ABSTRACT
INTRODUCTION: Up to 15% of adult patients in the clinical setting report to be allergic to penicillin. However, in most cases, penicillin allergy is not confirmed. Due to the negative aspects associated with erroneous penicillin allergy, the implementation of active delabelling processes for penicillin allergy is an important part of antibiotic stewardship programmes. Depending on the clinical setting, different factors need to be considered during implementation. This review examines the effectiveness of different delabelling interventions and summarises components and structures that facilitate, support or constrain structured penicillin allergy delabelling. METHODS AND ANALYSIS: This review will adhere to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses. The databases MEDLINE (via PubMed), EMBASE and Cochrane Library were searched for studies reporting on any intervention to identify, assess or rule out uncertain penicillin allergy. To improve completeness, two further databases are also searched for grey literature. Study design, intervention type, professional groups involved, effectiveness, limitations, barriers, facilitating factors, clinical setting and associated regulatory factors will be extracted and analysed. In addition, exclusion criteria for participation in the delabelling intervention and criteria for not delabelling penicillin allergy will be summarised. In case of failed protocols, these are highlighted and quantitatively analysed if possible. Two independent reviewers will perform the screening process and data extraction. Discordant decisions will be resolved through review by a third reviewer. Bias assessment of the individual studies will be performed using the Newcastle Ottawa Scale. ETHICS AND DISSEMINATION: Because individual patient-related data are not analysed, an ethical approval is not required. The review will be published in a peer-reviewed scientific journal.
Subject(s)
Drug Hypersensitivity , Penicillins , Humans , Penicillins/adverse effects , Research Design , Systematic Reviews as TopicABSTRACT
OBJECTIVES: To investigate the performance and risk associated with the usage of Chat Generative Pre-trained Transformer (ChatGPT) to answer drug-related questions. METHODS: A sample of 50 drug-related questions were consecutively collected and entered in the artificial intelligence software application ChatGPT. Answers were documented and rated in a standardised consensus process by six senior hospital pharmacists in the domains content (correct, incomplete, false), patient management (possible, insufficient, not possible) and risk (no risk, low risk, high risk). As reference, answers were researched in adherence to the German guideline of drug information and stratified in four categories according to the sources used. In addition, the reproducibility of ChatGPT's answers was analysed by entering three questions at different timepoints repeatedly (day 1, day 2, week 2, week 3). RESULTS: Overall, only 13 of 50 answers provided correct content and had enough information to initiate management with no risk of patient harm. The majority of answers were either false (38%, n=19) or had partly correct content (36%, n=18) and no references were provided. A high risk of patient harm was likely in 26% (n=13) of the cases and risk was judged low for 28% (n=14) of the cases. In all high-risk cases, actions could have been initiated based on the provided information. The answers of ChatGPT varied over time when entered repeatedly and only three out of 12 answers were identical, showing no reproducibility to low reproducibility. CONCLUSION: In a real-world sample of 50 drug-related questions, ChatGPT answered the majority of questions wrong or partly wrong. The use of artificial intelligence applications in drug information is not possible as long as barriers like wrong content, missing references and reproducibility remain.