The Future of Healthy Eating: The artificial intelligence nutritionist is here | Health and Technology
The Artificial Intelligence Nutritionist is Here: The Future of Healthy Eating!
Companies are experimenting with personalized eating apps and say the future of healthy eating lies in artificial intelligence.
After 20 years with type 2 diabetes, Tom Idema has given up hope of getting his condition under control. He tried many diets without success and even considered bariatric surgery. When her employer gave her the opportunity to use a new diet app that uses artificial intelligence to monitor blood sugar, she accepted.
Mr Edema, 50, sent in a stool sample with his microbiome sequence and filled out an online questionnaire that included his blood sugar, height, weight and health status. The data was used to create a profile for him, to which he added endless blood glucose measurements over weeks. After that, an app called Detu rates Mr. Idema's different foods based on how good or bad his blood sugar is to help him make better food choices.
After using the procedure for about 500 days, her diabetes disappeared and her blood sugar levels returned to normal. Though Datu says the app isn't a weight-loss goal, he's dropped from 320 pounds to 229 pounds. "I'm wearing pants that I haven't worn since high school," said Mr. Idma, an administrator at Central Michigan University in Mount Pleasant, Michigan.
DayTwo is one of the host apps that claims to offer artificial intelligence. eat solutions. Traditional eating habits often have a set list of "good" and "bad" foods, and these programs are like personal assistants, helping people make quick and healthy food choices. These are based on research showing that everyone reacts differently to the same foods and that healthy choices can be unique to everyone.
Regardless, AI nutritionists are still not ready for widespread deployment, and there is little research from external app vendor sources. Users should be wary of overly broad claims that go beyond predicting how foods affect blood sugar.
But proponents say blood sugar is just the start, and AI programs can target other aspects of metabolic health, like obesity and heart disease, and ultimately help guide a person's daily food choices.
How to choose (artificially) smart foods
The algorithm used by the DayTwo app is based on research by Iran Elinav and Iran Segal from the Weizmann Institute of Science in Israel, who co-founded the company in 2015. Last year, when the company used its algorithm to match a person's microbiome and metabolism through diet, the company found that it controlled blood sugar better than Mediterranean foods, which are considered some of the healthiest foods on the planet.
"You need to start measuring individuals instead of measuring foods by calorie count and trying to find a 'healthy diet,'" said Dr. Elinav.
The technology is relatively new and only deals with blood sugar. Now, with decades of research behind the Mediterranean diet, it's likely to remain the gold standard of healthy eating for years to come. Still, Mr. Idema could make it easier for people like AI to maintain healthy eating habits like DayTwo.
The app's machine learning algorithms recognize patterns and learn from the data with the help of humans. It analyzes data on different people's glycemic responses to thousands of different foods to identify individual characteristics — age, gender, weight, microbiome profile, and various metabolic measures — that explain why a person's glucose rises with certain foods while others don't. t. The algorithm uses these observations to predict how a particular food will affect a person's blood sugar and determines a score for each food.
The system still can't account for candy bars two hours in advance - but users can change the score for each meal through food combinations. For example, the app gave Mr. Idema a low score for one of his favorite macaroni and cheeses, but he was able to improve it by adding protein. This is because adding protein or healthy fats to high-carb foods like macaroni can trigger a spike in blood sugar.
"I thought they were going to say, 'Oh my God, you just had a salad and it didn't happen,'" Mr Idema said.
Currently only available for employers or health planners, DayTwo is one of the few AI-powered apps that recommends healthy eating habits, not consumers. Another company, ZOE, also creates food reviews and offers them direct to customers for $59 a month. In addition to microbiome and blood glucose tests, ZOE's algorithm uses additional data, such as: B. blood lipid levels. Professor of Genetic Epidemiology at King's College London. In a large-scale 2020 study led by company co-founder Tim Specter, the algorithm was able to predict how a person's blood sugar and fat would respond to different foods.
The algorithms currently focus on blood sugar, but newer versions will incorporate more personal data and, in theory, recommend foods that lower cholesterol, blood pressure, resting heart rate, or other measurable clinical indicators.
"It's very, very powerful to bring in all these different types of data, and this is where machine learning starts," said Dr. Michael Snyder, Professor of Genetics at Stanford University.
The field of personalized nutrition is still in the wild west, and experts say it's important to choose from the hype. Plenty of companies are willing to test your microbiome and offer AI-driven nutrition advice - and sell you supplements - but on the basis of some scientifically rigorous testing. Last year, uBiome, which created one, was even accused of cheating. In general, the broader a company's health and weight loss claims, the less reliable the evidence supporting them.
"Unfortunately, I think the hype is over for now," said Dr. Eric Topol, a cardiologist and founder and director of the Scripps Research Translational Institute.
The data used by apps like DayTwo and ZOE capture only a fraction of the interactions between the gut microbiome, our metabolism and food. There are many other factors, such as genetic factors that affect metabolism, that are overlooked by current AI program.
READ MORE: Best Electric Vehicles in 2022 | Technology
"It doesn't tell you the whole story, and tweaking around glucose alone isn't enough to create the perfect diet for you," said Dr. Casey Minus, co-founder and chief medical officer of a digital health company called Levels. AI applications can force users to eat foods that are good for raising blood sugar and preventing diabetes but may be unhealthy in other ways.
For example, when Topol tried the Datu app, his advice on blood sugar control, such as Eating spinach and raspberries, for example, are high in oxalic acid, which can lead to kidney stones. Because the app does not take into account the existing risk of this situation.
Additionally, food restriction is viewed as a poor way to change eating habits and is often counterproductive. But many experts want personalized AI. Applications will be easier to track and provide better long-term behavior.
Currently, these apps help nutritionists with nutritional advice, but they will not replace them, both ZOE and DayTwo regularly create virtual check-ups with a nutritionist or nutritionist in their programs.
According to dr Topol, larger and longer-term studies that integrate more layers of data into algorithms such as sleep, exercise or stress could make these procedures more precise and accurate for everyone. They can also help people understand how short-term responses, such as postprandial glucose spikes, can affect long-term health.
What we don't know is how or how everyday improvements translate into long-term health. dr Artificial Intelligence Popular Food Show. “Can diabetes be prevented? Can you prevent heart disease and other chronic diseases?”
This is a growing study. The National Institutes of Health's Precision Health Nutrition Research Program began a multi-year study in January to develop an algorithm to predict a person's response to food.
But for Mr. Idema, the impact of personalized nutrition is already evident, most recently when his blood sugar levels improved, allowing him to enjoy his daughter's birthday cake. "I had a blood glucose meter at the time and I was within reach, so my body took it well," he said. "So, I'm in a better place now and I think this project really saved my life."
Source: Sandeep Ravindran, The New York Times, Direct News 99