If you eat a snack – a meatball, say, or a marshmallow – how will it affect your blood sugar? It’s a surprisingly tricky question: the body’s glycemic response to different foods varies based on individual genetics, microbiomes, hormonal fluctuations, and more. Because of that, providing personalized nutritional advice – which can help manage diabetes, obesity, and cardiovascular diseases, among other conditions – requires costly and intrusive testing, making it hard to deliver effective care at scale.
In a paper in the Journal of Diabetes Science and Technology, researchers at Stevens Institute of Technology offer a new approach: a data-sparse model capable of accurately predicting individual glycemic responses with no need for blood draws, stool samples, or other unpleasant testing. The key to…