Breaking News

Machine Learning Uncovers Link Between Diet, Chronic Disease Risk – HealthITAnalytics.com

By Jessica Kent

February 04, 2021 – A machine learning algorithm may be able to inform clinicians how food intake influences chronic disease risk.
A team from the Harvard T.H. School of Public Health, together with researchers from Rovira i Virgili University and the University of Navarra, Spain, developed machine learning models that identified elements in walnuts associated with reduced risk of type 2 diabetes and cardiovascular diseases.
In a study published in the Journal of Nutrition, researchers evaluated data from 1,833 participants of a large-scale, multi-year study that took place in Spain. The team looked at the effects of a Mediterranean diet in the prevention of cardiovascular disease among people at high risk for heart disease.

Dig Deeper

Participants were between the ages of 55 and 80 and followed one of three diets: A Mediterranean diet supplemented with mixed nuts (50 percent walnuts, 25 percent almonds, and 25 percent hazelnuts); a Mediterranean diet supplemented with extra-virgin olive oil; or a low-fat diet.
Researchers used machine learning algorithms to identify 19 metabolites that were associated with walnut consumption. The body forms specific metabolites based on what food is consumed, and 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 three decades of existing research on walnuts and heart health.
“With data-driven technologies, we are able to enhance our understanding of the relationship between diet and disease and take a personalized approach to nutrition which will lead to better prevention and management of various health conditions,” said Dr. Marta Guasch-Ferré, a Research Scientist at the Department of Nutrition at Harvard T.H. Chan School of Public Health and lead investigator of this research.
The team noted that these results do not prove cause and effect, and that more research is necessary in different populations as this study focused on only older Spanish adults. Additionally, because the field of metabolomics is rapidly evolving, future studies will need to aim to identify additional biomarkers of walnut intake that were not pursued in this study as well as to understand individual metabolic responses after consuming walnuts.
Despite these limitations, researchers expect that new and innovative tools – like the machine learning algorithm used in this study – will help researchers identify links between diet and disease.
“In this study, we revealed the unique metabolomic signature of walnuts, which brings us one step closer to understanding “how” walnuts are good for our health. These cutting-edge technologies are shaping the future of nutrition recommendations,” said Guasch-Ferré, who is also an instructor in medicine at Harvard Medical School and Brigham and Women’s Hospital.
Researchers are increasingly turning to machine learning and artificial intelligence tools to reduce chronic disease risk and improve the management of these conditions.
In June 2020, a study published in Nature Metabolism showed that a clinical decision support system that leverages machine learning could help patients control their glucose levels and enhance type 1 diabetes management.
The Oregon Health and Sciences University team developed a machine learning algorithm that could generate insulin injection recommendations. Researchers validated the system by monitoring 16 people with type 1 diabetes over the course of four weeks, showing that the model can help reduce hypoglycemia.
“Our system design is unique,” said lead author Nichole Tyler, an MD-PhD student in the OHSU School of Medicine. “We designed the AI algorithm entirely using a mathematical simulator, and yet when the algorithm was validated on real-world data from people with type 1 diabetes at OHSU, it generated recommendations that were highly similar to recommendations from endocrinologists.”

Source: https://healthitanalytics.com/news/machine-learning-uncovers-link-between-diet-chronic-disease-risk