MetaPlate: Counterfactual-Guided RAG-LLM Tool for Personalized Food Recommendation and Hyperglycemia Prevention

2026-06-08

AI Summary

Current dietary recommendations are static and lack personalization, limiting their effectiveness in preventing postprandial hyperglycemia. This work proposes an intelligent system that integrates counterfactual optimization with retrieval-augmented generation (RAG), uniquely incorporating structured constraints and domain knowledge into a large language model (LLM). Leveraging continuous glucose monitoring data, wearable physiological signals, and the USDA food database, the system dynamically predicts individual postprandial glycemic responses and generates actionable, personalized meal adjustment plans. Evaluations by registered dietitians demonstrate that the proposed approach significantly improves the clinical plausibility, portion appropriateness, and practical feasibility of dietary recommendations, thereby achieving a closed-loop transition from clinically infeasible advice to context-aware, implementable guidance.

Abstract

Postprandial hyperglycemia is a key risk factor for metabolic disorders; however, existing dietary guidance is often static, impractical, and insufficiently personalized, providing recommendations that are difficult to follow or not impactful. While recent advances leverage continuous glucose monitoring (CGM) and machine learning to predict glycemic responses, these approaches are largely predictive and lack actionable guidance. Moreover, recommendation systems are often misaligned with user goals and require extensive input. We present MetaPlate, a counterfactual explanation (CF) guided, context-aware decision-support framework that generates personalized meal recommendations to mitigate postprandial glucose excursions in healthy adults. MetaPlate integrates multimodal data, including CGM readings, wearable-derived physiological signals, and user-provided meal inputs from $25$ individuals to model pre-meal context. A machine learning model predicts glucose response, while a CF optimization module adjusts meal composition modifying macronutrient amounts to maintain glucose levels within a target range ($\leq 140$ mg/dL). An LLM-based retrieval-augmented generation (RAG) layer enhances interpretability by producing human-readable recommendations using constrained search of the USDA food database. We evaluate MetaPlate via a structured expert-in-the-loop assessment with registered dietitians (RDs), comparing performance before and after prompt refinement. Results show improvements in meal realism, portion suitability, and recommendation likelihood, with expert feedback indicating a shift from clinically implausible outputs to actionable, contextually appropriate recommendations. Our findings emphasize the importance of domain knowledge and structured constraints in LLM-driven systems and highlight the potential of MetaPlate as a real-time personalized dietary decision-support tool.

Problem

• postprandial hyperglycemia
• personalized food recommendation
• actionable guidance
• dietary decision support
• glucose response prediction

Innovation

• counterfactual explanation
• retrieval-augmented generation
• personalized nutrition
• postprandial glycemic control
• multimodal health data