Development of Betalactam-Predictor: A clinical decision tool for delabeling low-risk Betalactam Allergy patients. Initial validation in penicillin allergy

Abstract

Background: A label of betalactam (BL) allergy is estimated in around 10% of the population in their medical records. Second-line choices carry significant negative consequences, including reduced efficacy, effectiveness, and safety. This study aimed todevelop a new highly specific score constructed by selecting variables assisted by artificial intelligence to identify low-risk BL-allergic patients.Methods: In this study, derivation and validation of the BL-predictor score were performed on a retrospective cohort of 2207patients who underwent penicillin allergy testing at Málaga University Hospital (Spain). The development of the BL-predictorencompassed expert drafting and a two-step variable selection process consisting of univariate analysis and variable filtering,followed by stepwise logistic regression with resampling. To assess the efficiency, a multicentric retrospective external valida-tion was performed in 4261 patients from six populations: Salamanca and Madrid, Spain; Nashville, United States of America;Verona, Italy; Paris, France; and Copenhagen, Denmark.Results: The definitive questionnaire consisted of eight items and risk points were computed from the logistic regression modelas follows: +1 for reactions after first dose or in less than 1 h (ITEM-1), +2 for anaphylaxis (ITEM-2); +1 for previous reaction withthe culprit (ITEM-3); −1 for resolution in > 24 h (ITEM- 4); +2 for spontaneous resolution (ITEM-5); −2 for unknown symptoms