AI uses wearable data to predict biological age

Researchers from GERO, a longevity biotech company, and the Moscow Institute of Physics and Technology (MIPT) have developed an artificial intelligence (AI) system that uses physical data collected from wearables to develop digital biomarkers of aging and fragility. Findings were published March 26 in Scientific Reports.

The team’s artificial biological clock involved collecting data including age, DNA methylation, gene expression and circulating blood factor levels. These data points were used to predict biological age and rate-of-ageing estimates. Currently, developing biochemical or genomic profiling is difficult and expensive. In response, researchers in this study evaluated the feasibility of using data collected from wearable sensors and AI to continuously monitor health risks.

“Artificial Intelligence is a powerful tool in pattern recognition and has demonstrated outstanding performance in visual object identification, speech recognition, and other fields,” said Peter Fedichev, PhD, GERO Science Director and head of MIPT lab. “Recent promising examples in the field of medicine include neural networks showing cardiologist-level performance in detection of arrhythmia in ECG data, deriving biomarkers of age from clinical blood biochemistry, and predicting mortality based on electronic medical records. Inspired by these examples, we explored AI potential for Health Risks Assessment based on human physical activity.”

To develop the AI, researchers analyzed physical activity records and clinical data from the 2003 to 2006 U.S. National Health and Nutrition Examination Survey (NHANES). The data were used to train a neural network to predict biological age and mortality risk. The convolution neural network was able to correlate motion patterns to build a general life span. Results of the study showed the AI outperformed previous models of biological age and mortality risks developed using the same data set.

“Life and health insurance programs have already begun to provide discounts to their users based on physical activity monitored by fitness wristbands,” concluded Fedichev. “We report that AI can be used to further refine the risks models. Combination of aging theory with the most powerful modern machine learning tools will produce even better health risks models to mitigate longevity risks in insurance, help in pension planning, and contribute to upcoming clinical trials and future deployment of anti-aging therapies.”