Exploring domains, clinical implications and environmental associations of a deep learning marker of biological ageing

Abstract

Deep Neural Networks (DNN) have been recently developed for the estimation of Biological Age (BA), the hypothetical underlying age of an organism, which can differ from its chronological age (CA). Although promising, these population-specific algorithms warrant further characterization and validation, since their biological, clinical and environmental correlates remain largely unexplored.Here, an accurate DNN was trained to compute BA based on 36 circulating biomarkers in an Italian population (N=23,858; age≥35 years; 51.7% women). This estimate was heavily influenced by markers of metabolic, heart, kidney and liver function. The resulting Δage (BA-CA) significantly predicted mortality and hospitalization risk for all and specific causes. Slowed biological aging (Δage<0) was associated with higher physical and mental wellbeing, healthy lifestyles (e.g. adherence to Mediterranean diet) and higher socioeconomic status (educational attainment, household income and occupational status), while accelerated aging (Δage>0) was associated with smoking and obesity. Together, lifestyles and socioeconomic variables explained 48% of the total variance in Δage, potentially suggesting the existence of a genetic basis.These findings validate blood-based biological aging as a marker of public health in adult Italians and provide a robust body of knowledge on its biological architecture, clinical implications and potential environmental influences.

Comparison of Biological Age Prediction Models Using Clinical Biomarkers Commonly Measured in Clinical Practice Settings: AI Techniques Vs. Traditional Statistical Methods

“…et al, 2020; Zhong et al, 2020;Gialluisi et al, 2021;Wang et al, 2021). However, there are few studies that compare AI techniques with traditional statistical methods to construct a BA prediction model using clinical biomarkers.…”

Association between the Inflammatory Potential of the Diet and Biological Aging: A Cross-Sectional Analysis of 4510 Adults from the Moli-Sani Study Cohort

“…The resulting discrepancy between BA and CA is usually indicated by Δage, which may suggest either accelerated (Δage > 0) or decelerated biological aging (Δage < 0) [ 13 ]. Negative values of Δage (i.e., where BA is less than CA) are associated with the deceleration of aging and a lower risk of morbidity, hospitalization, and mortality [ 15 , 16 ]. One of the most innovative ways to estimate biological aging is by applying deep neural networks to circulating biomarkers [ 16 , 17 , 18 , 19 ].…”

“…Negative values of Δage (i.e., where BA is less than CA) are associated with the deceleration of aging and a lower risk of morbidity, hospitalization, and mortality [ 15 , 16 ]. One of the most innovative ways to estimate biological aging is by applying deep neural networks to circulating biomarkers [ 16 , 17 , 18 , 19 ]. Indeed, although this represents only a generic marker of biological aging and other markers or scales such as frailty and cognitive performance may better tag organ-specific aging [ 20 ] or the intrinsic aging capacity [ 21 , 22 ], blood-based estimates of BA can provide information on several aging domains within the human body because it can be based on a range of different circulating biomarkers.…”

Ageing and degeneration analysis using ageing-related dynamic attention on lateral cephalometric radiographs

“…With the rapid growth of data scale and computing power, deep learning methods have been widely used in healthcare. Gialluisi et al used a deep neural network to predict mortality and hospitalization risk with multiple circulating biomarkers 11 . Lima et al used deep neural networks with electrocardiograms to predict the age of patients and explored the correlation between the difference between predicted and actual age and death 12 .…”