A High Performing Biomarker Signature for Detecting Early-Stage Pancreatic Ductal Adenocarcinoma in High-Risk Individuals
Bibliographic record
Abstract
Background/Objectives: Early detection of pancreatic cancer can improve patient survival, and blood-based biomarkers to aid in this are a significant need. The goal of this study was to develop and evaluate the performance of a 4- to 6-plex biomarker signature for detection of early-stage pancreatic ductal adenocarcinoma (PDAC) that performs well in high-risk controls. Methods: Enzyme-linked immunosorbent assays were used to measure 10 previously identified serum protein biomarker candidates in Stage I and II PDAC cases (n = 128), high-risk controls (n = 465), and normal-risk controls (n = 30). Various combinations of biomarker candidates (models) were trained using machine learning and tested for robustness in differentiating cases from controls on the full cohort and in clinically relevant sub-types including those with diabetes, those ≥65 years of age, and low producers of carbohydrate antigen 19-9 (CA 19-9). Results: At 98% specificity, the top performing model, which was comprised of tissue inhibitor of metalloproteinase 1 (TIMP1), intracellular adhesion molecule 1 (ICAM1), thrombospondin 1 (THBS1), cathepsin D (CTSD), and CA 19-9, achieved 85% sensitivity in the full cohort and sensitivities of 91% in diabetics, 90% in ≥65 years of age, and 60% in low CA 19-9 producers. This model demonstrated significantly higher sensitivity in detecting PDAC in the full cohort and all sub-populations compared to CA 19-9 alone (p < 0.001). Conclusions: Our findings demonstrate the feasibility of a blood-based assay for detecting early-stage PDAC in high-risk individuals and key sub-populations, representing an important step towards improving diagnostic success for early-stage disease.
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 | 0.002 | 0.004 |
| 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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 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".