Abstract
The rise of personalized nutrition is reshaping conventional dietary paradigms by shifting from generalized guidelines to individualized dietary interventions tailored to a person’s unique biological and lifestyle characteristics. This transformation is being driven by two cutting-edge technologies: artificial intelligence (AI) and three-dimensional (3D) food printing. AI facilitates the integration and analysis of diverse, high-dimensional data sources—including genomic, metabolomic, gut microbiota, biometric, and behavioral data—to generate precise, real-time nutritional recommendations.
In parallel, 3D food printing offers a novel manufacturing approach that enables the physical realization of personalized meals with customized textures, nutrient profiles, and aesthetic forms. This systematic review critically examined the current landscape of AI and 3D printing in personalized nutrition. Following PRISMA guidelines, we conducted a comprehensive literature search across PubMed, Scopus, and Web of Science, identifying 38 relevant studies published between 2015 and 2025.
The analysis focuses on clinical applications, consumer health solutions, and food technology innovations. Key findings indicate that AI algorithms have demonstrated effectiveness in predicting dietary needs and improving adherence, while 3D food printing has shown promise in producing tailored meals for populations with specific nutritional requirements, such as elderly and dysphagic patients.
However, integration challenges persist, including concerns over algorithmic bias, data privacy, limited regulatory frameworks, and technological scalability. The review also identifies promising future directions, including the use of AI-driven digital twins, multi-omics integration, and advances in sustainable food design using byproducts. Overall, this review highlights the synergistic potential of AI and 3D printing to revolutionize personalized diets and contribute to the future of smart nutrition.
1. Introduction
Traditional dietary guidelines have historically provided generalized nutritional recommendations aimed at serving broad populations. While these population-based approaches have contributed to foundational public health improvements, they often fall short in addressing the vast interindividual variability in genetics, metabolism, microbiota composition, health status, and lifestyle factors (Ordovas et al., 2018; Bush et al., 2020). As a result, the one-size-fits-all dietary paradigm frequently yields suboptimal outcomes in chronic disease prevention and management, particularly in conditions such as obesity, type 2 diabetes, and cardiovascular disease.
To overcome these limitations, the field of personalized nutrition has emerged as a more precise, individualized approach to dietary intervention. Personalized nutrition utilizes a diverse range of individual-specific data—including genomic, metabolomic, microbiome, and behavioral inputs—to tailor dietary plans that optimize health outcomes (de Toro-Martín et al., 2017). The development of this approach has been significantly accelerated by the advent of emerging technologies, especially artificial intelligence (AI) and three-dimensional (3D) food printing.
AI technologies, particularly machine learning and predictive analytics, have demonstrated immense potential for analyzing large-scale, high-dimensional health data. These systems can process inputs such as genetic profiles, microbiome composition, physical activity, and continuous biometric signals to generate real-time, dynamic dietary recommendations (Maleki Varnosfaderani & Forouzanfar, 2024; Salinari et al., 2023; D’Urso & Broccolo, 2024). In parallel, 3D food printing offers a complementary solution by enabling the on-demand production of meals that are tailored in texture, nutrient composition, flavor, and form—an especially valuable asset for populations with specific dietary or medical needs (Sun et al., 2015; Severini & Derossi, 2016; Arshad et al., 2025).
Together, these technologies have given rise to the emerging paradigm of smart nutrition, defined as a data-driven, technology-enhanced approach to dietary planning and intervention that integrates artificial intelligence, real-time biosensors, and advanced food manufacturing technologies such as 3D printing. Smart nutrition facilitates the delivery of personalized, adaptive, and scalable dietary solutions that can enhance health outcomes while simultaneously promoting sustainability. For example, 3D printing enables precise portion control and the reuse of food processing byproducts, thereby reducing food waste and supporting resource efficiency (Godoi et al., 2016; Baiano, 2020; Saha et al., 2025a).
Moreover, recent advancements in 3D food printing have emphasized its potential role in sustainable food systems through the valorization of agro-industrial byproducts. Padhiary et al. (2024) and Saha et al. (2025a) have shown that 3D printing applications in smart farming and food processing can support circular economy models by converting waste materials into nutritious, palatable food products. Simultaneously, AI-driven nutrition platforms and apps are gaining traction for their ability to continuously learn from user feedback and integrate multiple health data streams (Prasad et al., 2025). In the food industry, AI vision and automation systems are also being applied to improve precision and reduce operational inefficiencies (Saha et al., 2025b).
