The sensitivity of decision support tools for identifying patients with pancreatic cancer
Bibliographic record
Abstract
Background Pancreatic cancer causes non-specific symptoms, potentially leading to delays in diagnosis. Decision support tools may help primary care practitioners to triage patients for pancreatic imaging. Aim To investigate the sensitivity of three different tools for identifying patients who may have pancreatic cancer. Design & setting An observational study in Australia. Method We investigated the performance of the Risk Assessment Tool (RAT) for pancreatic cancer, the QCancer ® tool, and a tool developed through a consensus process led by QIMR Berghofer (the QPaC Tool). We applied these tools to people with pancreatic cancer who were interviewed about their symptoms on first presentation to a clinician. We designated patients as ‘flagged’ by each tool if they met specific criteria, and calculated the percentage flagged (that is, the sensitivity). Participants with jaundice were excluded from analyses of QCancer ® . Results We included 190 participants in analyses of the RAT and QPaC Tool (142 in analyses of QCancer ® ). The sensitivity of the QPaC Tool and the RAT were 54% and 27%, respectively. QCancer ® had a sensitivity of 14%, at a probability threshold of 1%; in the same 142 participants, QPaC and the RAT flagged 44% and 7%, respectively. Conclusion The QPaC Tool was the most sensitive, largely owing to its inclusion of severe epigastric pain and emphasis on diabetes, but it has unknown specificity. More research is needed to determine whether any tool could reduce delays in diagnosis; in the interim, the QPaC Tool may support clinicians to consider pancreatic cancer in their differential diagnoses.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".