Highly accurate prediction of food challenge outcome using routinely available clinical data

Background: Serum specific IgE or skin prick tests are less useful at levels below accepted decision points. Objectives: We sought to develop and validate a model to predict food challenge outcome by using routinely collected data in a diverse sample of children considered suitable for food challenge. Methods: The proto-algorithm was generated by using a limited data set from 1 service (phase 1). We retrospectively applied, evaluated, and modified the initial model by using an extended data set in another center (phase 2). Finally, we prospectively validated the model in a blind study in a further group of children undergoing food challenge for peanut, milk, or egg in the second center (phase 3). Allergen-specific models were developed for peanut, egg, and milk. Results: Phase 1 (N = 429) identified 5 clinical factors associated with diagnosis of food allergy by food challenge. In phase 2 (N = 289), we examined the predictive ability of 6 clinical factors: skin prick test, serum specific IgE, total IgE minus serum specific IgE, symptoms, sex, and age. In phase 3 (N = 70), 97% of cases were accurately predicted as positive and 94% as negative. Our model showed an advantage in clinical prediction compared with serum specific IgE only, skin prick test only, and serum specific IgE and skin prick test (92% accuracy vs 57%, and 81%, respectively). Conclusion: Our findings have implications for the improved delivery of food allergy-related health care, enhanced food allergy-related quality of life, and economized use of health service resources by decreasing the number of food challenges performed.