The microbes that live in, and on, a person’s body can reveal important information about their health. Now, researchers have found they can use microbe samples—and a little help from machine learning techniques—to predict someone’s age.
The team shared its findings in a new study published by mSystems, noting that this work could lead to the development of “noninvasive microbiome-based tests to determine signs of accelerated or delayed aging in the elderly, or in individuals with chronic diseases.”
The study involved 4,434 fecal samples, more than 2,550 saliva samples and more than 1,975 skin samples. Participants were all between the ages of 18 and 90 years old, and they did not used antibiotics for at least one month before the samples were taken.
Skin samples resulted in the most accurate prediction, estimating a participant’s age within approximately 3.8 years. Saliva samples provided a prediction within 4.5 years, and the fecal samples provided a prediction within 11.5 years.
“The accuracy of our results demonstrate the potential for applying machine learning and artificial intelligence techniques to better understand human microbiomes,” co-author Ho-Cheol Kim, PhD, program director of the Artificial Intelligence for Healthy Living Program, a collaboration between IBM Research and the University of California, San Diego (UCSD), said in a prepared statement. “Applying this technology to future microbiome studies could help unlock deeper insights into the correlation between how microbiomes influence our overall health and a wide range of diseases and disorders from neurological to cardiovascular and immune health.”
“This new ability to correlate microbes with age will help us advance future studies of the roles microbes play in the aging process and age-related diseases, and allow us to better test potential therapeutic interventions that target microbiomes,” co-senior author Zhenjiang Zech Xu, PhD, a researcher at UCSD at the time, said in the same statement.
The authors hope to build on this research, designing new machine learning models to learn more about inflammation, autoimmune conditions and other serious health issues.