A114 DEVELOPING AND VALIDATING A PATIENT RISK ASSESSMENT TOOL TO PREDICT POST-ERCP PANCREATITIS
Bibliographic record
Abstract
Abstract Background Post-ERCP pancreatitis (PEP), the most common complication of ERCP, can lead to significant patient morbidity and even mortality. Both American (ASGE) and European (ESGE) guidelines emphasize the importance of assessing PEP risk among patients about to undergo ERCP so appropriate preventative measures can be initiated. Though multiple PEP risk factors have been identified, an ideal risk assessment tool has not yet been developed that accurately predicts PEP risk among ERCP patients. An ideal PEP risk factor screening tool would be one that most sensitively identifies patients likely to benefit from PEP preventative measures. We have developed a patient PEP risk screening tool based on both ASGE and ESGE guidelines (Table 1) and analyzed its accuracy predicting PEP rates in our clinical practice. Aims We investigated whether the ERCP patient and procedural risk factors listed in the ASGE and ESGE guidelines were linked to PEP rates using a novel PEP risk screening tool in patients undergoing ERCP. Methods Retrospective chart reviews of patients undergoing ERCP were performed within a single clinician’s practice at the London Health Science Centre, Victoria Hospital, between January 2016 and October 2019 to: 1) assess the proportion of patients identified as high PEP risk using our novel PEP risk screening tool; 2) determine whether a high PEP risk score using this tool was linked to higher PEP rates following ERCP; and 3) identify the absolute score threshold that best delineates patients at higher risk. A chi-square test of independence was performed to examine the relationship between high PEP risk identified via screening and the actual PEP rate following ERCP. Results Five hundred sixty-one patients who underwent ERCP were assessed using the new PEP risk screening tool. Among those patients, 6.6% (37/561) developed post-ERCP pancreatitis. Using the screening tool, 79.5% (446/561) were identified as high risk, using a cut-off score of 1; the score with the highest sensitivity (95%) and specificity (22%) combination. Identifying high PEP risk patients at this cut-off was significantly linked to increased PEP rates in patients who underwent ERCP (X2 = 5.5; df = 1, p < .05). Conclusions Using a cut-off score of 1, the PEP risk screening tool was very sensitive, but relatively non-specific at identifying patients who went on to develop post-ERCP pancreatitis. We hope that, based on these findings, high-risk patient identification can be improved, so more aggressive and appropriately-targeted prophylactic measures against PEP can be provided. Funding Agencies None
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 | 0.020 | 0.055 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".