AI and IoT in Nutritional Science: Transforming Digestion Research and Precision Nutrition

Introduction

Gastrointestinal (GI) digestion is a vital biological process that breaks down food into essential nutrients, which the body absorbs and uses for energy, growth, and cellular repair. Digestion begins in the mouth with the breakdown of food, journeys through the stomach and intestines by way of digestive enzymes and fluids, and concludes in the small intestine, site of most nutrient absorption.

Digestion is the process that provides nutrient molecules into the cells; therefore, proper digestion is the very beginning step in sustaining our health. Conversely, digestive irregularities can lead to malnutrition, GI conditions, and other diseases. Healthcare providers and researchers need to have a deep understanding of this process. Advances in technology, particularly advances in Artificial Intelligence (AI) and the Internet of Things (IoT), are providing cutting-edge new insights into gastrointestinal digestion. These platforms are paving the way to transformative research and customized diets that can revolutionize public health and consumer behaviour.

In real-world applications, AI is increasingly being used to support dietitians in dietary planning, weight management, and malnutrition prediction. For instance, virtual nutrition assistants like chatbots have demonstrated up to 97% accuracy in diet-related queries and have shown potential in facilitating behavioral change in users.^1,2 AI-based tools are also being tested to assess nutritional knowledge, achieving more than 74% accuracy in simulating dietitian responses.³ This review aims to critically analyze the integration of AI and IoT in digestive health monitoring and personalized nutrition.

Discussion

Transforming nutritional research through AI and IoT

AI and IoT are reshaping the field of nutritional science by enhancing the precision, personalization, and efficiency of data collection, analysis, and application. These technologies are driving innovative approaches to better understand dietary habits and health outcomes.⁴

Artificial Intelligence (AI)

AI uses advanced technologies such as natural language processing, machine learning, and computer vision to imitate human-like intelligence.^5,6 In nutrition research, AI helps in processing a large amount of data to predict deficiencies in nutrients and customize dietary plans.⁷ Machine learning models can be used to incorporate the dietary data with information about any patient’s microbiome, genetics and lifestyle in order to customize the nutrition strategies that help promote optimal health.⁸

AI also provides insights into the complex relationships between diet, the gut microbiome, and metabolic health.⁹ In clinical settings and public health initiatives, these findings are proving to be extremely beneficial in the design of treatments that attempt to improve the nutritional outcomes of both people and communities.

Internet of Things (IoT)

With the use of IoT, smart devices can continuously monitor and transmit real-time data, enabling incredibly accurate tracking of metabolic responses, physical activity and eating habits. In case of nutrition, wearable fitness bands, biosensors, and smart kitchen appliances can be included as IoT devices.

These devices provide near-perfect dietary assessments. Studies have shown that fitness trackers that are worn on the wrist or leg can be used to monitor the physical activity and record various parameters including blood glucose levels, whereas smart kitchen gadgets help in tracking the consumption of food and reduce food wastage.¹⁰ Researchers and individuals alike are empowered by this constant flow of data to make better, faster decisions on their diet and well-being.¹¹

The synergy between AI and IoT

When AI and IoT are combined together, a powerful partnership is developed that helps in enhancing the nutritional science. This synergy can manage complex databases, process data in real time, and provide personalized dietary recommendations. Researchers benefit from advanced tools to analyze how diet impacts health, while individuals receive tailored guidance to manage their nutrition effectively. By leveraging these cutting-edge technologies, the future of nutritional science is poised for tremendous advancements not only in research capabilities but also in empowering individuals to make smarter, healthier dietary choices every day.

Figure 1: AI-powered insights into macronutrient digestion  Click here to view Figure

Predicting protein breakdown with Machine Learning

Protein hydrolysis plays a significant role in analysing the nutritional quality. Conventional methods used for studying hydrolysis of protein are often time-consuming and labor-intensive. Machine learning (ML) is developing this process by providing a quicker and more accurate prediction.

To produce accurate predictions, Machine Learning algorithms make use of datasets that include details like digestibility parameters, enzymatic conditions, and amino acid sequences. For example, decision tree algorithms and neural networks can mimic in vitro protein hydrolysis, greatly reducing the need for repeated trials.

Furthermore, the reactions of various protein sources, whether generated from plants or animals, may be examined by these models in relation to processing parameters such as heat or pH variations. In order to create customized formulations that satisfy certain dietary requirements, factors that either hinder or enhance the breakdown of proteins, such as anti-nutritional substances or additional additives, are additionally taken into account by advanced systems. Artificial Neural Networks (ANNs) have been extensively used in modeling non-linear nutritional datasets for food composition studies, such as classifying orange juice origin with over 92% accuracy and analyzing whey protein profiles in human vs. bovine milk.¹² AI has also been applied in bitterness prediction of peptides, micro-mineral profiling in vegetables, and evaluating nutrient retention during food processing using advanced ML algorithms like GA-RBFN, SVR, and LS-SVM. These approaches significantly reduce the time and cost of food analysis while increasing prediction precision.^13-16

This AI-driven approach saves time, resources and also enhances the customization of protein products to diverse needs, from athletes seeking quick amino acid absorption to individuals with digestive challenges.¹⁷ By combining these machine learning models with Internet of Things-enabled devices, further verification of results in practical contexts may be achieved, thereby facilitating the development of incredibly precise and customized dietary solutions.

