Researchers developed Artificial Intelligence (AI) system that can develop digital biomarkers of aging and fragility using physical data collected from wearable devices
Researchers from GERO, a longevity biotech company, and the Moscow Institute of Physics and Technology (MIPT) have developed an Artificial Intelligence (AI) system that can efficiently analyses recorded data of wearable devices for predicting biological age of an individual. Findings of the study were published in Scientific Reports on March 26, 2018. As a part of study, artificial biological clock collected data of individuals such as age, DNA methylation, gene expression, and circulating blood factor levels, which was used to predict biological age and rate-of-ageing estimates.
This study was aimed to evaluate the feasibility of data collection from wearable sensors and AI to continuously monitor health risks. Physical activity records and clinical data from the 2003 to 2006 in the U.S. were analyzed to develop AI software. Using the data, neural network was trained to predict biological age and mortality risk. It was observed that 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.
“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.”