Eye irritation of low-irritant cosmetic formulations: correlation of in vitro results with clinical data and product composition

Alternative methods to the Draize eye irritation test, such as the hen's egg test-chorioallantoic membrane (HET-CAM) or the bovine corneal opacity and permeability (BCOP) tests, are currently used to evaluate the irritant potential of cosmetic or consumer products. Although, for strong irritants, the results of these tests correlate well with those of the Draize test, they appear to be less suited to identify mild irritants. In order to improve the sensitivity of alternative eye irritation tests, we developed a novel method that uses a human corneal epithelial cell line (CEPl), and the endpoints of cytotoxicity and IL-8 release. Twelve make-up removers were assessed by the HET-CANl, BCOP and CEPl tests, as well as in a clinical in-use test under ophthalmological control after their application to the external eye lid. In addition, we investigated the impact of osmolality and raw material composition on in vitro and clinical results and compared the in vitro results with those of clinical studies. Overall, although HET-CAM results were unrelated to eye discomfort and adverse clinical signs, they correlated mainly with the presence and concentration of surfactants in the test articles. BCOP scores were unrelated to clinical signs, but related mainly to glycol and sodium lactate content and concentration in the test articles. Cytotoxicity in CEP1 mainly correlated with presence and concentrations of surfactants, and IL-8 release to clinical signs and/or glycol and sodium lactate concentrations. Overall, IL8 release appeared to be the most sensitive and reliable endpoint to predict human eye tolerance to mildly irritant products. Although our results suggest that the IL-8 assay appears to be a promising screen for borderline-irritant formulations, further experiments are required to confirm and validate these preliminary results. (C) 2004 Elsevier Ltd. All rights reserved.