AI in monitoring carbohydrate digestion and glycemic responses

During digestion, complex carbohydrates must be broken down into simple sugars, which has an immediate effect on blood glucose levels. Observing the glycemic responses is significant for people trying to manage diabetes and other metabolic disorders. AI can be used to predict the pattern of change in blood sugar level after meals, by analyzing the information from continuous glucose monitors (CGMs).¹⁸

AI helps in assessing the glycemic index of various foods, detect abnormalities and recommend dietary adjustments, by analysing the fluctuations in blood sugar.¹⁹ Additionally, the differentiation between quickly digestible starches and slower-digesting polysaccharides can be achieved by machine learning models, aiding in the development of low-glycemic food options. The digestion of lipids is recognized as a multifaceted process that involves emulsification, enzymatic breakdown by lipases and the absorption of fatty acids and glycerol.

Studies include image-recognition systems powered by AI, in which users upload meal photos for analysis. These tools determine the carbohydrate content and analyse the glycemic impact depending upon the portion size and carbohydrate content.^20,21 AI-powered Image-Based Food Recognition Systems (IBFRS) automate food-intake monitoring and convert photographic observations into nutrient estimates, improving accuracy over conventional recording methods.²² In this study, deep learning models such as Convolutional Neural Networks (CNNs) were used to classify food items from images and their nutrient values were evaluated.²³ IBFRS could estimate the glycemic index (GI) of meals, helping in personalized dietary recommendations. However, errors in portion estimation and the complexity of mixed ingredients are challenges that necessitate further modifications to AI algorithms.²⁴

AI methods such as machine learning and deep learning are also replacing traditional dietary recall methods. In one study, an AI app called COCO Nutritionist showed nutrient estimation almost equivalent to the gold-standard 24-hour recall, with macronutrient predictions within ±1% accuracy.²⁵ Similarly, large datasets like NHANES were used in ML models to predict cardiovascular risk using nutrient intake data, with AUROC values as high as 0.82, indicating high prediction accuracy.²⁶

Deep learning advancing lipid digestion research

Traditional methods of studying lipid digestion have relied heavily on in vitro models or animal trials, which struggle to fully mimic human physiology. The game is now being changed by deep learning through the use of datasets on lipid structure, emulsification properties and enzyme activity to simulate digestion processes. These advancements are not only refining drug delivery systems that are reliant on lipids but are also helping to fortify foods with essential fatty acids, ultimately leading to improvements in dietary recommendations for better health outcomes.²⁷

One major application is predicting how innovative lipid formulations such as structured lipids will behave during digestion. Tools such as CNNs and Long Short-Term Memory (LSTM) networks have been used to interpret electrogastrogram (EGG) signals. These non-invasive signals provide valuable insights into gut motility during lipid digestion.²⁸

Deep learning has a significant role in advancing lipid digestion research, especially in understanding the metabolic dysfunction associated fatty liver disease (MAFLD). Researches have shown how machine learning in association with lipidomics help in identifying biomarkers that cause progression of MAFLD. These deep learning models can analyze vast data of lipidomics to decode the pattern, classify the lipid profiles, which are not that effective through conventional methods. Furthermore, deep learning enhances the integration of multi-omics data, refining metabolic pathway analysis and providing a deeper understanding of lipid-mediated mechanisms in liver disease.²⁹ These advancements are not only refining drug delivery systems that rely on lipids but also helping to fortify foods with essential fatty acids, ultimately improving dietary recommendations for better health outcomes.³⁰ Deep learning approaches like CNNs are revolutionizing dietary assessments by enabling image-based macronutrient and portion size estimation, significantly outperforming hospital staff in malnutrition prediction. One AI tool demonstrated <15% error in macronutrient prediction compared to >30% by nurses.³¹

ANN models have been employed in optimizing production of bioactive nutrients like retinyl laurate, phycobiliproteins, and benzoquinones—compounds with anti-tumor and immunomodulatory potential. These models, sometimes combined with evolutionary techniques like genetic algorithms (GA) or fuzzy logic methodologies (FLM), enable complex nonlinear optimization for nutrient synthesis.³² This demonstrates how AI tools are not only analytical but also play a functional role in nutrient formulation.^33-35 

Real-time monitoring of digestion using IoT devices

Smart sensors for tracking gastrointestinal pH and enzyme activity

The gastrointestinal (GI) tract is a highly dynamic environment where fluctuations in pH levels and enzyme activity play a critical role in digestion and nutrient absorption. To better understand these processes, researchers have developed ingestible capsules equipped with smart sensors. These tiny devices are fitted with pH sensors, enzyme activity detectors, and wireless transmitters. Once swallowed, they travel through the digestive system, continuously transmitting data about pH levels and enzymatic activity at different stages of digestion.

