Nutrition Gets Personal

Advances in nutrition science are transforming the way dietitians tailor eating plans, moving from generalized advice to approaches informed by genetics, microbiome data, and other molecular-level insights. By integrating biological measures with social, environmental, and lifestyle factors, personalized nutrition aims to deliver highly targeted, actionable recommendations that fit each individual’s unique circumstances. Emerging tools like artificial intelligence and machine learning (AI/ML) are enabling scientists to analyze vast datasets, linking diet patterns to specific health outcomes with unprecedented precision. While the research is still evolving, the potential to improve health and prevent disease through precision nutrition makes this a pivotal moment for consumers and the science community alike.

Defining Precision Nutrition

Dietitians have been giving nutrition advice for generations—sodium restriction for high blood pressure, carbohydrate monitoring for diabetes, and higher fiber, lower saturated fat, and regular exercise for elevated blood lipids. These approaches, along with long-standing dietary guidelines, offer generalized recommendations to the broader population. We identify four nutrients of concern—vitamin D, calcium, potassium, and dietary fiber—and promote dietary patterns that increase their intake. We also accept that, for most people, broad guidance such as reducing solid fats, sodium, and added sugars can help improve links to disease outcomes.

Unlike pharmaceuticals, which target a specific disease risk or condition, diet is a generalized exposure that occurs multiple times a day. Even evidence-based patterns like the Dietary Approaches to Stop Hypertension (DASH) illustrate that it is the combination of exposures—such as higher fruit and vegetable intake, some dairy consumption, and regular exercise—that improves health outcomes rather than any single nutrient.

Precision nutrition seeks to move beyond these generalized approaches by tailoring dietary recommendations to an individual’s unique biological, lifestyle, and environmental context. Instead of offering one-size-fits-all guidance, precision nutrition integrates personal characteristics to optimize nutrition strategies for people striving to maintain health and reduce future chronic disease risk.

Nutrition is fundamental to human life, and we continue to have challenges with a one-size-fits-all approach to dietary guidance. There is high interpersonal variability in glycemic responses to foods, and this is an area that has become more obvious with the advent of new glucose monitors. Reasons for high variability in glucose response include genotype, phenotypes, and environmental exposures beyond diet. With the ability to track our personal data on health status markers through a healthcare database, we can track changes in standard health biomarkers collected at regular yearly medical visits.

Computational Nutrition Emerges

Recent advances in AI, wearable biosensors, and multi-omics technologies, combined with interdisciplinary translational collaborations, are transforming the nutrition landscape and enabling precision nutrition. Researchers suggest the term “computational nutrition,” using statistical modeling, simulation, causal inference, ML, and deep learning—building expertise from nutrition, food science, computer science, statistics, systems biology, and public health (Zhu et al. 2025).

Research directions include the following:

• Prediction of personalized metabolic responses to foods and establishment of individualized dietary reference intake
• Causal inference in nutrition and diseases and evaluation of individualized treatment effects of nutritional intervention
• Precise and dynamic assessment and monitoring of dietary-related disease risks
• Simulation and evaluation of public health nutrition policies and sustainability assessment of dietary pattern

Many challenges exist in this journey, including the reliability of wearable biosensors, trade-offs in feature selection, ethics of algorithms and health equity, and interpretability of algorithms—all important questions to ensure human well-being and rights.

In another study, researchers discuss personalized nutrition that aims to prevent and manage chronic diseases by providing individualized dietary guidance based on genetic, metabolic, and lifestyle data (Mundt et al. 2025). AI has become a key enabler in personalized nutrition by using large-scale, multi-omics datasets in obesity, diabetes, cardiovascular, and gastrointestinal disorders, where digital twins and health knowledge graphs support personalized intervention.

Widely accessible tools for personalized nutrition include demographic information (e.g., age, sex, and life stage), anthropometrics data, standard clinical biomarkers (e.g., cholesterol, blood glucose, and blood pressure), and potentially, biomarkers of nutrient levels recorded in a patient’s online account. Lifestyle information can be collected, but there are limited public databases to access this information. Physical activity, environment, and data from wearable devices for diet tracking and exercise tracking can also be accessed.

Other data are less accessible, including genotypic and omics-based information and tools. Genetic testing and counseling data are protected health information and present ethical concerns that must be addressed before they can be made publicly available. Omics testing—including transcriptomics, proteomics, metabolomics, microbiomics, and xenomicrobiomics—is gaining attention both in research environments and as a tool for personalized nutrition. Lifestyle information and tools include sensors for energy intake; prepared or portioned meal delivery; fitness testing and exercise training; challenge testing; metabolism (e.g., oral glucose tolerance tests and mixed macronutrient challenge tests); and other markers such as immune and gut microbiota.

AI models are used to guide microbiome-based dietary intervention and support obesity management. Researchers found global increases in AI-based personalized nutrition strategies and inclusion of machine learning approaches (Mundt et al. 2025). Challenges such as algorithmic bias, limited generalizability, and data privacy remain. AI can support individual and societal health goals by transforming nutrition science through predictive, adaptive, and ethically based approaches.

