ELEunyoung Lee

Eunyoung Lee

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Eunyoung Lee has a total of 88 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

    • 19 November 2026
    • Published by MDPI AG in Toxics
      • Vol. 14  (11) , 1021
      • https://doi.org/10.3390/toxics14111021
    Open Access

    Evaluating the Integration of Questionnaire and Measurement Data to Estimate Daily Cosmetic Product Use Distributions

    by Kyoung Ae Kong, Eunyoung Lee, Mi Soo Choi, Byung Cheol Park, Kyu-Bong Kim, Myung Hwa Kim

    Cosmetic exposure assessment requires daily product use, but repeated measurement is difficult. We evaluated two approaches combining categorical questionnaire frequencies with measured amounts. We analyzed questionnaires, 14-day diaries, and product weights from 561 Korean adults for four products. Measurement participants were donors matched by sex, age group, and questionnaire frequency. Method C multiplied questionnaire frequency by donors’ per-application amounts; D used frequency only for matching and assigned donors’ daily amounts. Monte Carlo estimates were compared with measurement-based (A) and questionnaire-based (B) values. C and D were applied to a 2000-person survey. Questionnaires yielded higher per-application medians than measurement but lower values in high-amount groups. C was closer to A than B for most statistics, but P90 exceeded A’s by 0.34 g/day (sunscreen) and 0.67 g/day (shampoo). D resembled A, possibly reflecting same-sample reassignment. In the survey, C and D means and P95s were below B’s; P90 exceeded B’s for body cleanser (C, D) and shampoo (C). Combining questionnaire frequency with measured amounts brought most statistics closer to measurement-based values than questionnaires, though some upper percentiles differed. Assigning measured daily amounts preserves donors’ frequency–amount combinations without directly using diary counts. Both may support distribution updates if measurements reflect current practices.

  • Open Access

    Artificial Intelligence Based Skin Analysis Models for Predicting Visual Grades and Device Measured Physiological Values From Facial Images

    by Eunyoung Lee, Jeongho Lee, Nahee Kim, Junchae Na, Byungcheol Park, Sang‐Il Choi

    Objective: This study aimed to develop and validate an artificial intelligence (AI)–based skin assessment framework capable of predicting both dermatologist‐assigned visual grades and device‐derived physiological measurements from facial images. In addition, we evaluated the impact of image‐acquisition modality (DSLR, tablet, or smartphone) on model performance. Methods: A total of 1,099 Korean participants aged 14–69 years were enrolled. High‐resolution facial images were obtained from seven standardized angles using a DSLR camera, and a subset of additional images was collected using a tablet and participant‐owned smartphones. Five board‐certified dermatologists graded eight facial signs, and physiological parameters were measured using non‐invasive skin assessment devices. CoAtNet‐4 served as the backbone architecture for both classification (visual grading) and regression (physiological prediction). Model performance was assessed using mean absolute error and correlation analyses. Results: When evaluated using DSLR images, the model achieved a mean exact‐grade accuracy of 51.4%, with an average of 93.3% of predictions falling within ± 1 grade across facial signs. High correlations were observed for wrinkles, pigmentation, pores, and sagging, whereas lip dryness demonstrated comparatively lower correlations. For physiological metrics, strong correlations were observed for pigmentation spot count, cheek pore visibility, and wrinkle severity, whereas hydration and elasticity showed moderate correlations. Performance on mobile‐device images remained high and showed strong agreement with DSLR‐based predictions, although a noticeable decline in pigmentation‐related accuracy was observed. Conclusion: The proposed AI framework reliably approximates dermatologist visual grading and multiple device‐based physiological measurements, offering a comprehensive, image‐driven approach to skin aging assessment. However, model performance varies across facial attributes and remains sensitive to image quality, emphasizing the need for domain adaptation and image enhancement strategies to ensure robust application in consumer environments.

  • Biophysical properties of redness‐prone skin in Korean women

    by Eunyoung Lee, Changhui Cho, Jaehyoun Ha

    Background: Facial skin redness can have a negative impact on the quality of life. In this study, we investigated the skin biophysical parameters associated with facial skin redness as a function of aging.Methods: Our aims were as follows: (1) to understand the impact of non‐pathological facial skin redness on the quality of life of Korean women through a survey; and (2) compare skin biophysical properties between women with and without facial skin redness.Results: Women aged between 20 and 39 years perceived their own facial skin redness at a higher rate than those aged ≥40 years. In addition, in redness‐prone women, the intensity of skin redness and skin surface perfusion were higher, while skin hydration was lower regardless of age. In redness‐prone women aged ≥40 years, the values for transepidermal water loss, elasticity, and skin thickness were lower, and the mean pore depth was greater. Facial redness intensity was higher, and the distribution was wider in redness‐prone younger women, while only redness intensity increased in the older age group.Conclusions: Overall, redness‐prone women aged ≥40 years had weaker skin properties. Our study indicated the age‐related biophysical characteristics of non‐pathological facial skin redness. We believe that our findings will help improve its negative effects.