Researchers explored a novel autonomous ingestible smart biosensing system in pill format designed for real-time monitoring of gastrointestinal (GI) pH levels. These pH levels are correlated with gastrointestinal disorders such as inflammatory bowel disease (IBD), ulcerative colitis, and pancreatitis. A smart sensing pill integrated with pH sensors based on PANI – electrodeposited polyaniline on carbon-coated conductive threads was developed, which offered a high sensitivity in detecting change in pH level as it passes through the GI tract. With the dimensions of 22.1 mm in length and 9 mm in diameter, the smart pill was designed for efficient in vivo operation.^36-38

Recent advancements in biosensing technology have facilitated the real-time assessment of biochemical markers in the gastrointestinal (GI) tract, providing critical insights into how diet composition influences digestive processes and gut health. A study utilizing Ion Selective Electrodes (ISEs) demonstrated the direct sensing of ammonium ions in gastrointestinal digesta samples, establishing a correlation between dietary protein digestibility and protein fermentation in the gut. By modulating the protein quality in pig diets, researchers observed a significant increase in ammonium ion concentration increasing from 180 ppm to 400 ppm in the proximal colon when consuming poorly digestible proteins, compared to diets based on easily digestible proteins. These findings highlight the impact of dietary composition on gut microbiota activity and metabolic byproducts, reinforcing the role of nutrition in digestive health. Moreover, the use of potentiometric sensors for in vivo-like detection of ammonium ions represents a promising approach for non-invasive gut analysis. When integrated with AI-powered platforms, such biosensing data can be analyzed in real-time, enabling advanced pattern recognition and predictive modeling to explore the relationship between dietary habits, enzymatic activity, and gut-brain axis interactions. This AI-driven approach enhances the potential for personalized dietary recommendations and targeted treatments for digestive disorders by identifying trends and metabolic responses specific to individual gut microbiomes.^39-44 

Wearable devices for monitoring glucose levels and analyzing dietary intake

Wearable technology, such as continuous glucose monitors (CGMs), has become an invaluable tool for people with diabetes, allowing them to keep track of their blood sugar levels in real time. These IoT-enabled devices synchronize with mobile applications, giving users instant insights into how their meals affect their glycemic response. By analyzing these patterns, advanced AI systems can suggest dietary adjustments customized to the individual’s needs.^45,46

Beyond glucose tracking, researchers are integrating additional dietary analysis features into wearable devices. Wearable technology is advancing beyond glucose tracking by integrating dietary analysis features, linking food intake with real-time metabolic responses. A study using continuous glucose monitoring (CGM) and wearables tracked 2,217 participants’ glucose levels, diet, and activity, providing personalized insights via a smartphone app. By overlaying glucose fluctuations with meal data, macronutrient breakdown, and glycemic index (GI), the system enabled tailored lifestyle recommendations. This aligns with emerging food recognition apps, which estimate calorie and nutrient intake, helping users understand how diet impacts glucose stability. Such AI-driven solutions promote personalized nutrition, metabolic health improvement, and Type 2 Diabetes prevention.^47-49

The future of these technologies lies in multi-sensor platforms that monitor not just glucose levels, but also parameters like heart rate, physical activity, and gut motility, giving a more comprehensive view of metabolic health. 

Advanced techniques in nutrient digestion research with IoT

The integration of IoT technology in nutrient digestion research has significantly enhanced the study of digestive processes by enabling real-time data collection and analysis. Ingestible capsules and smart sensors track key parameters such as pH levels, temperature, pressure, and nutrient concentrations within the gastrointestinal (GI) tract, providing researchers with valuable insights into nutrient release patterns and the influence of food composition, portion sizes, and digestive health. These devices also aid in diagnosing digestive disorders like gastroparesis and small intestinal bacterial overgrowth (SIBO), contributing to more personalized dietary and therapeutic solutions.⁵⁰ Additionally, IoT-enhanced in vitro digestion models allow for precise control and monitoring of experimental conditions, facilitating high-throughput studies on nutrient bioaccessibility and food matrix effects. Automated bioreactors equipped with IoT sensors help simulate real-life digestive conditions, improving food formulation and nutrient delivery through AI-based predictive models. Furthermore, IoT-driven real-time data collection, using wearable devices and ingestible sensors, enhances nutritional research by offering objective insights into eating habits, digestive health, and metabolic responses.⁵¹ This eliminates the inaccuracies of self-reported food diaries and enables more precise, personalized dietary recommendations, transforming the field of nutrition science. 

