{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T16:09:26Z","timestamp":1791216566691,"version":"4.1.0"},"reference-count":26,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:00:00Z","timestamp":1758672000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Nutrients"],"abstract":"<jats:p>Background\/Objectives: As convenience store meals become a major dietary source for modern society, the reliability of their nutrition labels is increasingly scrutinized. With advances in artificial intelligence (AI), large language models (LLMs) have been explored for automated nutrition estimation. Aim: To evaluate the accuracy and clinical applicability of AI-assessed nutrition data by comparing outputs from five AI models with professional dietitian estimations and labeled nutrition facts. Methods: Eight ready-to-eat convenience store meals were analyzed. Four experienced dietitians independently estimated the meals\u2019 calories, macronutrients, and sodium content based on measured food weights. Five AI chatbots were queried multiple times with identical input prompts to assess intra- and inter-assay variability. All results were compared to the official nutrition labels to quantify discrepancies and cross-model consistency. Results: Dietitian estimations showed strong internal consistency (CV &lt; 15%), except for fat, saturated fat and sodium (CVs up to 33.3 \u00b1 37.6%, 24.5 \u00b1 11.7%, and 40.2 \u00b1 30.3%, respectively). Among AI models, ChatGPT4.o showed relatively consistent calory, protein, fat, saturated fat and carbohydrate estimates (CV &lt; 15%), and Claude3.7, Grok3, Gemini, and Copilot showed caloric and protein content as consistent (CV &lt; 15%). Sodium values were consistently underestimated across all AI models, with CVs ranging from 20% to 70%. The accuracy of nutritional fact estimation over the five AI models for calories, protein, fat, saturated fat and carbohydrates was between 70 and 90%; when compared to the nutritional labels of RTE, the sodium content and saturated fat estimated were severely underestimated. Conclusions: Current AI chat models provide rapid estimates for basic nutrients and can aid public education or preliminary assessment; GPT-4 outperforms peers in calorie and potassium-related estimations but remains suboptimal in micronutrient prediction. Professional dietitian oversight remains essential for safe and personalized dietary planning.<\/jats:p>","DOI":"10.3390\/nu17193044","type":"journal-article","created":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T10:39:42Z","timestamp":1758710382000},"page":"3044","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Comparison of Accuracy in the Evaluation of Nutritional Labels on Commercial Ready-to-Eat Meal Boxes Between Professional Nutritionists and Chatbots"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0562-8310","authenticated-orcid":false,"given":"Chin-Feng","family":"Hsuan","sequence":"first","affiliation":[{"name":"Division of Cardiology, Department of Internal Medicine, E-Da Hospital, I-Shou University, Kaohsiung 82445, Taiwan"},{"name":"School of Medicine, College of Medicine, I-Shou University, Kaohsiung 82445, Taiwan"},{"name":"Division of Cardiology, Department of Internal Medicine, E-Da Dachang Hospital, I-Shou University, Kaohsiung 807066, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yau-Jiunn","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Lee\u2019s Clinic, 130 Min-Zu Rd, Pingtung 90000, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5154-3916","authenticated-orcid":false,"given":"Hui-Chun","family":"Hsu","sequence":"additional","affiliation":[{"name":"Department of Nursing, Lee\u2019s Clinic, 130 Min-Zu Rd, Pingtung 90000, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chung-Mei","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Department of Clinical Nutrition, Lee\u2019s Clinic, 130 Min-Zu Rd, Pingtung 90000, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Chin","family":"Yeh","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Internal Medicine, Ministry of Health and Welfare Yuli Hospital, Hualien 98142, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3338-9505","authenticated-orcid":false,"given":"Wei-Hua","family":"Tang","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Internal Medicine, Ministry of Health and Welfare Yuli Hospital, Hualien 98142, Taiwan"},{"name":"Faculty of Medicine, School of Medicine, National Yang Ming Chiao Tung University, Taipei 112304, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Hoang, Y.N., Chen, Y.L., Ho, D.K.N., Chiu, W.C., Cheah, K.J., Mayasari, N.R., and Chang, J.S. (2023). Consistency and Accuracy of Artificial Intelligence for Providing Nutritional Information. JAMA Netw. Open, 6.","DOI":"10.1001\/jamanetworkopen.2023.50367"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Haman, M., Skolnik, M., and Lostak, M. (2024). AI dietician: Unveiling the accuracy of ChatGPT's nutritional estimations. Nutrition, 119.","DOI":"10.1016\/j.nut.2023.112325"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ponzo, V., Rosato, R., Scigliano, M.C., Onida, M., Cossai, S., De Vecchi, M., Devecchi, A., Goitre, I., Favaro, E., and Merlo, F.D. (2024). Comparison of the Accuracy, Completeness, Reproducibility, and Consistency of Different AI Chatbots in Providing Nutritional Advice: An Exploratory Study. J. Clin. Med., 13.","DOI":"10.3390\/jcm13247810"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"S102","DOI":"10.1038\/ejcn.2011.94","article-title":"The European Food Consumption Validation Project: Conclusions and recommendations","volume":"65","author":"Slimani","year":"2011","journal-title":"Eur. J. Clin. Nutr."