Developing and disseminating an electronic penicillin allergy de-labelling tool using the model for improvement framework
Bibliographic record
Abstract
Abstract Background Many clinicians feel uncomfortable with de-labelling penicillin allergies despite ample safety data. Point of care tools effectively support providers with de-labelling. This study’s objective was to increase the number of providers intending to pursue a penicillin oral challenge by 15% by February 2023. Methods A validated de-labelling algorithm was translated into an electronic point of care tool and disseminated to eight healthcare institutions. Applying the Model for Improvement Framework, three PDSA cycles were conducted, where collected data and completed surveys were analysed to implement changes. Number of providers intending to pursue an oral challenge, tool usage as well as number of clinicians who felt satisfied with the tool and felt confident in its ability to risk-stratify patients was collected. Results 50.4% of providers intended to give an oral challenge of penicillin with version 1, which improved to 65.5% with version 2, representing a 15.1% increase. With version 1 of the tool, there was an average of 61.3 counts of tool usage per month. 73.1% of providers felt satisfied with the tool and 76.9% felt confident in its ability to risk-stratify patients. With version 2 of the tool, after implementing changes through three PDSA cycles, monthly usage counts increased to an average of 98.6. Furthermore, 100.0% of providers felt satisfied with the tool and 98.1% felt confident with the tool’s ability to risk-stratify patients. Conclusion Our quality improvement approach demonstrated improvement in the percentage of providers that intended to pursue an oral challenge and felt satisfied and confident in the risk-stratification capabilities of penicillin allergy de-labelling tool. Electronic tools should be further incorporated into institutional penicillin de-labelling protocols.
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 | 0.101 | 0.096 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".