Future directions – merging AI, IoT, and nutritional science

The integration of AI and IoT into nutritional science is revolutionizing how dietary data is gathered, analyzed, and applied, paving the way for more precise and personalized health solutions.⁵² AI-driven precision nutrition tailors dietary recommendations based on an individual’s genetic makeup, metabolism, and microbiome, optimizing health outcomes through targeted interventions. IoT devices, including fitness trackers and smart kitchen appliances, facilitate real-time dietary monitoring, offering continuous insights into eating habits and lifestyle choices. Predictive analytics powered by AI further enhances nutrition science by forecasting health outcomes and enabling early interventions. Innovations in food science, such as AI-powered automated nutritional analysis and IoT-enabled smart packaging, improve dietary tracking, food safety, and waste reduction.^53-57 AI and IoT also optimize food production by monitoring environmental factors to enhance crop yields and food quality.^58-60 The evolution of AI-driven systems may soon lead to the development of global nutritional monitoring networks that adapt to regional dietary habits and gut microbiota profiles. Certain platforms could personalize nutrient recommendations in real time and bridge biomedical, clinical, and epidemiological data through interconnected systems.⁶¹ However, challenges remain, including data privacy concerns, integration issues across multiple platforms, and ethical considerations related to algorithmic biases and transparency. Despite these hurdles, the future holds exciting opportunities, from highly personalized nutrition plans and improved public health initiatives to the development of innovative food products tailored to specific health needs and consumer preferences.⁶² Several other applications of AI in nutritional sciences is detailed in Table 1.

Table 1: Applications of AI in nutritional sciences

AI driven dietary platforms in precision nutrition

Several AI-driven dietary platforms are emerging as practical applications of computational nutrition science. Viome employs metatranscriptomic sequencing to capture active microbial pathways within the gut microbiome, thereby enabling highly personalized dietary recommendations that target host–microbe interactions and metabolic health.⁷² PhyteByte, a machine learning based computational tool, predicts the bioactivity of food-derived compounds by leveraging pharmacological datasets such as ChEMBL and linking predicted compounds to food sources through FooDB. This supports the identification of nutritionally relevant bioactives with drug-like effects for use in precision diets and nutraceutical development.⁷³ In parallel, goFOOD™ provides an AI-powered smartphone application that incorporates deep learning for food recognition, segmentation, and three-dimensional volume estimation to assess caloric and macronutrient intake from images or videos, with demonstrated accuracy across more than 300 food categories and clinical usability for dietary monitoring.⁷⁴ Collectively, these platforms illustrate how AI and IoT-enabled solutions are transitioning from theoretical models into actionable tools that advance personalized nutrition and real-time dietary assessment.

Ethical concerns in AI and IoT applications

The integration of AI and IoT in nutritional science raises critical ethical concerns, particularly regarding data privacy, algorithmic bias, and informed consent. Devices such as wearable trackers and ingestible sensors collect sensitive physiological and behavioral data, necessitating stringent data governance frameworks to protect user confidentiality. Additionally, AI models trained on non-representative datasets may produce biased dietary recommendations, potentially disadvantaging certain populations. Although chatbots and AI diet planners are accessible tools, users often misinterpret their recommendations. Studies have shown that AI systems occasionally failed to detect allergens or provide warnings for unbalanced meals, raising concerns about patient safety and misinformation.⁷⁵ Ensuring transparency in algorithm design, securing user consent for data use, and fostering equitable access to AI-driven nutrition technologies are essential steps to uphold ethical standards in this rapidly evolving field.⁷⁶ 

Conclusion

The integration of artificial intelligence (AI) and the Internet of Things (IoT) in nutritional science is reshaping how dietary data is monitored, analyzed, and applied in both clinical and consumer contexts. Numerous studies reviewed in this article demonstrate how AI models such as convolutional neural networks (CNNs), long short-term memory (LSTM) models, and ensemble machine learning algorithms have been effectively applied to predict postprandial glycemic responses, analyze macronutrient intake with over 90% accuracy, and personalize diet recommendations using real-time biosensor inputs. For instance, AI-driven dietary platforms like Viome, PhyteByte, and goFOOD™ have shown promising outcomes in tailoring nutrient intake and predicting metabolic responses based on individual gut microbiota, genetic profiles, or continuous glucose monitoring (CGM) data.

Viome works on the meta-transcriptomic analysis of gut microbiota in combination with AI models to provide personalized nutrition strategies. PhyteByte applies machine learning to identify bioactive compounds in foods with pharmacological potential, bridging the gap between food chemistry and individualized health outcomes. goFOOD™ is an AI-powered mobile app that enables real-time dietary assessment. These examples illustrate how commercial and research-driven tools are advancing precision nutrition by tailoring dietary recommendations.

Parallel advancements in IoT including ingestible sensors, wearable trackers, and smart kitchen systems have enabled continuous, real-time monitoring of digestion-related biomarkers such as pH, ammonia, and CO₂ levels. These devices contribute to a more granular understanding of nutrient bioaccessibility and gastrointestinal function under real-life conditions.

