Impact of real-world confounders on the accuracy of an AI model to support read out of skin prick automated test results
(2026) Rhinology Journal — Vol. 64, n° 5 (2026)
Files
Impact of real-world confounders on the accuracy of an AI model to support read out of skin prick automated test results.pdf
Open Access - Adobe PDF
- 8.21 MB
Details
- Authors
- Abstract
- Skin prick testing (SPT) is the gold standard for diagnosing allergic sensitization in individuals with a suspected airborne allergy (1). Skin tests are used as first option in 90% of individuals suffering from respiratory allergies and almost two-third of all types of allergies (2). However, its accuracy highly depends on the operator, causing variability during pricking and readout. S.P.A.T. or skin prick automated test standardises the SPT procedure and has been clinically validated (3). The S.P.A.T. device serves 12 simultaneous pricks delivering a fixed amount of test solution with controlled prick force to the patient's forearm. This automation has proven to lower intra-subject variability and bring more consistent test results compared to manual SPT (4,5).
- Affiliations
Citations
Roux, K., Seys, S., Hox, V., Chaker, A., Helling, P., De Greve, G., Lemmens, W., Poirrier, A., Daems, R., Loeckx, D., Gorris, S., & Van Gerven, L. (2026). Impact of real-world confounders on the accuracy of an AI model to support read out of skin prick automated test results. Rhinology Journal, 64(5). https://doi.org/10.4193/rhin25.634 (Original work published 2026)