Biological age is a universal marker of aging, stress, and frailty

Abstract

We carried out a systematic investigation of supervised learning techniques for biological age modeling. The biological aging acceleration is associated with the remaining healthand life-span. Artificial Deep Neural Networks (DNN) could be used to reduce the error of chronological age predictors, though often at the expense of the ability to distinguish health conditions. Mortality and morbidity hazards models based on survival follow-up data showed the best performance. Alternatively, logistic regression trained to identify chronic diseases was shown to be a good approximation of hazards models when data on survival follow-up times were unavailable. In all models, the biological aging acceleration was associated with disease burden in persons with diagnosed chronic age-related conditions. For healthy individuals, the same quantity was associated with molecular markers of inflammation (such as C-reactive protein), smoking, current physical, and mental health (including sleeping troubles, feeling tired or little interest in doing things). The biological age thus emerged as a universal biomarker of age, frailty and stress for applications involving large scale studies of the effects of longevity drugs on risks of diseases and quality of life.To be published as Chapter 2 in "Biomarkers of aging", ed. A. Moskalev, Springer, 2019. 2

Genetic and Phenotypic Evidence for the Causal Relationship Between Aging and COVID-19

“…An interesting alternative is to produce the log-linear all-cause mortality estimate with a proportional hazard model and treat the resulting value as a measure of biological age. Phenotypic Age from blood biochemistry markers 27 , DOSI from CBC 28 , averaged physical activity levels 29 , and more sophisticated machine learning algorithms used to predict the risk of death from physical activity time series of wearable devices 43 , or even self-reported health questionnaires, are all examples of this approach 44 . We were not able to obtain the epigenetic clock predictions of UKBB subjects due to the lack of corresponding measurements.…”

Metabolic health and lifestyle medicine should be a cornerstone of future pandemic preparedness

“…[50][51][52] Increased relative biological age, which can be inferred from a number of potential biomarkers, is tightly linked to lifestyle factors such as smoking, being sedentary, excessive alcohol intake, and a poor-quality diet. [51][52][53][54] Regardless whether the exact underlying mechanisms are currently understood, it is clear that the tenets of lifestyle medicine have extraordinary power to improve the health of the population, both overall as well as in the face of unknown future pandemics. For instance, a wide variety of dietary approaches have been shown to be effective in providing long-term weight loss, reductions in blood pressure, improved glycemic control, and even reversal of type 2 diabetes.…”

“…Even age, traditionally thought to be an unmodifiable risk factor for disease and mortality, may be partially modifiable, with biological age and immune age superseding chronological age as predictors of outcome 50‐52 . Increased relative biological age, which can be inferred from a number of potential biomarkers, is tightly linked to lifestyle factors such as smoking, being sedentary, excessive alcohol intake, and a poor‐quality diet 51‐54 …”

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

“…At present, deep learning blood-based Δ age results only associated with smoking status [12], as are more classical markers of biological age based on the Klemera-Doubal method [14]. Recently, another blood-based ageing clock was developed, MORTAL-bioage, based on the prediction of mortality risk by blood markers and chronological age through Cox Proportional Hazards (PH) models, and re-calibration of the risk in years [15]. The resulting biological age acceleration was negatively associated with physical activity, and positively with TV watching, and heavy alcohol drinking (>5 drinks/day), in addition to smoking status and number of cigarettes/day [15].…”

“…Recently, another blood-based ageing clock was developed, MORTAL-bioage, based on the prediction of mortality risk by blood markers and chronological age through Cox Proportional Hazards (PH) models, and re-calibration of the risk in years [15]. The resulting biological age acceleration was negatively associated with physical activity, and positively with TV watching, and heavy alcohol drinking (>5 drinks/day), in addition to smoking status and number of cigarettes/day [15]. However, this clock had a different construction paradigm aimed at detecting mortality risk with the highest accuracy, and explicitly included age as predictor.…”