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/j.pcd.2019.05.001","article-title":"The health effects of medical nutrition therapy by dietitians in patients with diabetes: A systematic review and meta-analysis: Nutrition therapy and diabetes","volume":"13","author":"Razaz","year":"2019","journal-title":"Prim. Care Diabetes"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Sun, H., Zhang, K., Lan, W., Gu, Q., Jiang, G., Yang, X., Qin, W., and Han, D. (2023). An AI Dietitian for Type 2 Diabetes Mellitus Management Based on Large Language and Image Recognition Models: Preclinical Concept Validation Study. J. Med. Internet Res., 25.","DOI":"10.2196\/51300"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cantu-Jungles, T.M., McCormack, L.A., Slaven, J.E., Slebodnik, M., and Eicher-Miller, H.A. (2017). A Meta-Analysis to Determine the Impact of Restaurant Menu Labeling on Calories and Nutrients (Ordered or Consumed) in U.S. Adults. Nutrients, 9.","DOI":"10.3390\/nu9101088"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1001\/jama.2011.993","article-title":"Accuracy of stated energy contents of restaurant foods","volume":"306","author":"Urban","year":"2011","journal-title":"JAMA"},{"key":"ref_9","unstructured":"(2025, June 30). Restaurant and Packaged Foods Can Have More Calories Than Nutrition Labeling Indicates. Available online: https:\/\/www.sciencedaily.com\/releases\/2010\/01\/100105100021.htm#:~:text=The%20authors%20also%20note%20that,exceed%20the%20stated%20energy%20content."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1017\/S1368980018003762","article-title":"Ultra-processed foods: What they are and how to identify them","volume":"22","author":"Monteiro","year":"2019","journal-title":"Public. Health Nutr."},{"key":"ref_11","unstructured":"National Health Administration, Ministry of Health and Welfare (2019). Food Substitution Table 2019."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1123\/ijsnem.13.2.152","article-title":"Variability in estimation of self-reported dietary intake data from elite athletes resulting from coding by different sports dietitians","volume":"13","author":"Braakhuis","year":"2003","journal-title":"Int. J. Sport. Nutr. Exerc. Metab."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Shonkoff, E., Cara, K.C., Pei, X.A., Chung, M., Kamath, S., Panetta, K., and Hennessy, E. (2023). AI-based digital image dietary assessment methods compared to humans and ground truth: A systematic review. Ann. Med., 55.","DOI":"10.1080\/07853890.2023.2273497"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kaya Kacar, H., Kacar, O.F., and Avery, A. (2025). Diet Quality and Caloric Accuracy in AI-Generated Diet Plans: A Comparative Study Across Chatbots. Nutrients, 17.","DOI":"10.3390\/nu17020206"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1241","DOI":"10.1017\/S0007114525000522","article-title":"Validity and accuracy of artificial intelligence-based dietary intake assessment methods: A systematic review","volume":"133","author":"Cofre","year":"2025","journal-title":"Br. J. Nutr."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chotwanvirat, P., Prachansuwan, A., Sridonpai, P., and Kriengsinyos, W. (2024). Advancements in Using AI for Dietary Assessment Based on Food Images: Scoping Review. J. Med. Internet Res., 26.","DOI":"10.2196\/51432"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1017\/S1368980021004390","article-title":"Dietary sodium estimation methods: Accuracy and limitations of old and new methods in individuals at high cardiovascular risk","volume":"25","author":"Tsirimiagkou","year":"2022","journal-title":"Public Health Nutr."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Baker, P., Machado, P., Santos, T., Sievert, K., Backholer, K., Hadjikakou, M., Russell, C., Huse, O., Bell, C., and Scrinis, G. (2020). Ultra-processed foods and the nutrition transition: Global, regional and national trends, food systems transformations and political economy drivers. Obes. Rev., 21.","DOI":"10.1111\/obr.13126"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Connolly, D., Minj, J., Murphy, K.M., Solverson, P.M., Rust, B.M., and Carbonero, F. (2024). Impact of quinoa and food processing on gastrointestinal health: A narrative review. Crit. Rev. Food Sci. Nutr., 1\u20134.","DOI":"10.1080\/10408398.2024.2416476"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, C.H., Wong, T.C., Chung, M., Bai, C.H., and Chen, Y.C. (2023). Sugar labeling information and online marketing strategies for hand-shaken tea drinks in northern Taiwan. Front. Nutr., 10.","DOI":"10.3389\/fnut.2023.1273713"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Huang, Y., Chen, Z., Chen, B., Li, J., Yuan, X., Li, J., Wang, W., Dai, T., Chen, H., and Wang, Y. (2023). Dietary sugar consumption and health: Umbrella review. BMJ, 381.","DOI":"10.1136\/bmj-2022-071609"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"52","DOI":"10.3109\/10408363.2015.1084990","article-title":"Sugar consumption, metabolic disease and obesity: The state of the controversy","volume":"53","author":"Stanhope","year":"2016","journal-title":"Crit. Rev. Clin. Lab. Sci."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Pham, T. (2025). Ethical and legal considerations in healthcare AI: Innovation and policy for safe and fair use. R. Soc. Open Sci., 12.","DOI":"10.1098\/rsos.241873"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kassem, H., Beevi, A.A., Basheer, S., Lutfi, G., Cheikh Ismail, L., and Papandreou, D. (2025). Investigation and Assessment of AI's Role in Nutrition-An Updated Narrative Review of the Evidence. Nutrients, 17.","DOI":"10.3390\/nu17010190"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: The convergence of human and artificial intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat. Med."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Markus, A.F., Kors, J.A., and Rijnbeek, P.R. (2021). The role of explainability in creating trustworthy artificial intelligence for health care: A comprehensive survey of the terminology, design choices, and evaluation strategies. J. Biomed. Inf., 113.","DOI":"10.1016\/j.jbi.2020.103655"}],"container-title":["Nutrients"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6643\/17\/19\/3044\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:48:47Z","timestamp":1760035727000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6643\/17\/19\/3044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,24]]},"references-count":26,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["nu17193044"],"URL":"https:\/\/doi.org\/10.3390\/nu17193044","relation":{},"ISSN":["2072-6643"],"issn-type":[{"value":"2072-6643","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,24]]}}}