A recent study published in the journal Nature Aging investigated the genetic architecture of artificial intelligence (AI)-derived biological age gaps (BAGs) for multiple organ systems and their links with lifestyle, chronic disease, and aging. Aging is a multifaceted biological process shaped by lifestyle, genetic, and environmental factors, which impacts organ systems and leads to chronic disease. Deciphering the phenotypic heterogeneity of aging across organs can lead to advances in precision medicine.
One study investigated this heterogeneity using AI to estimate BAGs. BAG represents the difference between individuals’ AI-predicted and chronological age. Notwithstanding the progress in multiorgan research, two questions remain: Which genetic variants influence the phenotypic heterogeneity of BAGs, and how are they causally linked to each other, lifestyle factors, and chronic diseases? The study and findings In the present study, researchers used computational genomics and AI to explore the genetic architecture of BAGs for nine organ systems and their causal links and associations with lifestyle factors, organ aging, and chronic diseases.
They used multi-omics data of more than 370,000 participants from the United Kingdom (UK) Biobank. First, support vector regression was used to derive BAGs for metabolic, musculoskeletal, cardiovascular, eye, brain, immune, renal, hepatic, and pulmonary systems using clinical and organ-specific imaging data. The BAGs were fit as phenoty.