Search

We developed an artificial intelligence algorithm (AIA) for smartphones to determine the severity of facial acne using the GEA scale and to identify different types of acne lesion (comedonal, inflammatory) and postinflammatory hyperpigmentation (PIHP) or residual hyperpigmentation. Overall, 5972 images (face, right and left profiles) obtained with smartphones (IOS and/or Android) from 1072 acne patients were collected. Three trained dermatologists assessed the acne severity for each patient. One acne severity grade per patient (grade given by the majority of the three dermatologists from the two sets of three images) was used to train the algorithm. Acne lesion identification was performed from a subgroup of 348 images using a tagging tool; tagged images served to train the algorithm. The algorithm evolved and was adjusted for sensibility, specificity and correlation using new images. The correlation between the GEA grade and the quantification and qualification of acne lesions both by the AIA and the experts for each image were evaluated for all AIA versions. At final version 6, the GEA grading provided by AIA reached 68% and was similar to that provided by the dermatologists. Between version 4 and version 6, AIA improved precision results multiplied by 1.5 for inflammatory lesions, 2.5 for non‐inflammatory lesions and by 2 for PIHP; recall was improved by 2.6, 1.6 and 2.7. The weighted average of precision and recall or F1 score was 84% for inflammatory lesions, 61% for non‐inflammatory lesions and 72% for PIHP. more...

Sunscreens have been designed to protect against sunburn and their efficacy has, therefore, been labeled by the so-called sun protection factor (SPF). Although this value is well determined using a standardized protocol and it affords a good evaluation of the protection against erythema it may be inadequate to provide a relevant measurement of efficacy against other biologic damages. This is particularly true when action spectra and threshold dose are different from those of erythema. In the case of ultraviolet (UV)-induced immune suppression, the action spectrum is not known, so it cannot be asserted that SPF may accurately predict the level of protection against this endpoint. We addressed this issue by measuring in human volunteers the ability of two broad-spectrum SPF 15 sunscreens with different ultraviolet A (UVA) protection levels, to prevent the alteration of the efferent phase of the local delayed-type hypersensitivity (DTH) response to recall antigens (Multitest Pasteur/Merieux, Lyon, France) after acute solar-simulated UV exposure. We first determined the ultraviolet radiation (UVR) dose needed to induce a significant DTH inhibition in several groups of 15 volunteers. Two minimal erythemal doses (2 MED) were found to be the minimal immunosuppressive dose (MISD). As a result, the immune DTH response is reduced in average by 36%. The lower doses tested (0.5 and 1 MED) were ineffective. Sunscreen-treated groups were exposed to either 1 or 2 MED × SPF doses. As expected, no alteration in DTH response was observed in the groups exposed to 1 MED × SPF whatever the sunscreen applied. In contrast, after exposure to 2 MED × SPF, the DTH response remained unaltered in the group pretreated with the sunscreen product with the higher protection in the UVA range but was significantly suppressed by 55.7% in the group pretreated with sunscreen with a much lower protection in the UVA range. These data suggest that SPF may not be sufficient to predict the ability of sunscreens to protect from UV-induced immune suppression. Determining the level of UVA protection is particularly needed, as UVA seems to have a relatively low contribution to erythema but is highly involved in immunosuppression. more...

It is well established that ultraviolet radiation has immunomodulatory effects which may be involved in skin cancer. Recent studies have shown that UVA radiation (320-400 nm) as well as UVB (290-320 nm) is immunosuppressive. This means that sunscreens which mainly absorb UVB (protection against erythema) may be less effective in preventing UVR-induced immunosuppression than broad-spectrum products. We have studied the effects of UVA exposure on the human delayed-type hypersensitivity response (DTH) and compared the efficacy of sunscreens having different levels of UVA protection under both solar-simulated radiation (SSR) chronic exposures or acute exposure and outdoor real-life solar exposure conditions. DTH was assessed using recall antigens. Our studies clearly demonstrate the role of UVA in the induction of photoimmunosuppression together with the need for sunscreen products providing efficient photoprotection throughout the entire UV spectrum. These data suggest that sun protection factor may not be sufficient to predict the ability of sunscreens for protection from UV-induced immune suppression. Determining the level of UVA protection is particularly necessary, because UVA seems to have a relatively low contribution to erythema but is highly involved in immunosuppression. more...