A computer algorithm that creates personalized diets for individuals seeking to lose weight could help more than counting calories or exercising alone, a new study suggests.
Results from a study conducted by scientists at the Weizmann Institute in Israel indicate that it is the way in which the stomach’s bacteria react to food that dictates what a person should and should not eat.
The premise that general suggestions for eating healthy — by, for example, consuming more vegetables and fruits — are suitable for everyone, the research indicates, may not hold water. Instead, personally tailored diets, depending on each individual’s unique biological make-up, may be the most effective method.
“We are all different,” Dr. Eran Segal, a computational biologist who runs the project with Eran Elinav at the Weizmann Institute in Rehovot, told The Guardian. “We see tremendous variability in people’s responses to foods, so if you want to prescribe diets, they have to be personally tailored.”
The study was done initially with 20 individuals with pre-diabetes, who found that throughout the program, their glucose levels were at healthy levels. More than 1,000 people have been signed up over the past two years.
“Blood glucose is key to weight management and diabetes, and is linked to many, many other diseases, including cancer,” Segal said.
Participants were made to wear a blood glucose monitor, which recorded levels every five minutes, and to keep a food diary. Scientists gathered data on how participants reacted to more than 50,000 meals throughout the study. The differences were very significant.
“In some people, when they have bread, they show no change in glucose levels, but others spike dramatically,” Segal said.
The scientists then set out to determine what factors led to those differences and homed in on the microorganisms that live in our guts and how they responded to food. In the last stage of the study, they developed computer algorithms to analyze the gathered data and found that they could accurately predict how different people would respond to foods.
In many of the cases, Segal said, the controlled diets given to the participants contained foods most people would not find conducive to losing weight, such as ice cream and buttered bread.
“There are many more such surprises, including foods considered to be good which on average are not,” he added. “Our entire approach is data driven, not based on hypotheses or preconceptions, which in our view makes it powerful and science based.”
In the coming months, the scientists are set to expand the trial to further test the effectiveness of personalized diets.