[A predictive model for pancreatic cancer using serum protein footprint map].
Bibliographic record
Abstract
OBJECTIVE: To establish a predictive model for pancreatic cancer by using serum protein footprint map. METHODS: Surface-enhanced laser desorption/ionization (SELDI) ProteinChip technology was applied to screen abnormally expressed proteins in 92 pancreatic cancer patients, 15 patients with benign pancreatic diseases, 18 patients with other diseases of digestive tract, and 96 healthy volunteers. 48 patients with pancreatic diseases and 48 healthy volunteers selected randomly constituted the training group, and 43 pancreatic cancer patients,48 healthy volunteers, 15 patients with pancreatic diseases, and 18 patients with malignant diseases of digestive tract selected randomly constituted the testing group. A predictive model was founded by bioinformation methods using the data of the training group. The data of the testing group was imported to this model to verify by blind method. The sensitivity and specificity of both diagnosis models and CA19-9, were analyzed to evaluate the clinical application value of the model in diagnosis of pancreatic cancer. RESULTS: Using IMAC3-Cu chip, 12 peaks of differentially expressed proteins were discovered. Six of those had significant value in diagnosis of pancreatic cancer. With the principle of decision tree, a model was founded to diagnose pancreatic cancer, which was composed of 4 decisive nodes and 5 terminal nodes. With the blind test, the sensitivity of the model was 90.7% (39/43) and the specificity was 89.6% (43/ 48) in differentiating cancer from normal status. The modal was better than CA19-9. Serial tests could raise the specificity to 97.9% (47/48), while parallel test could raise the sensitivity to 95.3% (41/43). CONCLUSION: The predictive model established by serum protein footprint map is a quick, easy, convenient and accurate method to diagnosis pancreatic cancer and screen new tumor markers.
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 | 0.001 | 0.003 |
| 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 | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".