Penicillin Allergy De-labeling Results in Significant Changes in Outpatient Antibiotic Prescribing Patterns

Abstract

Unverified penicillin allergies are common but most patients with a penicillin allergy label can safely use penicillin antibiotics. Penicillin allergy labels are associated with poor clinical outcomes and overuse of second-line antibiotics. There is increasing focus on penicillin allergy "de-labeling" as a tool to improve antibiotic prescribing and antimicrobial stewardship. The effect of outpatient penicillin allergy de-labeling on long-term antibiotic use is uncertain. We performed a retrospective pre- and post- study of antibiotic dispensing patterns, from an electronic dispensing data repository, in patients undergoing penicillin allergy assessment at Auckland City Hospital, New Zealand. Over a mean follow-up of 4.55 years, 215/304 (70.7%) of de-labeled patients were dispensed a penicillin antibiotic. Rates of penicillin antibiotic dispensing were 0.24 (0.18-0.30) penicillin courses per year before de-labeling and 0.80 (0.67-0.93) following de-labeling with a reduction in total antibiotic use from 2.30 (2.06-2.54) to 1.79 (1.59-1.99) antibiotic courses per year. In de-labeled patients, the proportion of antibiotic courses that were penicillin antibiotics increased from 12.81 to 39.62%. Rates of macrolide, cephalosporin, trimethoprim/co-trimoxazole, fluoroquinolone, "other" non-penicillin antibiotic use, and broad-spectrum antibiotic use were all lower following de-labeling. Further, antibiotic costs were lower following de-labeling. In this study, penicillin allergy de-labeling was associated with significant changes in antibiotic dispensing patterns.

Keywords: allergy; antibiotic; antimicrobial stewardship; electronic dispensing data; hypersensitivity; penicillin; prescribing.

Figure 1

The use of penicillin antibiotics, time to first antibiotic and first penicillin antibiotic, and spectrum of dispensed antibiotic, pre- and post- penicillin allergy de-labeling. (A,B) Dispensing rates and proportions of total antibiotic courses are presented as means with 95% confidence intervals for de-labeled patients (n = 304) and allergic patients (n = 37). (C) Cumulative incidence of dispensing for any antibiotic and specifically for a penicillin antibiotic following penicillin allergy de-labeling. (D) Broad-spectrum antibiotic dispensing rates and broad-spectrum antibiotic courses as a proportion of each patient's total antibiotics dispensed are presented as a mean with 95% confidence intervals. Dispensing prior to assessment is displayed as black bars (A,B,D). Dispensing following assessment is displayed as gray bars (A,B,D). Antibiotic dispensing rates and specific antibiotic as a proportion of total antibiotics dispensed, before and after de-labeling, were compared using paired t-tests (Wilcoxon matched–pairs ranked sign test if data was non-parametric). P-values are represented as “ns” for p > 0.05, *p ≤ 0.05, **p ≤ 0.01, and ***p ≤ 0.001.

Figure 2

The use of non-penicillin antibiotic pre- and post- penicillin allergy de-labeling. Dispensing rates (A) and dispensing as a proportion of each patient's total antibiotic courses (B) are presented as means with 95% confidence intervals (n = 304 de-labeled patients). Dispensing prior to de-labeling is displayed as black bars. Dispensing following de-labeling is displayed as gray bars. Rates and proportions before and after de-labeling were compared using paired t-tests (Wilcoxon matched–pairs ranked sign test if data was non-parametric). P values are represented as “ns” for p > 0.05, *p ≤ 0.05, **p ≤ 0.01, and ***p ≤ 0.001.