3D facial image analysis to predict heterogeneity of human aging rate and impact of lifestyles

ABSTRACT: Not all individuals age at the same rate. Methods like ‘methylation clock’ were developed to infer aging rate by training on chronological age, relying on tissue samples, expensive assays and training errors to chronological age. Here we develop Convoluted Neural Networks (CNNs) based models through training on non-invasive, no assay required 3D facial images of approximately 5,000 Han Chinese individuals that achieve an average difference between chronological or perceived age and predicted age of ±2.8 years. We further profile blood transcriptomes from 280 individuals and infer the molecular regulators mediating the impact of lifestyles on facial aging speed through a causal inference model. These relationships are deposited and visualized in the human blood gene expression-3D facial image (HuB-FI) database. Overall, we find that humans age with different rates both in the blood and in the face, but coherently, with heterogeneity peaking at middle age. Our study provides an example how artificial intelligence can be leveraged to determine perceived age of humans as marker of biological age, no longer relying on training errors to chronological age, and to estimate the heterogeneity of aging rates within a population.

SUBMITTER: Xian,Xia 

PROVIDER: OEX003863 | NODE |

REPOSITORIES: NODE