• Anca Mirela Chiriac, Youna Wang, Rik Schrijvers, Philippe Jean Bousquet, Thibault Mura, Nicolas Molinari, and Pascal Demoly.
• Department of Pulmonology, Division of Allergy, Hôpital Arnaud de Villeneuve, University Hospital of Montpellier, Montpellier, France; UPMC Univ Paris 06, Sorbonne Universités, Paris, France. Electronic address: a-chiriac@chu-montpellier.fr.
• J Allergy Clin Immunol Pract. 2018 Jan 1; 6 (1): 139-148.e2.

BackgroundBeta-lactam antibiotics represent the main cause of allergic reactions to drugs, inducing both immediate and nonimmediate allergies. The diagnosis is well established, usually based on skin tests and drug provocation tests, but cumbersome.ObjectivesTo design predictive models for the diagnosis of beta-lactam allergy, based on the clinical history of patients with suspicions of allergic reactions to beta-lactams.MethodsThe study included a retrospective phase, in which records of patients explored for a suspicion of beta-lactam allergy (in the Allergy Unit of the University Hospital of Montpellier between September 1996 and September 2012) were used to construct predictive models based on a logistic regression and decision tree method; a prospective phase, in which we performed an external validation of the chosen models in patients with suspicion of beta-lactam allergy recruited from 3 allergy centers (Montpellier, Nîmes, Narbonne) between March and November 2013. Data related to clinical history and allergy evaluation results were retrieved and analyzed.ResultsThe retrospective and prospective phases included 1991 and 200 patients, respectively, with a different prevalence of confirmed beta-lactam allergy (23.6% vs 31%, P = .02). For the logistic regression method, performances of the models were similar in both samples: sensitivity was 51% (vs 60%), specificity 75% (vs 80%), positive predictive value 40% (vs 57%), and negative predictive value 83% (vs 82%). The decision tree method reached a sensitivity of 29.5% (vs 43.5%), specificity of 96.4% (vs 94.9%), positive predictive value of 71.6% (vs 79.4%), and negative predictive value of 81.6% (vs 81.3%).ConclusionsTwo different independent methods using clinical history predictors were unable to accurately predict beta-lactam allergy and replace a conventional allergy evaluation for suspected beta-lactam allergy.Copyright © 2017 American Academy of Allergy, Asthma & Immunology. Published by Elsevier Inc. All rights reserved.

22 keywords...

hide…