However, across many studies, limitations persist. Common biases include over-reliance on small, homogeneous datasets, lack of longitudinal validation, and insufficient representation of diverse population groups. Furthermore, integration across platforms remains technically challenging, and ethical concerns regarding data privacy and algorithmic transparency are not yet fully addressed.

Despite these challenges, the convergence of AI and IoT holds significant promise for the future of precision nutrition. This review highlights the growing body of evidence supporting their use in disease prevention, individualized dietary planning, and metabolic optimization. As interdisciplinary technologies mature and data governance frameworks evolve, these innovations are expected to deliver more accurate, culturally inclusive, and clinically actionable nutrition solutions on a global scale.

Acknowledgement

The authors would like to express their gratitude to Saintgits College of Engineering and Anna University for their support in facilitating this research. Special thanks to colleagues and researchers who provided valuable insights and technical assistance.

Funding Sources

The author(s) received no financial support for the research, authorship, and/or publication of this article.

Conflict of Interest

The authors do not have any conflict of interest.

Data Availability Statement

This statement does not apply to this article.

Ethics Statement

This research did not involve human participants, animal subjects, or any material that requires ethical approval.

Informed Consent Statement

This study did not involve human participants, and therefore, informed consent was not required.

Clinical Trial Registration

This research does not involve any clinical trials.

Permission to Reproduce Material from Other Sources

Not applicable

Author Contributions

• Poojitha Pushparaj – conceptualized the study, designed the research framework, and supervised the overall project execution.
• Lakshmi Mohan – contributed to the literature review and data analysis related to AI-driven nutritional research.
• Anju Kanicheril Ambikalekshmi – responsible for collecting and analyzing data on IoT applications in digestion monitoring.
• Elsa Cherian – assisted in drafting the manuscript and compiling references.
• Rosamma Rajan – contributed to experimental design and interpretation of findings in nutritional science.
• Nandha Kumar – provided technical expertise in machine learning models and statistical validation. All authors reviewed and approved the final manuscript. 

