Background: It is unknown whether ChatGPT provides quality responses to infectious diseases (ID) pharmacotherapy questions. This study surveyed ID pharmacist subject matter experts (SMEs) to assess the quality of ChatGPT version 3.5 (GPT-3.5) responses. Methods: The primary outcome was the percentage of GPT-3.5 responses considered useful by SME rating. Secondary outcomes were SMEs' ratings of correctness, completeness, and safety. Rating definitions were based on literature review. One hundred ID pharmacotherapy questions were entered into GPT-3.5 without custom instructions or additional prompts, and responses were recorded. A 0–10 rating scale for correctness, completeness, and safety was developed and validated for interrater reliability. Continuous and categorical variables were assessed for interrater reliability via average measures intraclass correlation coefficient and Fleiss multirater kappa, respectively. SMEs' responses were compared by the Kruskal-Wallis test and chi-square test for continuous and categorical variables. Results: SMEs considered 41.8% of responses useful. Median (IQR) ratings for correctness, completeness, and safety were 7 (4–9), 5 (3–8), and 8 (4–10), respectively. The Fleiss multirater kappa for usefulness was 0.379 (95% CI, .317–.441) indicating fair agreement, and intraclass correlation coefficients were 0.820 (95% CI, .758–.870), 0.745 (95% CI, .656–.816), and 0.833 (95% CI, .775–.880) for correctness, completeness, and safety, indicating at least substantial agreement. No significant difference was observed among SME responses for percentage of responses considered useful. Conclusions: Fewer than 50% of GPT-3.5 responses were considered useful by SMEs. Responses were mostly considered correct and safe but were often incomplete, suggesting that GPT-3.5 responses may not replace an ID pharmacist's responses.

Patients with reported penicillin allergies have been proven to experience negative health consequences, such as increased cost, suboptimal antimicrobial therapy, and adverse reactions. Though skin testing has been proposed as a method to clarify penicillin allergies, many institutions may lack the resources to perform skin testing on a wide scale. This literature review describes the current literature surrounding the use of penicillin allergy interviews when skin testing is not an option. Specifically, the review highlights the steps in carrying out a successful antibiotic allergy patient interview, summarizes the clinical evidence surrounding antibiotic allergy clarifications, and addresses key advantages and disadvantages of clarifying antibiotic allergies without the availability of skin testing.

Background: Patients with reported β-lactam allergies often receive broad-spectrum antimicrobials and have been shown to experience a variety of negative health consequences, such as increased mortality, costs, readmission, and adverse reactions. Current literature focuses on β-lactam allergy skin testing but lacks evidence on β-lactam allergy interviews (BLAI) when skin testing is unavailable. Objective: This study aimed to test the impact of a pharmacy-led BLAI on duration of fluoroquinolones at a community hospital. Methods: A quasi-experimental design with a prospective cohort design and historical control group was used to assess patients with reported penicillin (PCN) allergies in a community hospital. The primary outcome was duration of fluoroquinolones before and after implementation of BLAI. Secondary outcomes included length of stay (LOS), percentage of patients switched to a β-lactam antibiotic, percentage of antimicrobial stewardship recommendations made/accepted, and discrepancies between allergy in medical record and interview-reported allergy. Nonparametric continuous data and medians were evaluated by Mann-Whitney U. Results: A total of 80 patients were included in the study (43 in the control group and 37 in the prospective group). Fluoroquinolone duration was reduced after the implementation of BLAI (3.7 vs 2.7 days, P = 0.027). In all, 49% of patients in the prospective group were switched to a β-lactam antibiotic after BLAI, with no allergic reactions, adverse effects, or impact on LOS. Conclusion and Relevance: BLAI resulted in a significant reduction in fluoroquinolone duration in patients with PCN allergies and may represent a safe and effective option for institutions lacking skin-testing capabilities.