Scientists from GERO, the longevity biotech company together with Moscow Institute of Physics and Technology (MIPT) have demonstrated that physical activity data that is acquired from various wearables can now be utilized so as to produce digital biomarkers of frailty and aging.
Findings from the new research that has been published recently in Scientific Reports with an article bearing the title “Extracting Biological Age from Biomedical Data via Deep Learning: Too Much of a Good Thing?” exhibit the rising potential of mixing artificial intelligence technologies and wearable sensors for constant monitoring of health risk with real-time feedback to health and life insurance, wellness providers, and healthcare.
Various Biomarkers of Age Could be Utilized to Gauge Accurate Biological Clock
Artificial Intelligence is considered to be a powerful tool for the purpose of pattern recognition and has exhibited exceptional performance in identification of visual object, speech recognition, and various other fields. In the words of Peter Fedichev, Ph.D., GERO science director, senior study investigator, and head of the laboratory of biological systems simulation at MIPT, recent promising instances pertaining to the field of medicine comprise deriving biomarkers of age from clinical blood biochemistry, predicting mortality based on electronic medical records, and neural networks showing cardiologist-level performance in detection of an arrhythmia in ECG data. The team was inspired by these instances and it started exploring potential of artificial intelligence for assessment of various health risks based on human physical activity.
Many of the physiological parameters exhibit tight correlations with age. Various biomarkers of age, like circulating blood factor levels, gene expression or DNA methylation could be utilized so as to create accurate “biological clocks” in an effort to obtain biological age of individuals and the rate of aging estimations. Yet, large-scale genomic or biochemical profiling is still logistically expensive and difficult for any practical applications that is beyond any academic research.
However, the recent launch of affordable wearable sensors which allows collection and cloud storing of personal digitized activity records. This tracking has already been done without interfering with the day to day routines of hundreds of millions of individuals across the globe.