GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health

TL;DR

GLEN-Bench is a comprehensive benchmark combining graph and language data to improve personalized nutritional health assessment, addressing real-world constraints and providing explainable recommendations for managing health conditions.

Contribution

It introduces the first unified graph-language benchmark for nutritional health, integrating diverse data sources and tasks to evaluate models on risk detection, personalized recommendations, and explainability.

Findings

Identified dietary patterns linked to health risks.

Established baseline performances for graph-language models.

Provided insights for practical nutritional interventions.

Abstract

Nutritional interventions are important for managing chronic health conditions, but current computational methods provide limited support for personalized dietary guidance. We identify three key gaps: (1) dietary pattern studies often ignore real-world constraints such as socioeconomic status, comorbidities, and limited food access; (2) recommendation systems rarely explain why a particular food helps a given patient; and (3) no unified benchmark evaluates methods across the connected tasks needed for nutritional interventions. We introduce GLEN-Bench, the first comprehensive graph-language based benchmark for nutritional health assessment. We combine NHANES health records, FNDDS food composition data, and USDA food-access metrics to build a knowledge graph that links demographics, health conditions, dietary behaviors, poverty-related constraints, and nutrient needs. We test the benchmark using opioid use disorder, where models must detect subtle nutritional differences across disease stages. GLEN-Bench includes three linked tasks: risk detection identifies at-risk individuals from dietary and socioeconomic patterns; recommendation suggests personalized foods that meet clinical needs within resource constraints; and question answering provides graph-grounded, natural-language explanations to facilitate comprehension. We evaluate these graph-language approaches, including graph neural networks, large language models, and hybrid architectures, to establish solid baselines and identify practical design choices. Our analysis identifies clear dietary patterns linked to health risks, providing insights that can guide practical interventions.