Despite these advancements, several important research and implementation gaps remain. There is limited empirical evidence assessing the feasibility, long-term effectiveness, and acceptability of AI-generated dietary plans and 3D-printed meals across diverse populations. Moreover, ethical and regulatory challenges—such as algorithmic bias, data privacy, digital literacy, and the lack of standardized safety protocols for 3D-printed foods—pose significant barriers to clinical and commercial integration (Verma et al., 2018; Sosa-Holwerda et al., 2024; Kassem et al., 2025).
In light of the identified research gaps, this review is organized around three central questions. First, it examines the current applications of artificial intelligence (AI) and three-dimensional (3D) food printing in personalized nutrition, including AI’s role in dietary analysis, predictive modeling, and real-time feedback, and how 3D printing enables the physical customization of meals based on nutritional needs, texture preferences, and individual health conditions (Arshad et al., 2025; Prasad et al., 2025).
Second, the review critically assesses the empirical evidence on the effectiveness, feasibility, and user acceptability of these technologies. This involves evaluating clinical trials, pilot studies, and usability reports to determine their impact on health outcomes, adherence rates, and consumer satisfaction across diverse populations (D’Urso & Broccolo, 2024; Sosa-Holwerda et al., 2024).
Third, it explores the ethical, regulatory, and implementation challenges limiting broader adoption. Key concerns include data privacy, algorithmic bias, unclear food safety regulations for printed products, and socioeconomic barriers to accessibility (Verma et al., 2018; Kassem et al., 2025).
This review synthesizes the state-of-the-art literature to assess the technological, ethical, and practical dimensions of smart nutrition, highlighting how the integration of AI and 3D printing moves beyond traditional dietary models by delivering real-time, individualized, and sustainable nutrition strategies. Finally, it presents evidence-based recommendations for future interdisciplinary research and real-world application in both clinical and consumer settings. Smart nutrition technologies offer transformative potential by enabling responsive, personalized, and scalable dietary solutions that promote health and support sustainable food systems through optimized nutrient delivery, portion control, and food waste reduction.
10. Conclusion
This review highlights the transformative potential of artificial intelligence (AI) and three-dimensional (3D) food printing in advancing the field of personalized nutrition. These emerging technologies enable the translation of complex biological and behavioral data—such as genomics, metabolomics, gut microbiota, and lifestyle metrics—into individualized dietary strategies that can be physically realized through customized meal production. Together, AI and 3D printing promise to enhance dietary precision, improve clinical outcomes, support chronic disease prevention, and drive innovation in the food industry. However, widespread implementation is currently hindered by technical limitations, data privacy risks, fragmented regulatory oversight, and socioeconomic disparities in access. To realize the full potential of smart nutrition, coordinated efforts from multiple stakeholders are required. Food manufacturers should invest in scalable and sustainable 3D printing solutions that utilize alternative ingredients, including valorized food waste streams, to support both personalization and environmental goals. Clinicians and nutrition professionals must work alongside technologists to validate AI-generated recommendations through clinical trials and ensure their safety, efficacy, and acceptability across diverse populations. Technologists and developers should prioritize ethical AI design, focusing on explainability, inclusivity, and interoperability between platforms and biosensors. Finally, policymakers need to establish standardized regulations for AI-based nutritional tools and 3D-printed food products, addressing concerns around consumer safety, labeling, and equitable access. Ultimately, the successful integration of smart nutrition technologies into healthcare and consumer environments will depend on interdisciplinary collaboration and a shared commitment to advancing personalized, preventive, and participatory nutrition.
Download the full article as PDF here Smart nutrition
or read it here
Mohammad Nazrul Islam Bhuiyan, Meher Nahid, Smart nutrition: AI and 3D printing for personalized diets,
Food Nutrition, 2025, 100032, ISSN 3050-8436, https://doi.org/10.1016/j.fnutr.2025.100032.
