Prediction of treatment effect perception in cosmetics using machine learning.

Perception of treatment effect (TE) in cosmetics is multifaceted and influenced by multiple parameters that need to be considered simultaneously when evaluating TE. Here we provide a global approach to predicting TE perception using Random Forest (RF) classifier. Data from three randomized double-blind clinical studies with a total of 50 subjects were used.

Mapping, in vivo, the uniformity of two skin properties alongside the human face by a 3D virtual approach.

Objective: To determine the homogeneity in the distribution of two cutaneous functions (hydration and elasticity) along the entire human face.

Material And Methods: The half faces (right or left, randomly chosen) of two groups of Caucasian women were measured on 24 different small sites (elasticity) and 41 others (hydration), by instruments of small-sized probes (Cutometer and Corneometer , respectively). Hydration of the face was recorded at different times (up to 24 h), post application of a highly hydrating product.

Seasonally-induced alterations of some facial signs in Caucasian women and their changes induced by a daily application of a photo-protective product.

Objectives: These were two-fold: (i) to assess the possible changes in some facial signs induced in a 6-month period by the periodical shift from winter to summer in Caucasian women and (ii) to appraise the preventive effects of a strong photo-protective product.

Methods: The facial signs of two cohorts of French women (N= 40 and 42), of comparable ages were graded between winter to summer. One group was left unprotected whereas the other daily applied a strong photo-protective product for 6 months.