Predicting the stages of PDAC using non-invasive method
Bibliographic record
Abstract
Pancreatic Ductal Adenocarcinoma (PDAC) is a highly lethal malignancy in which early and accurate staging is paramount for effective therapeutic decision-making and prognostication. Traditionally, the prediction of PDAC staging has depended heavily on invasive methods such as CT scans and tissue biopsies. These methods can be costly, time-consuming, and distressing for patients [1]. Recently, focus has shifted towards the development of non-invasive detection methods utilizing Machine Learning. Research conducted by the Barts Cancer Institute[2], which investigated the early detection of PDAC using bio-markers such as CA19-9, LYVE1, REG1B, REG1A, TFF1, and creatinine, has shown promising results. Our study is a subsequent investigation that relies on the same open-access data-set comprising 590 participants. It aims to first ascertain the previous work of researchers related to early detection of PDAC. Second, to investigate the possibility of utilizing the same bio-markers to predict the stage of PDAC, this differs our work from previous work. We have tried out several machine learning algorithms. Our results for the first problem, early prediction of PDAC are very promising - we achieved an accuracy of 87%, 84% and 78% for precision and recall respectively utilizing XGBoost. For the second problem, predicting the stage of PDAC, MLP neural networks yielded an accuracy of 70% with an AUC of 79%. These results are promising and better than the base models, which opens a new area for future works. Based on our work, we propose the establishment of a certified pancreatic bio-marker platform.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".