Featured Collection in The Journal of Nutrition

*This collection was prepared by Muzi Na, PhD, MHS, FASN, Editorial Science Fellow at The Journal of Nutrition.

Artificial intelligence (AI) and machine learning are fundamentally transforming nutritional science by enabling precision diets, complex data analysis, and predictive health modeling. This featured collection in The Journal of Nutrition showcases these technologies in action, from evaluating large language models in clinical settings to deriving network-based dietary patterns. Together, these studies offer a roadmap for integrating computational methods into evidence-based nutrition research.

• Evaluating ChatGPT’s Multilingual Performance in Clinical Nutrition Advice Using Synthetic Medical Text: Insights from Central Asia  — ChatGPT-4 gave passable nutrition advice in English and Russian but failed almost entirely in Kazakh, exposing a stark equity gap for underrepresented languages. A timely cautionary benchmark for anyone deploying LLMs in clinical or public-health nutrition.
• Harnessing Artificial Intelligence and Precision Diets for Brain Health and Cognitive Resilience — This review maps out “smart neuronutrition,” where AI integrates dietary, multi-omic, and neuroimaging data to personalize interventions against cognitive decline. A ready-made framing reference for the emerging AI–diet–brain intersection.
• Associations between Dietary Pattern Networks Derived from Machine Learning Algorithms and Cardiovascular Disease Risk in the NutriNet-Sante Cohort  — Network-based machine learning on a large French cohort derives data-driven dietary patterns and links them to cardiovascular risk. A fresh methodological template for moving beyond traditional a priori diet indices.
• The Application of Machine Learning in the Analysis of Macro and Micro-Nutrients of Human Milk: a Scoping Review  — This scoping review is the first consolidated map of how ML is applied to human milk composition. Ideal to cite when justifying computational approaches in lactation science.
• Dynamic Prediction of Postprandial Glycemic Response and Personalized Dietary Interventions Based on Machine Learning  — Builds ML models that forecast individual glucose responses to guide personalized diets. Essential precedent for the booming precision-glycemia literature.
• Predicting Cognitive Outcome Through Nutrition and Health Markers Using Supervised Machine Learning  — A concrete worked example using supervised learning to predict cognitive outcomes from nutritional and health biomarkers. Handy for anyone applying predictive modeling to diet–brain questions.