AI Enabled Nutritional Epidemiology for Cardiometabolic Health, Ageing, and the Double Burden of Malnutrition

Nutritional epidemiology has entered a new era with the advent of artificial intelligence (AI) and machine learning (ML), offering powerful tools to address some of the most pressing health challenges of our time. Cardiometabolic diseases, the complexities of healthy ageing, and the persistent double burden of malnutrition, characterised by the coexistence of undernutrition, overweight, and micronutrient deficiencies, pose significant threats to global health. Despite substantial advances in epidemiological study design, measurement, and causal inference, robust, scalable, and equitable solutions remain elusive. Current challenges include high measurement error in dietary assessment, limited causal inference with high-dimensional data, and a lack of interpretability and fairness in predictive models. Ongoing research has begun to demonstrate the utility of AI for dietary exposure measurement, risk prediction, and integration of diverse data streams, but widespread adoption is hampered by gaps in validation, reporting standards, and equity-oriented methodologies.This Research Topic aims to showcase cutting-edge research leveraging artificial intelligence and machine learning to transform nutritional epidemiology for the benefit of cardiometabolic health, healthy ageing, and addressing malnutrition in all its forms. The main objective is to advance the rigorous application of AI/ML in study design, exposure and outcome measurement, causal inference, and translation to public health action. Key questions include: How can AI improve dietary assessment accuracy and scale? In what ways can causal analyses be enhanced with ML, especially for time-varying exposures and confounders? What approaches ensure risk prediction is not only robust but also interpretable and actionable for different population subgroups? And critically, how do we guarantee that AI-driven approaches in nutrition support equity and avoid reinforcing existing disparities?To gather further insights in the intersection of AI innovation, nutritional epidemiology, and population health, we welcome articles addressing, but not limited to, the following themes:o AI-enabled dietary assessment and novel measurement methods, including image recognition and NLP for dietary datao Harmonization and integration of large-scale, multi-source dietary datasets using machine learningo Causal inference frameworks using AI, with emphasis on valid estimation, mediation, and effect heterogeneityo Multi-omics, digital health, and wearable data in relation to diet and cardiometabolic or ageing-related outcomeso Approaches to address and audit fairness, bias, and transportability of AI models across diverse populations and settingso Implementation strategies, translational research, and policy evaluation using AI in nutrition epidemiology o Applications that specifically address the double burden of malnutrition and promote global health equity Topic editors: Joyeta Ghosh, Reeti Debnath Source: https://www.frontiersin.org/research-topics/78329/ai-enabled-nutritional-epidemiology-for-cardiometabolic-health-ageing-and-the-double-burden-of-malnutrition