Deep aging clocks: AI-powered strategies for biological age estimation.

Abstract

Several strategies have emerged lately in response to the rapid increase in the aging population to enhance health and life span and manage aging challenges. Developing such strategies is imperative and requires an assessment of biological aging. Several aging clocks have recently been developed to measure biological aging and to assess the efficacy of longevity interventions. Biological age better reflects a person's actual age and is closely associated with health outcomes and time to mortality. Traditionally, most aging clocks assume that biological changes occur linearly over time. However, age-related changes do not necessarily follow a linear trajectory. Thus, "Deep Aging Clocks" have been developed to overcome previous clocks' limitations and better capture subtle changes that occur during aging. Here, we summarize the current deep aging clocks, including epigenetics, transcriptomics, metabolomics, microbiome, and imaging based clocks for age prediction. Recent advances in artificial intelligence (AI), utilizing deep learning techniques, have significantly enhanced the prediction of biological aging, and this would help improve aging clocks and accelerate efforts to reach longer and healthier lives.