S1028 Validating a Patient Risk Assessment Tool to Predict Post-ERCP Pancreatitis and Assist Prophylactic Treatment Planning
Bibliographic record
Abstract
Introduction: Post-ERCP pancreatitis (PEP) is a complication of ERCPs leading to significant patient morbidity and mortality. ASGE/ESGE guidelines recommend pancreatic duct stent placement, rectal indomethacin (IND), and/or fluid hydration with lactated Ringer’s (RL) or normal saline (NS) to prevent PEP. Recommendations regarding which treatment to use are often based on a patient’s PEP risk level and relevant comorbidities. To our knowledge, there is no objective calculator to aid in predicting PEP risk level for patients undergoing ERCP. Methods: Retrospective chart reviews of ERCP patients were completed within a single clinician’s practice at London Health Sciences Centre between 2016-2019. We developed a patient PEP risk screening tool based on ASGE/ESGE guidelines (Table 1) and analyzed its accuracy in predicting PEP in our practice. We then assessed the PEP rate for different PEP prophylactic treatments and determined whether these treatments were given according to the patient’s PEP risk level. Results: Five hundred sixty-one ERCP patients were assessed using the PEP risk screening tool with 6.6% (37/561) developing post-ERCP pancreatitis. A cut-off score totalling 1 for our tool was chosen to identify high PEP risk patients due to its high sensitivity and moderate specificity. Using the screening tool, 79.5% (446/561) were identified as high PEP risk. Patients receiving ERCP identified as high PEP risk by our tool were roughly 4 times more likely to go on to develop PEP (OR 4.81, [CI] 1.14-20.31). PEP rates were highest in patients who received pancreatic stenting (16.7%) or IND (8.8%) +/- RL (11.2%). Using the risk screening tool, all patients receiving pancreatic stenting were deemed high PEP risk and high PEP risk patients were roughly twice as likely to receive IND (OR 2.09, [CI] 1.36-3.21) compared to low PEP risk patients. Conclusion: Overall, our PEP risk screening tool was very sensitive at identifying patients who were likely to develop PEP. Patients with a higher risk level received more extensive prophylactic treatments as expected. The observed elevated post-ERCP pancreatitis rates in patients receiving these treatments might be partially explained by the higher average PEP risk level in these patients. We hope, high-risk patient identification can be improved prior to ERCP, to provide more objective risk level stratification to better assess PEP prophylactic treatment efficacy moving forward.Table 1.: Post-ERCP Pancreatitis (PEP) Risk Screening Tool Based on ASGE and ESGE Guidelines.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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".