Risk factors and early prediction of pancreatic cancer among patients with diabetes mellitus: a systematic review and meta-analysis
Bibliographic record
Abstract
Aim: Diabetes mellitus (DM) increases the risk of pancreatic cancer (PC). This study evaluates risk factors for PC in DM patients and the predictive accuracy of machine learning (ML) models to provide research-backed data for the development and update of intelligent prediction tools. Methods: PubMed, Cochrane, Embase, and Web of Science were systematically retrieved, up to December 1, 2024. The quality of the original studies was assessed through the Newcastle-Ottawa Scale (NOS). A meta-analysis was conducted on the c-index that reflects the comprehensive accuracy of the prediction models. Results: 18 studies were included. The rough annual incidence of PC among DM was estimated at 0.4% (95% CI: 0.1% - 0.9%), and the incidence rates of PC for new-onset DM and pre-existing DM were 0.3% (95% CI: 0.1% - 0.5%) and 0.5% (95% CI: 0% - 2.7%), respectively. The possible risk factors included age at DM diagnosis, weight changes, blood sugar, ALP, GI symptoms, pancreatic disease history, and the usage of hypoglycemic drugs. ML models based on risk factors had ROC-AUCs of 0.79 (95% CI: 0.75-0.84) in the training set and 0.79 (95% CI: 0.71-0.87) in the validation set. Conclusions: Risk factors for PC in DM are diverse. Current ML models appear to exhibit favorable predictive accuracy but are built on severely imbalanced data. Future studies with larger, broader populations are needed to address this limitation. Systematic review registration: https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42025631534.
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 | 0.009 | 0.023 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.014 | 0.031 |
| Bibliometrics | 0.006 | 0.008 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| 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".