Title : Artificial intelligence in nutrigenetics
Abstract:
Advances in Artificial Intelligence (AI) are accelerating the evolution of nutrigenetics toward clinically actionable personalized medicine, enabling individualised dietary recommendations based on genetic variability. Nutrigenetics examines how genetic differences influence nutrient metabolism, dietary response, and disease risk, challenging the effectiveness of population-level dietary guidelines for individual care. Evidence from precision nutrition research demonstrates that genetic, metabolic, and environmental factors interact to shape dietary needs, providing a scientific rationale for individualized nutritional therapy (Ordovas et al., 2018). AI technologies offer new capabilities for analyzing complex, high-dimensional datasets generated by genomic, dietary, and phenotypic assessments. Machine-learning approaches can identify non-linear gene–nutrient interactions, stratify individuals by metabolic response, and support adaptive nutritional recommendations that evolve over time. Within nutritional therapy practice, AI has the potential to enhance practitioner decision-making rather than replace it, supporting integrative approaches that align modern data science with traditional dietary principles and patient-centred care (Topol, 2019). Direct-to-consumer (DTC) genetic testing labs have increased public access to nutrigenetic information, yet these services raise concerns regarding analytic validity, clinical utility, and appropriate interpretation. Reviews of DTC nutrigenomics highlight variability in test quality, limited evidence for sustained behaviour change, and the risk of over-simplified dietary advice when genetic results are delivered without professional guidance (Guasch-Ferré et al., 2018). These limitations underscore the importance of practitioner-mediated interpretation within evidence-based nutritional therapy frameworks. Ethical considerations are central to the responsible integration of AI into nutrigenetics. Issues of data privacy, informed consent, algorithmic bias, and equitable access must be addressed to ensure that AI-driven nutritional recommendations do not exacerbate existing health disparities. Ethical models of AI in healthcare emphasize transparency, accountability, and the preservation of human judgement in clinical decision-making (Topol, 2019). AI-enabled nutrigenetics represents a promising frontier for personalized nutrition within traditional and integrative medicine. Its successful implementation depends on rigorous scientific validation, ethical governance, and skilled practitioner involvement to translate genetic insights into safe, culturally sensitive, and effective nutritional therapy.
