Date: January 2024.
Source: Proceedings of the National Academy of Sciences USA (PNAS), 121.3: e2308812120. https://doi.org/10.1073/pnas.2308812120.
Significance: The aging process is inevitable and is a risk factor for chronic diseases. The biological age (BA) of each individual contains structural and functional determinants of aging, and its difference (AgeDiff) from the chronological age (CA) can be used as a biomarker for accelerated aging caused by underlying pathologies. We described a multimodal Transformer–based architecture which can estimate BA based on facial, fundus, and tongue images. Our results demonstrated that we can accurately estimate BA of healthy individuals, significant deviations of AgeDiff are present in individuals with chronic diseases, and AgeDiff can be used to accurately detect systematic diseases and identify progression risks. Our study highlights an approach to use easily and readily acquired patient data to identify chronic diseases.
Abstract: Aging in an individual refers to the temporal change, mostly decline, in the body’s ability to meet physiological demands. Biological age (BA) is a biomarker of chronological aging and can be used to stratify populations to predict certain age-related chronic diseases. BA can be predicted from biomedical features such as brain MRI, retinal, or facial images, but the inherent heterogeneity in the aging process limits the usefulness of BA predicted from individual body systems. In this paper, we developed a multimodal Transformer–based architecture with cross-attention which was able to combine facial, tongue, and retinal images to estimate BA. We trained our model using facial, tongue, and retinal images from 11,223 healthy subjects and demonstrated that using a fusion of the three image modalities achieved the most accurate BA predictions. We validated our approach on a test population of 2,840 individuals with six chronic diseases and obtained significant difference between chronological age and BA (AgeDiff) than that of healthy subjects. We showed that AgeDiff has the potential to be utilized as a standalone biomarker or conjunctively alongside other known factors for risk stratification and progression prediction of chronic diseases. Our results therefore highlight the feasibility of using multimodal images to estimate and interrogate the aging process.

Article: Accurate estimation of biological age and its application in disease prediction using a multimodal image Transformer system.
Authors: Jinzhuo Wanga, Yuanxu Gaob, Fangfei Wang, Simiao Zengd, Jiahui Li, Hanpei Miao, Taorui Wang, Jin Zeng, Daniel Baptista-Hon, Olivia Monteiro, Taihua Guan, Linling Cheng, Yuxing Lu, Zhengchao Luo, Ming Li, Jian-kang Zhu, Sheng Nie, Kang Zhang, Yong Zhou. Peking University, Beijing, China.

Related Articles:

  1. Three-Dimensional Stereophotogrammetry Facial Morphologic Signatures of Temporomandibular Disorders. L Mei, C Au, S Foo, C Gao, S Zhu, G Guan.
  2. A digital workflow with the virtual enamel evaluation and stereolithographic template for accurate tooth preparation to conservatively manage a case of complex exogenous dental erosion. T Luo, JJ Zhang, L Fan, Y Huang, J Yu , H Yu.
  3. A multi-ancestry GWAS meta-analysis of facial features and its application in predicting archaic human features. S Du, J Chen, J Li, W Qian, S Wu, Q Peng, Y Liu, T Pan, Y Li, SS Hadi, J Tan, Z Yuan, J Wang, K Tang, Z Wang, Y Wen, X Dong, W Zhou, A Ruiz-Linares, Y Shi, L Jin, F Liu, M Zhang, S Wang.
  4. Thermal facial image analyses reveal quantitative hallmarks of aging and metabolic diseases. Z Yu, Y Zhou, K Mao, B Pang, K Wang, T Jin, H Zheng, H Zhai, Y Wang, X Xu, H Liu, Y Wang, JDJ Han.