Revolutionizing Nutritional Epidemiology: Harnessing Digital Health, AI, and Big Data for Population-Level Disease Prevention and Management: Volume II

Nutritional epidemiology focuses on understanding the relationship between diet, health, and disease, playing a crucial role in identifying dietary risk factors and shaping public health recommendations. Traditional methods of analyzing dietary patterns have faced challenges due to the complexity of nutritional data and individual variability. However, recent advancements in digital technologies, such as artificial intelligence (AI), big data, and digital health tools, are transforming this field. These innovations allow for the integration and analysis of vast amounts of data from diverse sources, including genetic profiles, electronic health records, and wearable devices, enabling more accurate and personalized insights into dietary impacts on health. This evolution opens new opportunities to develop precision strategies for preventing and managing chronic diseases like diabetes, obesity, cardiovascular conditions, and cancer, advancing both research and public health interventions. Socioeconomic factors such as income, education, occupation, neighbourhood deprivation, and food insecurity are key determinants of diet and health, and digital data sources now make it possible to capture and analyse them at scale alongside dietary and clinical information. Building on the strong reception of Volume I, this second volume moves further into the practical and ethical dimensions of these technologies, including how they translate into real-world dietary assessment, how wearable and biomarker data can be integrated at scale, and the methodological and ethical questions that come with using these tools in nutrition research.This Research Topic aims to explore how emerging digital tools, including artificial intelligence (AI), big data, and digital health technologies, can revolutionize the field of nutritional epidemiology by enabling more personalized, precise, and real-time approaches to disease prevention and management. Despite advancements in nutrition science, challenges remain in understanding the complex relationship between diet, health, and disease due to the vast variability in individual responses to dietary patterns and the limitations of traditional methods. To address this, the integration of large-scale datasets, spanning genetic, metabolic, dietary, lifestyle and socioeconomic information, alongside innovative analytical tools like machine learning, can uncover patterns that were previously difficult to identify. This research aims to highlight the potential of these technologies to improve dietary recommendations, predict disease outcomes, and enhance public health interventions. By leveraging these digital innovations, we can move towards more targeted, individualized strategies for chronic disease prevention, ultimately leading to better health outcomes at both the individual and population levels. Volume II places particular emphasis on AI-driven dietary assessment tools, including automated, image-based, and multimodal approaches that move beyond traditional self-report methods, on applications of generative AI and large language models, on the growing role of wearable technologies, digital biomarkers, and passive sensing in capturing continuous, real time health and dietary data, on the integration and harmonization of large-scale datasets, and on explainable AI together with the ethical and methodological considerations these approaches raise, including data privacy, governance, algorithmic bias, validation of digital tools, and equitable access across populations.We welcome articles that address, but are not limited to, the following themes:• The application of AI and machine learning to analyze dietary patterns and disease risk at the population level.• The use of big data to track and predict nutritional trends and health outcomes in populations.• AI driven dietary assessment methods, including automated, image-based, and multimodal approaches, that improve on traditional self-reported methods.• Applications of generative AI and large language models in nutritional epidemiology, dietary assessment, personalized nutrition, and public health nutrition.• The use of digital biomarkers, wearable technologies, and passive sensing to capture continuous, real time dietary, behavioral, and health data.• Integrating genetic, metabolic, dietary, and wearable-derived data for personalized nutrition recommendations, and the harmonization of large-scale nutritional, clinical, omics, and lifestyle datasets.• Development of predictive algorithms for health outcomes based on dietary intake and lifestyle factors.• Integration of socioeconomic data, including income, education, occupation, area level deprivation, and food insecurity, into AI and big data models of diet, health, and disease risk.• Use of digital health tools and big data to study socioeconomic inequalities in diet and chronic disease, including evidence from low and middle income settings and underserved groups.• Explainable and transparent AI approaches in nutritional epidemiology, including reproducibility, validation, algorithmic bias, and generalizability.• The impact of digital nutritional databases and real world applications of AI and big data on public health policy, with attention to equitable access across populations.• Ethical, methodological, and equity considerations associated with AI, wearables, and big data in nutrition research, including data privacy, governance, bias, and validation. Topic editors: Leandro Oliveira, Marta Esgalhado, Rui Poínhos Source: https://www.frontiersin.org/research-topics/85581/revolutionizing-nutritional-epidemiology-harnessing-digital-health-ai-and-big-data-for-population-level-disease-prevention-and-management-volume-ii