Validation of AI-based software for objectification of conjunctival provocation test results in routine examinations and clinical studies

Abstract

Abstracts1.BackgroundProvocation tests are widely used in allergology to objectively reveal patients’ sensitivity to specific allergens. The objective quantification of an allergic reaction is a crucial characteristic of these tests. Due to the absence of objective quantitative measurements the conjunctival provocation test (CPT) is a less frequently used method despite its sensitivity and simplicity. We developed a new method AllergoEye based on AI for quantitative evaluation of conjunctival allergic reactions and validated it in a clinical study.2.MethodsAllergoEye was implemented as a two component system. The first component is based on an Android smartphone camera for screening and imaging the patient’s eye and the second one is PC based for image analysis and quantification. For the validation of AllergoEye an open-label, prospective, monocentric study was carried out on 41 patients. Standardized CPT was performed with sequential titration of grass allergens in 4 dilutions with the reaction evaluated by subjective/qualitative symptom scores and by quantitative AllergoEye scores.3.ResultsAllergoEye demonstrated high sensitivity (98%) and specificity (90%) as compared with human-estimated allergic reaction. Tuning cut-off thresholds allowed to increase the specificity of AllergoEye to 97%, where the correlation between detected sensitivity to allergen and sIgE CAP-class becomes obvious. Strikingly, such correlation was not found with sensitivity to allergen detected by subjective and qualitative symptom scores.4.ConclusionThe clinical validation demonstrated that AllergoEye is a sensitive and efficient instrument for objective measurement of allergic reactions in CPT for clinical studies as well as for routine therapy control.