This technology is relatively new and deals only with blood sugar. In the meantime, the Mediterranean diet has decades of research behind it and is likely to remain the gold standard for healthy eating for years to come. Still, for people like Mr. Idema, AI like DayTwo’s could make it easier to maintain healthy eating patterns.
The app’s machine-learning algorithm can identify patterns and learn from the data with human assistance. It analyzes data from individual individuals’ blood glucose responses to identify individual characteristics – age, gender, weight, microbiome profiles and various metabolic measurements – that explain why a person’s glucose may fluctuate with certain foods. Grows up when the other person doesn’t. The algorithm uses these observations to predict how a particular food will affect someone’s blood sugar and assigns each food a score.
The system can’t yet take into account the candy bars someone had two hours ago — but users can play with food combinations to change the score for each meal. For example, the app gave macaroni and cheese – one of Mr Idema’s favorites – a low score, but he was able to improve it by adding protein. That’s because adding protein or healthy fats can reduce blood sugar spikes from a carbohydrate-heavy meal like macaroni.
“I thought they were going to say, ‘Oh my God, you’ve just become a salad eater,’ and that’s not the case,” Mr. Idema said.
DayTwo, which is currently only available to employers or health plans, not consumers, is one of the first AI-based apps to recommend healthy food options. Another company, ZOE, also generates food scores and is available directly to consumers for $59 per month. ZOE’s algorithm uses additional data, such as blood fat levels, in addition to microbiome and blood sugar tests. In a large 2020 study led by one of the company’s founders, Dr. Tim Spector, who is professor of genetic epidemiology at King’s College London, the algorithm was able to predict how a person’s blood sugar and fat would react to different foods. How does it react to substances?
Currently these algorithms focus mostly on blood sugar, but newer versions will incorporate more personalized data, and, in theory, recommend diets that are based on cholesterol, blood pressure, resting heart rate or any other measurable clinical measure. reduce the signal.
“Bringing together all these different data types is very, very powerful, and that’s where machine learning starts,” said Dr. Michael Snyder, a genetics professor at Stanford University.
#artificial #intelligence #nutritionist