NutriOrion: A Hierarchical Multi-Agent Framework for Personalized Nutrition Intervention Grounded in Clinical Guidelines

2026-02-20

AI Summary

This study addresses the challenges of delivering personalized nutrition interventions for patients with multimorbidity, particularly the integration of heterogeneous clinical data and the risk of diet–drug interactions, which often overwhelm conventional single-agent models due to context overload. To overcome these limitations, the authors propose a hierarchical multi-agent framework that decomposes tasks through a parallel–serial reasoning topology, integrating a multi-objective prioritization algorithm with hard pharmacological contraindication constraints to ensure clinical compliance. The system also enables automatic mapping between ADIME documentation standards and FHIR R4 resources, enhancing interoperability. Evaluated on 330 stroke patients, the approach reduced diet–drug interaction violations to 12.1%, significantly increased fiber (+167%) and potassium (+27%) intake, decreased sodium (−9%) and sugar (−12%), and yielded nutrient recommendations that correlated negatively with key biomarkers (r = −0.26 to −0.35).

Technology Category

• Multiagent Systems: Adversarial Agents
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Humans and AI: Intelligent User Interfaces

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Personalized nutrition intervention for patients with multimorbidity is critical for improving health outcomes, yet remains challenging because it requires the simultaneous integration of heterogeneous clinical conditions, medications, and dietary guidelines. Single-agent large language models (LLMs) often suffer from context overload and attention dilution when processing such high-dimensional patient profiles. We introduce NutriOrion, a hierarchical multi-agent framework with a parallel-then-sequential reasoning topology. NutriOrion decomposes nutrition planning into specialized domain agents with isolated contexts to mitigate anchoring bias, followed by a conditional refinement stage. The framework includes a multi-objective prioritization algorithm to resolve conflicting dietary requirements and a safety constraint mechanism that injects pharmacological contraindications as hard negative constraints during synthesis, ensuring clinical validity by construction rather than post-hoc filtering. For clinical interoperability, NutriOrion maps synthesized insights into the ADIME standard and FHIR R4 resources. Evaluated on 330 stroke patients with multimorbidity, NutriOrion outperforms multiple baselines, including GPT-4.1 and alternative multi-agent architectures. It achieves a 12.1 percent drug-food interaction violation rate, demonstrates strong personalization with negative correlations (-0.26 to -0.35) between patient biomarkers and recommended risk nutrients, and yields clinically meaningful dietary improvements, including a 167 percent increase in fiber and a 27 percent increase in potassium, alongside reductions in sodium (9 percent) and sugars (12 percent).

Problem

• personalized nutrition
• multimorbidity
• dietary guidelines
• drug-food interaction
• clinical decision support

Innovation

• hierarchical multi-agent framework
• personalized nutrition intervention
• clinical guideline grounding
• hard negative constraints
• FHIR interoperability