Reliability and validation of an electronic penicillin allergy risk-assessment tool in a pregnant population
Bibliographic record
Abstract
BACKGROUND: Penicillin allergy adversely impacts patient care, yet most cases do not have true allergies. Clinicians require efficient, reliable clinical tools to identify low risk patients who can be safely de-labeled. Our center implemented the FIRSTLINE electronic point-of-care decision support tool to help non-allergist practitioners risk stratify patients with penicillin allergy. We sought to explore the reliability and validity of this tool in relation to allergist assessment and actual patient outcomes. We additionally compared it with two other published stratification tools, JAMA and PENFAST, to assess ability to accurately identify low risk patients appropriate for direct oral challenge. METHODS: In this single-center, retrospective, observational study, 181 pregnant females with self-reported penicillin allergy between July 2019 to June 2021 at BC Women's Hospital, Vancouver, Canada were used to assess the reliability and validity of all three tools. Physician-guided history of penicillin use and symptoms were used for scoring. Results and recommendations were compared to actual patient outcomes after clinician decision for direct oral challenge or intradermal tests. We compared the performance of JAMA, PENFAST and FIRSTLINE. RESULTS: 181 patients were assessed. 176/181 (97.2%) patients were deemed not allergic. Each risk stratification tool labelled majority of patients as low risk with 88.4% of patients PENFAST 0-2, 60.2% of patients JAMA low risk, 86.7% of patients FIRSTLINE very low risk. CONCLUSION: We demonstrate that our point-of-care electronic algorithm is reliable in identifying low risk pregnant patients, as compared to an allergist assessment. To our knowledge, this is the first study to provide direct comparison between multiple decision support tools using the same population, minimizing participant bias. Providing clinical algorithms to risk stratify patients, can enable healthcare professionals to safely identify individuals who may be candidates for direct penicillin oral challenges versus needing referral to specialists. This increases the generalizability and efficiency of penicillin allergy de-labeling.
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 | 0.000 |
| 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 | 0.001 |
| 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".