References

1. Davis CR, Murphy KJ, Curtis RG, et al. A process evaluation examining the performance, adherence, and acceptability of a physical activity and diet artificial intelligence virtual health assistant. Int J Environ Res Public Health. 2020;17(24):9137.
   CrossRef
2. Maher CA, Davis CR, Curtis RG, et al. A physical activity and diet program delivered by artificially intelligent virtual health coach: Proof-of-concept study. JMIR Mhealth Uhealth. 2020;8(7):e17558.
   CrossRef
3. Beyeler M, Légeret C, Kiwitz F, et al. Usability and overall perception of a health bot for nutrition-related questions for patients receiving bariatric care: Mixed methods study. JMIR Hum Factors. 2023;10:e47913.
   CrossRef
4. Hsu MH, Huang LC, Chen TM, et al. A web-based decision support system for dietary analysis and recommendations. Telemed E Health. 2011;17(1):68-75.
   CrossRef
5. Mascarenhas M. Artificial intelligence and capsule endoscopy: Unraveling the future. Ann Gastroenterol. 2021;34(3):300-309.
   CrossRef
6. Nilsson NJ. The Quest for Artificial Intelligence. Cambridge University Press; 2013. doi:10.1017/CBO9780511819346. ISBN: 9780511819346.
   CrossRef
7. Kim SH, Lim YJ. Artificial intelligence in capsule endoscopy: A practical guide to its past and future challenges. Diagnostics (Basel). 2021;11(10):1722.
   CrossRef
8. Erickson BJ, Korfiatis P, Akkus Z, et al. Machine learning for medical imaging. 2017;37(2):505-515.
   CrossRef
9. Buisson JC. Nutri-Educ, a nutrition software application for balancing meals, using fuzzy arithmetic and heuristic search algorithms. Artif Intell Med. 2008;42(3):213-227.
   CrossRef
10. More S, Shelar S, Randhave V, et al. IoT-based smart kitchen system. Int J Sci Res Sci Eng Technol. 2021;8(3):479-485. doi:10.32628/IJSRSET2183198
    CrossRef
11. Dakhia Z, Russo M, Merenda M. AI-enabled IoT for food computing: Challenges, opportunities, and future directions. Sensors (Basel). 2025;25(7):2147. doi:10.3390/s25072147.
    CrossRef
12. Dettmar H, Barbour G, Blackwell KT, et al. Orange juice classification with a biologically based neural network. Computers & Chemistry. 1996;20:261–266.
    CrossRef
13. Rasouli Z, Hassanzadeh Z, Ghavami R. Application of a new version of GA-RBF neural network for simultaneous spectrophotometric determination of Zn(II), Fe(II), Co(II) and Cu(II) in real samples: An exploratory study of their complexation abilities toward MTB. 2016;160:86–98.
    CrossRef
14. Soltani S, Haghaei H, Shayanfar A, et al. QSBR study of bitter taste of peptides: Application of GA-PLS in combination with MLR, SVM, and ANN approaches. Biomed Res Int. 2013;2013:501310.
    CrossRef
15. Shen T, Li W, Zhang X, et al. High-sensitivity determination of nutrient elements in Panax notoginseng by laser-induced breakdown spectroscopy and chemometric methods. 2019;24:1525.
    CrossRef
16. Puce L, Ceylan Hİ, Trompetto C, et al. Optimizing athletic performance through advanced nutrition strategies: Can AI and digital platforms have a role in ultraendurance sports? Biol Sport. 2024;41(4):305–313. doi:10.5114/biolsport.2024.141063
    CrossRef
17. Guan Z, Li H, Liu R, et al. Artificial intelligence in diabetes management: Advancements, opportunities, and challenges. Cell Rep Med. 2023;4(10):101213. doi:10.1016/j.xcrm.2023.101213
    CrossRef
18. Klonoff AN, Lee WAA, Xu NY, et al. Six digital health technologies that will transform diabetes. J Diabetes Sci Technol. 2023;17:239–249. doi:10.1177/19322968211043498
    CrossRef
19. Boushey CJ, Spoden M, Zhu FM, et al. New mobile methods for dietary assessment: Review of image-assisted and image-based dietary assessment methods. Proc Nutr Soc. 2017;76(3):283–294.
    CrossRef
20. Sak J, Suchodolska M. Artificial intelligence in nutrients science research: A review. 2021;13(2):322. doi:10.3390/nu13020322
    CrossRef
21. Dettmar H, Barbour G, Blackwell KT, et al. Orange juice classification with a biologically based neural network. Computers & Chemistry. 1996;20(3):261-266.
    CrossRef
22. Rasouli Z, Hassanzadeh Z, Ghavami R. Application of a new version of GA-RBF neural network for simultaneous spectrophotometric determination of Zn(II), Fe(II), Co(II), and Cu(II) in real samples: An exploratory study of their complexation abilities toward MTB. 2016;160:86-98.
    CrossRef
23. Soltani S, Haghaei H, Shayanfar A, et al. QSBR study of bitter taste of peptides: Application of GA-PLS in combination with MLR, SVM, and ANN approaches. Biomed Res Int. 2013;2013:501310.
    CrossRef
24. Shen T, Li W, Zhang X, et al. High-sensitivity determination of nutrient elements in Panax notoginseng by laser-induced breakdown spectroscopy and chemometric methods. 2019;24(8):1525.
    CrossRef
25. Puce L, Ceylan Hİ, Trompetto C, et al. Optimizing athletic performance through advanced nutrition strategies: Can AI and digital platforms have a role in ultraendurance sports? Biol Sport. 2024;41(4):305–313. doi:10.5114/biolsport.2024.141063
    CrossRef
26. Guan Z, Li H, Liu R, et al. Artificial intelligence in diabetes management: Advancements, opportunities, and challenges. Cell Rep Med. 2023;4(10):101213. doi:10.1016/j.xcrm.2023.101213
