Associations of Multidimensional Image-Derived Facial Skin Scores with Adiposity Measures in a Large Screening Cohort in Japan: A Cross-Sectional Study with Internal Temporal Evaluation
4 affiliations
- 1Department of Dermatology, Kindai University Faculty of Medicine, 1-14-1 Mihara-dai, Minami-ku, Sakai 590-0197, Osaka, Japan
- 2Anti-Aging Center, Kindai University, 3-4-1 Kowakae, Higashiosaka 577-8502, Osaka, Japan
- 3Pharmaceutical Research and Technology Institute, Kindai University, 3-4-1 Kowakae, Higashiosaka 577-8502, Osaka, Japan
- 4Department of Clinical Gene Therapy, School of Medicine, Osaka University, 2-2 Yamada-oka, Suita 565-0871, Osaka, Japan
Abstract
Background/Objectives: Proprietary, age-referenced, image-derived facial skin scores may contain adiposity-related information, but their validity is uncertain. We tested whether 14 scores added predictive information for body mass index (BMI), bioelectrical impedance analysis (BIA)-derived body fat percentage, and a proprietary BIA-derived visceral fat level score beyond age category and sex, after redness, and, exploratorily, after BMI. Methods: This study included 387,859 deduplicated account IDs from a Japanese screening program, a 95.5% nested subset of the previous report’s unique-account cohort. Gradient-boosting models were developed using April–July data and evaluated without retuning on August–October data. Performance was assessed with R2, mean absolute error (MAE), and paired bootstrap confidence intervals. Results: In the internal temporal evaluation cohort (159,726 account IDs), the facial skin-score panel provided incremental predictive information beyond age category and sex and beyond redness. After BMI inclusion, however, the additional explained variance was negligible (ΔR2 = 0.00165 for body fat percentage and 0.00017 for the visceral fat level score). Conclusions: The panel provided modest, order-dependent information in internal temporal evaluation but negligible additional information after BMI inclusion. These unvalidated proprietary scores are hypothesis-generating and do not support diagnostic or body-compartment-specific use.
Related
- Empirically Derived Whole-Diet Patterns and Multidimensional Adiposity in Emerging Adulthood: A Cross-Sectional Study of Geographically Diverse Students at a UK University
- Independent and joint associations of visceral adiposity and insulin resistance with hyperuricemia: A large-scale cross-sectional study
- Comparative Evaluation of Blood Pressure, Central Adiposity, and Physical Activity Patterns Between Wheelchair Users and Ambulatory Adults in a Rural South African Settings: A Cross-Sectional Study Protocol
- Social determinants of health and multidimensional health screening findings among immigrants participating in a community-based programme in Portugal: a cross-sectional study
- Associations of adiposity and physical fitness with hippocampaldependent mnemonic discrimination in postmenopausal women
BibTeX
@article{iinuma2026associations,
title = {{Associations of Multidimensional Image-Derived Facial Skin Scores with Adiposity Measures in a Large Screening Cohort in Japan: A Cross-Sectional Study with Internal Temporal Evaluation}},
author = {Kimi Iinuma and Kazuyasu Fujii and Chisa Nakashima and Shunsuke Morita and Toshio Morikawa and Hidekazu Yamada and Ryuichi Morishita and Atsushi Otsuka},
journal = {Journal of Clinical Medicine},
year = {2026},
month = oct,
doi = {10.3390/jcm15218413},
url = {https://www.mdpi.com/2077-0383/15/21/8413},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Associations of Multidimensional Image-Derived Facial Skin Scores with Adiposity Measures in a Large Screening Cohort in Japan: A Cross-Sectional Study with Internal Temporal Evaluation
AU - Kimi Iinuma
AU - Kazuyasu Fujii
AU - Chisa Nakashima
AU - Shunsuke Morita
AU - Toshio Morikawa
AU - Hidekazu Yamada
AU - Ryuichi Morishita
AU - Atsushi Otsuka
PY - 2026
DA - 2026/10/29
JO - Journal of Clinical Medicine
DO - 10.3390/jcm15218413
UR - https://www.mdpi.com/2077-0383/15/21/8413
AB - Background/Objectives: Proprietary, age-referenced, image-derived facial skin scores may contain adiposity-related information, but their validity is uncertain. We tested whether 14 scores added predictive information for body mass index (BMI), bioelectrical impedance analysis (BIA)-derived body fat percentage, and a proprietary BIA-derived visceral fat level score beyond age category and sex, after redness, and, exploratorily, after BMI. Methods: This study included 387,859 deduplicated account IDs from a Japanese screening program, a 95.5% nested subset of the previous report’s unique-account cohort. Gradient-boosting models were developed using April–July data and evaluated without retuning on August–October data. Performance was assessed with R2, mean absolute error (MAE), and paired bootstrap confidence intervals. Results: In the internal temporal evaluation cohort (159,726 account IDs), the facial skin-score panel provided incremental predictive information beyond age category and sex and beyond redness. After BMI inclusion, however, the additional explained variance was negligible (ΔR2 = 0.00165 for body fat percentage and 0.00017 for the visceral fat level score). Conclusions: The panel provided modest, order-dependent information in internal temporal evaluation but negligible additional information after BMI inclusion. These unvalidated proprietary scores are hypothesis-generating and do not support diagnostic or body-compartment-specific use.
SN - 2077-0383
ER -