Translating Dietary Standards into Healthy Meals with Minimal Substitutions
This work addresses the need for personalized diet systems to improve nutrition conveniently and affordably, with potential applications in clinical support, public health, and consumer apps, though it is incremental in its approach.
The paper tackles the problem of converting dietary standards into healthy meals by developing a framework that uses meal archetypes and generative models to meet USDA nutritional targets with minimal food substitutions. The results show that generated meals improve adherence to recommended daily intake by 47.0%, increase nutrition by 10%, and reduce costs by 19-32% on average.
An important goal for personalized diet systems is to improve nutritional quality without compromising convenience or affordability. We present an end-to-end framework that converts dietary standards into complete meals with minimal change. Using the What We Eat in America (WWEIA) intake data for 135,491 meals, we identify 34 interpretable meal archetypes that we then use to condition a generative model and a portion predictor to meet USDA nutritional targets. In comparisons within archetypes, generated meals are better at following recommended daily intake (RDI) targets by 47.0%, while remaining compositionally close to real meals. Our results show that by allowing one to three food substitutions, we were able to create meals that were 10% more nutritious, while reducing costs 19-32%, on average. By turning dietary guidelines into realistic, budget-aware meals and simple swaps, this framework can underpin clinical decision support, public-health programs, and consumer apps that deliver scalable, equitable improvements in everyday nutrition.