    CrossRef
27. Klonoff AN, Lee WAA, Xu NY, et al. Six digital health technologies that will transform diabetes. J Diabetes Sci Technol. 2023;17:239–249. doi:10.1177/19322968211043498
    CrossRef
28. Boushey CJ, Spoden M, Zhu FM, et al. New mobile methods for dietary assessment: Review of image-assisted and image-based dietary assessment methods. Proc Nutr Soc. 2017;76(3):283–294.
    CrossRef
29. Papathanail I, Bruhlmann J, Vasiloglou MF, et al. Evaluation of a novel artificial intelligence system to monitor and assess energy and macronutrient intake in hospitalised older patients. 2021;13(12):4539.
    CrossRef
30. Sosa-Holwerda A, Park OH, Albracht-Schulte K, et al. The role of artificial intelligence in nutrition research: A scoping review. 2024;16(13):2066. doi:10.3390/nu16132066
    CrossRef
31. Huang SM, Li HJ, Liu YC, et al. An efficient approach for lipase-catalyzed synthesis of retinyl laurate nutraceutical by combining ultrasound assistance and artificial neural network optimization. 2017;22(11):1972.
    CrossRef
32. Zheng J, Wang Z, Zhu C. Food image recognition via superpixel-based low-level and mid-level distance coding for smart home applications. 2017;9(5):856.
    CrossRef
33. Kumar Saini D, Yadav D, Pabbi S, et al. Phycobiliproteins from Anabaena variabilis CCC421 and its production enhancement strategies using combinatory evolutionary algorithm approach. Bioresour Technol. 2020;309:123347.
    CrossRef
34. Asci C, Sharma A, Del-Rio-Ruiz R, et al. Ingestible pH sensing device for gastrointestinal health monitoring based on thread-based electrochemical sensors. Mikrochim Acta. 2023;190(10):385. doi:10.1007/s00604-023-05946-1
    CrossRef
35. Devika NT, Raman K. Deciphering the metabolic capabilities of Bifidobacteria using genome-scale metabolic models. Sci Rep. 2019;9:18222.
    CrossRef
36. Mohammed A, Guda C. Application of a hierarchical enzyme classification method reveals the role of gut microbiome in human metabolism. BMC Genomics. 2015;16(Suppl 7):S16.
    CrossRef
37. Leonardi F, Sijabat R, Minderhoud R, et al. Sensing the impact of diet composition on protein fermentation by direct electrochemical NH₄⁺ sensing in gastrointestinal digesta. Biosens Bioelectron X. 2023;15:100406. doi:10.1016/j.biosx.2023.100406
    CrossRef
38. Sharma A, Podoplelova E, Shapovalov G, et al. Sustainable smart cities: Convergence of artificial intelligence and blockchain. 2021;13(24):13076.
    CrossRef
39. Addanki M, Patra P, Kandra P. Recent advances and applications of artificial intelligence and related technologies in the food industry. Appl Food Res. 2022;2:100126.
    CrossRef
40. Singh R, Khan S, Dsilva J, et al. Blockchain integrated IoT for food supply chain: A grey-based Delphi-DEMATEL approach. Appl Sci (Basel). 2023;13(2):1079.
    CrossRef
41. Raza F. AI for Predictive Maintenance in Industrial Systems. Cosmic Publications; 2023.
42. AlZubi AA, Kalda G. Artificial intelligence and internet of things for sustainable farming and smart agriculture. IEEE Access. 2023;11:78686–78692.
    CrossRef
43. Westerman KE, Harrington S, Ordovás JM, et al. PhyteByte: Identification of foods containing compounds with specific pharmacological properties. BMC Bioinformatics. 2020;21:238.
    CrossRef
44. Shamanna P, Saboo B, Damodharan S, et al. Reducing HbA1c in type 2 diabetes using digital twin technology–enabled precision nutrition: A retrospective analysis. Diabetes Ther. 2020;11:2703–2714.
    CrossRef
45. Zahedani AD, McLaughlin T, Veluvali A, et al. Digital health application integrating wearable data and behavioral patterns improves metabolic health. NPJ Digit Med. 2023;6(1):216. doi:10.1038/s41746-023-00956-y
    CrossRef
46. Tily H, Patridge E, Cai Y, et al. Gut microbiome activity contributes to prediction of individual variation in glycemic response in adults. Diabetes Ther. 2022;13:89–111.
    CrossRef
47. Bul K, Holliday N, Bhuiyan MRA, et al. Usability and preliminary efficacy of an artificial intelligence–driven platform supporting dietary management in diabetes: Mixed methods study. JMIR Hum Factors. 2023;10:e43959.
    CrossRef
48. Thwaites PA, Yao CK, Halmos EP, et al. Review article: Current status and future directions of ingestible electronic devices in gastroenterology. Aliment Pharmacol Ther. 2024;59(4):459–474. doi:10.1111/apt.17844
    CrossRef
49. Holt BM, Stine JM, Beardslee LA, et al. An ingestible bioimpedance sensing device for wireless monitoring of epithelial barriers. Microsyst Nanoeng. 2025;11:24. doi:10.1038/s41378-025-00877-8
    CrossRef
50. Papastratis I, Konstantinidis D, Daras P, et al. AI nutrition recommendation using a deep generative model and ChatGPT. Sci Rep. 2024;14:14620. doi:10.1038/s41598-024-65438-x
    CrossRef
51. Kan J, Li A, Zou H, et al. A machine learning–based dose prediction of lutein supplements for individuals with eye fatigue. Front Nutr. 2020;7:577923.
    CrossRef
52. Vilas-Boas JL, Rodrigues JJPC, Alberti AM. Convergence of distributed ledger technologies with digital twins, IoT, and AI for fresh food logistics: Challenges and opportunities. J Ind Inf Integr. 2023;31:100393.