© Parradee Kietsirikul/iStock/Getty Images Plus

Precision Sports Nutrition

Endurance athletes, including triathletes, long-distance runners, cyclists, swimmers, rowers, and cross-country skiers, require tailored nutrition strategies to optimize performance, recovery, and training adaptations. Sports nutrition guidelines provide advice for different types of athletes, including endurance, strength, and sports that require low body weight. Optimizing sports performance requires a tailored nutrition plan that considers the athletes’ goals, needs, and physiological characteristics. Individual variability in metabolic responses to diet in athletes supports the need for precision nutrition informed by genetic, biological, and environmental factors.

In a scoping review evaluating the application of systems biology–driven sports nutrition for endurance athletes, researchers focused on “omics” and wearable technologies (Bedrac et al. 2024). They reviewed studies involving endurance athletes, systems biology approaches, and nutritional interventions or continuous glucose monitoring (CGM). Fifty-two studies were included, with distance runners as the most studied cohort. Eleven studies used metagenomics, 11 CGM, 10 nutrigenetics, 10 metabolomics, seven multi-omics, one proteomics, one epigenomics, and one lipidomics. Over half (n=31; 60%) were randomized controlled trials with generally high methodological quality. Most studies were proof-of-concept investigations aimed at assessing biomarkers.

The evidence linking novel biomarkers to performance, recovery, and long-term health outcomes in endurance athletes remains insufficient. The authors suggest that future research should focus on well-powered replicated crossover randomized controlled trials (RCTs), multivariate N-of-1 (N=1) clinical trials, 360-degree systems-wide approaches, and the validation of genetic impacts on nutritional interventions to refine dietary guidelines. However, this area is not well funded by government agencies, so it is unlikely that these aspirational goals for improvements in the research base will materialize.

Monitoring Metabolic Risk

Research is being conducted to determine whether precision and personalized nutrition interventions improve risk factors in adults with prediabetes or metabolic syndrome (MetS). Prediabetes is a metabolic state characterized by disruption in glucose regulation and insulin resistance. Blood glucose levels exceed the normal threshold but do not reach the diagnostic criteria for Type 2 diabetes. MetS is a cluster of metabolic abnormalities that include hypertension, central obesity, insulin resistance, and atherogenic dyslipidemia. The global prevalence of impaired fasting glucose is estimated at 10.6%, making it a critical public health challenge. The pathology for both conditions is complicated, with lifestyle risk factors including poor dietary habits, sedentary behavior, obesity, smoking, and inadequate sleep. If prediabetes is untreated, it is likely to progress to Type 2 diabetes and associated chronic diseases. If new precision nutrition tools could be used to intervene in the challenge, they would likely be covered by insurance and used in clinical care.

In a systematic review of six databases of RCTs published from January 2000 to April 2023, researchers examined existing literature on the efficacy of personalized or precision nutrition intervention (Robertson et al. 2024). The review considered medical nutrition therapy in improving outcomes related to glycemic control (e.g., hemoglobin A1C [HbA1c], post-prandial glucose [PPG], and fasting blood glucose); anthropometry (weight, body mass index, and waist circumference); blood lipids and pressure; and dietary intake among adults with prediabetes or MetS. Academy of Nutrition and Dietetics Quality Criteria were used to assess the risk of bias. Seven RCTs (n=873) comprising five precision nutrition interventions and two medical nutrition therapy interventions lasting 3–24 months were included.

Consistent and significant improvements were reported across studies that examined outcomes like HbA1c, PPG, and waist circumference. Results for other measures, including fasting blood glucose, Homeostatic Model Assessment for Insulin Resistance, blood lipids, blood pressure, and diet, were inconsistent. The study also showed that longer, more frequent interventions yielded greater improvements, especially for HbA1c and waist circumference. The authors concluded that more research using larger sample sizes and standardized personal nutrition factors is needed. Also, they indicated that future studies should investigate combining medical nutrition therapy with contemporary personal nutrition measures, including genetic, epigenetic, metabolomic, and metagenomic data.

Future Possibilities

New precision nutrition tools are bringing us closer to predicting individual responses to foods and enabling more personalized dietary guidance to help prevent chronic disease. New wearable technologies for glucose monitoring would suggest that we can link changes in blood glucose levels to disease prevention for prediabetes or MetS. And each new biomarker discovery offers hope and may open a promising frontier in diet-based disease prevention.

Advancing this field will require collaboration across disciplines—nutritionists, food scientists, biostatisticians, epidemiologists, data scientists, and public health experts. Nutrition involves many interacting variables, but our increasing ability to gather and integrate biomarkers is creating remarkable opportunities. Food scientists, in particular, are essential partners, bringing deep expertise in food that is foundational to precision nutrition’s future.ft