively measured in serum from a blinded independent cohort of Stage I and II PDAC cases and high-risk controls. A predictive signal for PDAC was generated from a predefined cutoff established in a previous model development study. PancreaSure distinguished early-stage PDAC from controls with 76.5% sensitivity (95% CI, 67.7–83.9), significantly higher than the performance target (p = 0.005). PancreaSure achieved 87.8% specificity (95% CI, 83.9–91.4), similar to the performance goal, and significantly outperformed sensitivity of CA 19-9 alone (p = 0.02). These results confirm that PancreaSure performs well at detecting early-stage PDAC in high-risk individuals.
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 | 0.008 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| 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".