    CrossRef
53. Bourechak A, Zedadra O, Kouahla MN, et al. At the confluence of artificial intelligence and edge computing in IoT-based applications: A review and new perspectives. Sensors (Basel). 2022;23:1639.
    CrossRef
54. Liu Z, Zhang M. Overcoming data interoperability challenges in food supply chains using IoT and AI. J Food Sci Technol. 2021;12:130–145.
55. Pigsborg K, Stentoft-Larsen V, Demharter S, et al. Predicting weight loss success on a new Nordic diet: An untargeted multi-platform metabolomics and machine learning approach. Front Nutr. 2023;10:1191944.
    CrossRef
56. Ding H, Tian J, Yu W, et al. The application of artificial intelligence and big data in the food industry. 2023;12(24):4511. doi:10.3390/foods12244511
    CrossRef
57. Liu Z, Wang S, Zhang Y, et al. Artificial intelligence in food safety: A decade review and bibliometric analysis. 2023;12(6):1242. doi:10.3390/foods12061242
    CrossRef
58. Kassem H, Beevi AA, Basheer S, et al. Investigation and assessment of AI’s role in nutrition—An updated narrative review of the evidence. 2025;17(1):190.
    CrossRef
59. Mitchell EG, Tabak EG, Levine ME, et al. Enabling personalized decision support with patient-generated data and attributable components. J Biomed Inform. 2021;113:103639.
    CrossRef
60. Detopoulou P, Voulgaridou G, Moschos P, et al. Artificial intelligence, nutrition, and ethical issues: A mini-review. Clin Nutr Open Sci. 2023;50:46–56.
    CrossRef
61. Fukuzawa F, Yanagita Y, Yokokawa D, et al. Importance of patient history in artificial intelligence–assisted medical diagnosis: Comparison study. JMIR Med Educ. 2024;10:e52674.
    CrossRef
62. Sarker IH. Machine learning: Algorithms, real-world applications and research directions. SN Comput Sci. 2021;2:160.
    CrossRef
63. Emmanuel WRS, Minija SJ. Fuzzy clustering and whale-based neural network for food recognition and calorie estimation in daily dietary assessment. Sādhanā. 2018;43(5). doi:10.1007/s12046-018-0865-3.
    CrossRef
64. Lu Y, Stathopoulou T, Vasiloglou MF, et al. goFOOD™: An artificial intelligence system for dietary assessment. 2020;20(15):4283.
    CrossRef
65. Situju SF, Takimoto H, Sato S, et al. Food constituent estimation for lifestyle disease prevention by multi-task CNN. Appl Artif Intell. 2019;33(8):732–746.
    CrossRef
66. Everloo E, Savion O. Bytes to bites part one: Digitizing consumption insights—Leveraging AI in food product development. AgFunder News. September 2023.
67. Minija SJ, Emmanuel WRS. Food recognition using neural network classifier and multiple hypotheses image segmentation. Imaging Sci J. 2020;68(2):100-113.
    CrossRef
68. Limketkai BN, Mauldin K, Manitius N, et al. The age of artificial intelligence: Use of digital technology in clinical nutrition. Curr Surg Rep. 2021;9(7):20.
    CrossRef
69. Ptomey LT, Willis EA, Goetz JR, et al. Digital photography improves estimates of dietary intake in adolescents with intellectual and developmental disabilities. Disabil Health J. 2015;8(1):146–150.
    CrossRef
70. Reusch A, Weber A, Thiele M, et al. RecipeGM: A hierarchical recipe generation model. In: Proceedings of the 2021 IEEE 37th International Conference on Data Engineering Workshops (ICDEW). Chania, Greece; 2021:24–29.
    CrossRef
71. Liang S, Gu Y. Multi-stage convolutional neural network framework for food recognition with boundary-aware module and deformable ROI pooling. J Food Recognit. 2024;1(1):1-10.
72. Hatch A, Horne J, Toma R, et al. A robust metatranscriptomic technology for population-scale studies of diet, gut microbiome, and human health. Int J Genomics. 2019;2019:1718741. doi:10.1155/2019/1718741
    CrossRef
73. Westerman KE, Harrington S, Ordovás JM, et al. PhyteByte: Identification of foods containing compounds with specific pharmacological properties. BMC Bioinformatics. 2020;21:238. doi:10.1186/s12859-020-03582-7
    CrossRef
74. Lu Y, Stathopoulou T, Vasiloglou MF, et al. goFOOD™: An artificial intelligence system for dietary assessment. Sensors (Basel). 2020;20(15):4283. doi:10.3390/s20154283.
    CrossRef
75. Pouladzadeh P, Shirmohammadi S, Arici T. Intelligent SVM-based food intake measurement system. In: Proceedings of the 2013 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA). Milan, Italy; 2013:1–6.
    CrossRef
76. Liao H, Lim Z, Lin H. Food intake estimation method using short-range depth camera. In: Proceedings of the IEEE International Conference on Signal and Image Processing (ICSIP). Beijing, China; 2016:243–247.
    CrossRef

Abbreviations List

AI – Artificial Intelligence

CGMs – Continuous Glucose Monitors

CNNs – Convolutional Neural Networks

EGG – Electrogastrogram

GI – Gastrointestinal

IBFRS – Image-based Food Recognition Systems

ISEs – Ion Selective Electrodes (ISEs)

IoT – Internet of Things

LSTM – Long Short-Term Memory

MAFLD – Metabolic Dysfunction Associated Fatty Liver Disease

ML – Machine Learning

PANI – Pill integrated pH sensors Electrodeposited Polyaniline

SIBO – Small Intestinal Bacterial Overgrowth