This is an English translation of a news release in Japanese on October 26.
The Biological Science Research Laboratory, Skin Care Research Laboratory, and Analytical Science Research Laboratory of Kao Corporation (President: Michitaka Sawada) have been studying skin surface lipids-RNA monitoring technology*1 and developing methods to precisely predict constantly changing skin conditions using ribonucleic acid (RNA) in skin surface lipids (SSL-RNA). Their recent studies revealed that SSL-RNA varies during the menstrual cycle and age; such changes, including 86 attributes of skin and body conditions, can be predicted by artificial intelligence (AI). These attributes include skin moisture level, skin transparency scores through visual evaluation by a specialist, and glycosylation of stratum corneum proteins*2 (carboxymethyllysine level) (Table 1).
These findings were reported at the 72nd Annual Congress of the Japan Society of Obstetrics and Gynecology, held online from April 23 to 28, 2020, as well as at the 31st IFSCC (International Federation of Societies of Cosmetic Chemists) Congress Yokohama, held online from October 21 to 30, 2020.
Kao discovered the presence of human RNA in sebum in the form of SSL-RNA and succeeded in developing SSL-RNA monitoring technology, which is a unique technology that comprehensively analyzes this RNA. Using this technology, the company has found that SSL-RNA is associated with the symptoms of atopic dermatitis in adults and young children. RNA expression patterns vary from day to day depending on health conditions and the environment. Therefore, Kao is currently researching the association between skin conditions and SSL-RNA expression, with the goal of establishing an SSL-RNA monitoring technology that can easily and precisely evaluate the skin condition of individuals.
In the study detailed below, Kao investigated whether SSL-RNA provides information on periodic biological and age-related changes and what attributes of the skin and body can be predicted using a single SSL-RNA sample.
SSL-RNA samples from 38 women 20 to 45 years of age at various stages of their menstrual cycle (follicular, luteal, and menstrual phases) were analyzed. The study revealed that the expression patterns of SSL-RNA varied depending on the menstrual cycle. In addition, an increase in vascular endothelial growth factor-A (VEGF-A) in the follicular phase, which was reported in a previous study, was observed also in SSL-RNA in the present study (Figure 1).
Furthermore, SSL-RNA samples collected from 134 women 20 to 59 years of age were analyzed to investigate the correlation between SSL-RNA expression patterns and age. SSL-RNA expression patterns were found to change with age. In addition, the analysis showed that ATP5A1 (ATP*3 synthase F1 subunit alpha) expression levels, which are known to decrease with age, also decreased in SSL-RNA (Figure 2).
These findings suggest that SSL-RNA expression reflects changes in health conditions and the environment in real-time.
Kao has constructed a predictive model for 99 attributes of the skin and body conditions based on its study of 134 women 20 to 59 years of age. Researchers collected SSL-RNA samples from these women as well as numerical attributes of the skin measured using specialized instruments, visual evaluation scores of the skin, and quantitative data of skin components. They enabled AI to learn the patterns of correlation among SSL-RNA expression, age information, and measured data of approximately 90% of these women. Then, using this AI, they predicted the current skin conditions in approximately 10% of the women, based on the information for SSL-RNA expression and age.
The results revealed 86 attributes of the skin and body conditions including the skin moisture level, skin transparency scores visually evaluated by a specialist, and glycosylation of stratum corneum proteins (carboxymethyllysine level)―which is conventionally difficult to evaluate―that could be predicted with high precision based on SSL-RNA expression and age (Figure 3 and Table 1).
These findings suggest that this technology makes it possible to visualize various aspects of skin conditions using only a single sebum sample with considerably less time, effort, and burden on the skin.
The variation in the SSL-RNA expression during the menstrual cycle and age found in this study demonstrated that SSL-RNA expression reflects changes in the body in real-time. The study findings also indicated that current skin conditions could be predicted by AI technology from various aspects using only a single SSL-RNA sample.
Kao is currently conducting a collaborative research project with Preferred Networks Inc. (PFN) to develop a highly sophisticated predictive algorithm for skin conditions through the application of PFN's AI technology. Through the precise visualization of constantly changing skin conditions, Kao aims to develop individualized beauty counseling advice and skin care products.
Kao creates high-value-added products that enrich the lives of consumers around the world. Through its portfolio of over 20 leading brands such as Attack, Bioré, Goldwell, Jergens, John Frieda, Kanebo, Laurier, Merries and Molton Brown, Kao is part of the everyday lives of people in Asia, Oceania, North America and Europe. Combined with its chemical division, which contributes to a wide range of industries, Kao generates about 1,500 billion yen in annual sales. Kao employs about 33,000 people worldwide and has 130 years of history in innovation. Please visit the Kao Group website for updated information.