Farran, AndreuUrpí Sardà, Mireia2026-01-142026-01-142025-05-012072-6643https://hdl.handle.net/2445/225462This editorial highlights how <strong>nutritional databases</strong> are essential for understanding the complex relationships between diet and health. These databases collect diverse types of information—such as food composition, dietary intake, health outcomes, and environmental data—and organize them in structured formats that make analysis possible. By integrating data from different sources, researchers can detect patterns and associations that would otherwise remain hidden. </p><p>The article emphasizes that as nutritional data grows in volume and complexity, <strong>advanced tools like artificial intelligence (AI) and machine learning (ML)</strong> are becoming increasingly important. These technologies help extract meaningful insights from large datasets, aid in identifying biomarkers, and support the development of predictive models that go beyond traditional analysis methods. </p><p>One of the most promising applications mentioned is the combination of nutritional databases with <strong>metabolomics</strong>—the study of metabolites in biological systems—which can reveal biochemical responses to dietary components. However, the authors also note challenges, such as the need for <strong>validated biomarkers</strong> and comprehensive metabolite databases to improve accuracy and usability in research and personalized nutrition. </p><p>Overall, the article argues that well-designed databases, supported by modern analytical approaches, are key to advancing nutrition science and informing evidence-based dietary guidelines and policies.4 p.application/pdfengcc-by (c) Farran-Codina, A. et al., 2025http://creativecommons.org/licenses/by/4.0/NutricióFonts d'informacióBases de dadesNutritionInformation resourcesDatabasesinfo:eu-repo/semantics/article7613412026-01-14info:eu-repo/semantics/openAccess