  • Evaluation of facial skin age based on biophysical properties in vivo

    by Changhui Cho, Eunyoung Lee, Gyeonghun Park, Eunbyul Cho, Nahee Kim, Juhee Shin, Sanga Woo, Jaehyoun Ha, Jaesung Hwang

    Objective: The evaluation of skin age, reflecting overall facial characteristics, has not been established. Previous studies focused on visual assessment or individual‐specific feature such as wrinkles or skin color. We studied the evaluation model of skin age index (SAI) including the overall aging features including wrinkles, skin color, pigmentation, elasticity, and hydration.Methods: Total 300 healthy women aged between 20 and 69 years included in this study. Pearson correlation analysis performed to identify the key factors among the biophysical properties with aging and developed the prediction model of SAI. Statistical regression analysis and machine learning technique applied to build the prediction model using the coefficient of determination (R2) and root mean square error (RMSE). Validation study of the SAI model performed on 24 women for 6 weeks application with anti‐aging product.Results: Prediction model of SAI consisted of skin elasticity, wrinkles, skin color (brightness, Pigmented spot, and Uv spot), and hydration, which are major features for aging. The cforest model to assess a SAI using machine learning identified the highest R2 and lowest RMSE compared to other models, such as svmRadial, gaussprRadial, blackboost, rpart, and statistical regression formula. The cforest prediction model confirmed a significant decrease of predicted SAI after 6 weeks of application of anti‐aging product.Conclusion: We developed a prediction model to evaluate a SAI using machine learning, and led to accurate predicted age for overall clinical aging. This model can a good standard index for evaluating facial skin aging and anti‐aging products.


  • In vivo method to evaluate antioxidative activity using UVA‐induced carbonylated protein on human skin

    by Changhui Cho, Eunyoung Lee, Eunbyul Cho, Heejoo Yoo, Jiyeoun Bae, Jaehyoun Ha, Jaesung Hwang

    Background: Skin is continuously exposed to oxidative stress caused by reactive oxygen species (ROS) produced by the ultraviolet (UV) light, and it is important to evaluate the antioxidant activity. Carbonylated proteins (CPs) are candidate markers of oxidative modification as a result from the ROS. We aimed to develop the CP‐based method to assess the efficacy of antioxidants in human skin.Methods: Ten healthy females were enrolled in the study to determine the UVA dosage for CP production, and another 10 females were included to evaluate the antioxidative activity. The stratum corneum was collected from test skin using D‐Squame tape, and CPs from the SC were stained by fluorescence labeling and observed using a fluorescence microscope.Results: CP level significantly increased with UVA irradiation from 15J/cm2 to 50J/cm2 compared to the control (non‐UVA) area. CP production significantly increased by 34.38% and 35.22% in UVA irradiation and squalene (vehicle) areas. 5% α‐tocopherol and β‐carotene significantly increased the CP production by 20.77% and 19.34% after 2 hours of 30J of UVA irradiation compared to control area. Inhibition rate of CPs in 5% α‐tocopherol and 5% β‐carotene showed 41.45% and 45.37% after 2 hours of UVA irradiation.Conclusion: This study developed the simple, visual, and direct in vivo method to evaluate the antioxidative activity for products in human skin by measuring the CP level as an oxidative modification caused by UVA‐induced ROS generation.


  • CXCL14 downregulation in human keratinocytes is a potential biomarker for a novel in vitro skin sensitization test

    by Eunyoung Lee, Sungjin Ahn, Sun Hee Jin, Moonyoung Lee, Jeong Joo Pyo, Jeayoung C. Shin, Seungchan An, Jaehyoun Ha, Minsoo Noh


  • Open Access

    The Relationship between Epidemiologic Factors and Usage Pattern of Hair Care Products in Korea

    by Kyung-Duck Park, Byung Cheol Park, Ki Hyun Sung, Eunyoung Lee, Taewon Lee, Daeki Yoon, Kyu Bong Kim, Gyeong Hun Park, Il Yong Park, Myung Hwa Kim

    Park KD, et al. Ann Dermatol. 2019 Jun;31(3):307-314. https://doi.org/10.5021/ad.2019.31.3.307


  • Biophysical properties of striae rubra and striae alba in human skin: Comparison with normal skin

    by Changhui Cho, Eunbyul Cho, Nahee Kim, Juhee Shin, Sanga Woo, Jiun Lee, Jungok Lee, Eunyoung Lee, Jaehyoun Ha

    Background: Striae distensae are common dermal lesions that progress through two different stages: the striae rubra, which appears to be erythematous, and striae alba, which is characterized by a hypopigmented feature. The clinical characteristics between striae distensae stages and normal skin remain unknown.Objectives: We aimed to investigate the clinical characteristics according to stages of striae distensae in terms of their biophysical properties, using objective noninvasive measurements in comparison with adjacent normal skin.Methods: Sixty‐one healthy female subjects with striae distensae were included as follows: 30 with striae rubra and 31 with striae alba on the abdomen and thighs. Hydration of the epidermis and dermis, skin color brightness, and Erythema index were measured. Skin elasticity, roughness, and dermal echo‐density of the skin with striae distensae and adjacent normal skin were also measured.Results: Hydration of the epidermis and dermis showed no significant difference between the skin with striae distensae and normal skin. Brightness of skin with striae alba and normal skin was significantly higher than that of skin with striae rubra. Erythema index of skin with striae rubra was significantly higher than that of skin with striae alba and normal skin. Skin with striae rubra and striae alba had a rougher surface than normal skin. Elasticity and dermal echo‐density were significantly lower in striae distensae skin.Conclusions: Striae rubra and striae alba had similar biophysical properties in terms of skin hydration, elasticity, roughness, and dermal density. Moreover, striae distensae have less elasticity, more roughness, and lower dermal density than normal skin.


  • Assessment of exposure for baby cosmetic care products in a Korean population

    by Eunyoung Lee, Jongbok Yun, Jaehyoun Ha, Byung Cheol Park, Gyeong Hun Park, Hak Rim Kim, Seung Phil Hong, Kyu Bong Kim, Myung Hwa Kim


  • Cystathionine metabolic enzymes play a role in the inflammation resolution of human keratinocytes in response to sub-cytotoxic formaldehyde exposure

    by Eunyoung Lee, Hyoung-June Kim, Moonyoung Lee, Sun Hee Jin, Soo Hyun Hong, Seyeon Ahn, Sae On Kim, Dong Wook Shin, Seung-Taek Lee, Minsoo Noh