Harvard researchers study health impact of walnuts by using machine learning models
Findings show eating walnuts leaves a metabolomic signature in the body linked with lower risk of type 2 diabetes and cardiovascular disease.
Researchers, from the Harvard T.H. Chan School of Public Health, in collaboration with investigators from Rovira i Virgili University and the University of Navarra, Spain, used machine learning models, a subset of artificial intelligence, to identify more precisely the components in walnuts that may be responsible for potentially reducing the risk of type 2 diabetes and cardiovascular diseases—two of the leading causes of death in the U.S.
This study, supported by the California Walnut Commission and published in The Journal of Nutrition, used a novel machine learning model to identify 19 metabolites that were associated with walnut consumption. The body forms specific metabolites based on what food is consumed. The walnut metabolite profile was associated with a 17 percent lower risk of type 2 diabetes and 29 percent lower risk of cardiovascular disease. This is the first study to examine the association between walnut metabolites and the risk of cardiometabolic diseases, contributing to the three decades of existing research on walnuts and heart health.