{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T08:57:52Z","timestamp":1791449872352,"version":"4.3.3"},"reference-count":31,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"tdm","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: Large language models (LLMs) are increasingly used to generate nutrition-related recommendations, but their reliability for therapeutic diets requiring precise nutrient control remains uncertain. This study evaluated AI-generated one-day diet plans for standardized simulated cases of classical phenylketonuria (PKU). Methods: Eight standardized simulated cases representing infancy, adolescence, adulthood, and maternal PKU were evaluated. Between 8 and 10 February 2026, ChatGPT-5.2, Claude 4.5, and Gemini 3 were each used through their standard consumer-facing chat interfaces to generate one diet plan per case under two prompting conditions, yielding 48 plans. Nutrient composition was independently recalculated using B\u0130AYS, and three blinded pediatric metabolic dietitians evaluated the plans using a structured 25-item checklist. Results: Across all 48 plans, phenylalanine provision calculated using B\u0130AYS was below the case-specific prescription in 36 plans (75.0%). After Holm correction, none of the 12 paired AI-reported versus B\u0130AYS-calculated nutrient comparisons remained statistically significant, while plan-level error metrics demonstrated substantial variability for several nutrients. Overall expert scores did not differ among models, whereas clinically specified structured prompts received higher expert ratings than limited-information zero-shot prompts. Inter-rater reliability was modest at the diet-plan level. Conclusions: AI-generated PKU diet plans may incorporate core dietary principles, but numerical plausibility does not ensure agreement with independent nutrient calculations or adherence to individualized clinical prescriptions. Independent nutrient verification and specialist metabolic-dietitian review remain necessary. Because only one output was generated for each case\u2013model\u2013prompt combination, the findings characterize the 48 evaluated outputs rather than within-model reproducibility.<\/jats:p>","DOI":"10.3390\/nu18193158","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T08:09:02Z","timestamp":1790323742000},"page":"3158","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Nutritional Accuracy and Clinical Applicability of Large Language Model-Generated Therapeutic Diet Plans for Phenylketonuria: A Comparative Simulation Study"],"prefix":"10.3390","volume":"18","author":[{"given":"Bahar","family":"Kulu","sequence":"first","affiliation":[{"name":"Division of Inherited Metabolic Disorders, University of Health Sciences, Tepecik Training and Research Hospital, \u0130zmir 35170, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5975-5868","authenticated-orcid":false,"given":"Banu","family":"S\u00fczen","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, School of Health Sciences, Cappadocia University, Nev\u015fehir 50420, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0033-6861","authenticated-orcid":false,"given":"Nuriye Ece","family":"Minta\u015f","sequence":"additional","affiliation":[{"name":"Division of Inherited Metabolic Disorders, Mu\u011fla Training and Research Hospital, Mu\u011fla 48000, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"given":"Sibel Bur\u00e7ak","family":"\u015eahin Uyar","sequence":"additional","affiliation":[{"name":"Division of Inherited Metabolic Disorders, \u0130zmir City Hospital, \u0130zmir 35530, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9393-143X","authenticated-orcid":false,"given":"Esra","family":"\u00d6zcan","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, \u0130zmir City Hospital, \u0130zmir 35530, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1365-2475","authenticated-orcid":false,"given":"Fulya","family":"Dur\u011fun","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, Tepecik Training and Research Hospital, \u0130zmir 35180, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0059-178X","authenticated-orcid":false,"given":"Neslihan Buse","family":"Tatl\u0131dil","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, Tepecik Training and Research Hospital, \u0130zmir 35180, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"data-curation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"}]},{"given":"Nur","family":"Arslan","sequence":"additional","affiliation":[{"name":"Division of Inherited Metabolic Disorders, Faculty of Medicine, Dokuz Eyl\u00fcl University, \u0130zmir 35340, T\u00fcrkiye"},{"name":"Izmir Biomedicine and Genome Center (\u0130BG), \u0130zmir 35340, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2227-194X","authenticated-orcid":false,"given":"Volkan","family":"Hanc\u0131","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology and Reanimation, Division of Intensive Care, Faculty of Medicine, Dokuz Eyl\u00fcl University, \u0130zmir 35340, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"conceptualization","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1417","DOI":"10.1016\/S0140-6736(10)60961-0","article-title":"Phenylketonuria","volume":"376","author":"Blau","year":"2010","journal-title":"Lancet"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"109125","DOI":"10.1016\/j.ymgme.2025.109125","article-title":"European guidelines on diagnosis and treatment of phenylketonuria: First revision","volume":"145","author":"MacDonald","year":"2025","journal-title":"Mol. Genet. Metab."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.ymgme.2016.04.008","article-title":"Updated, web-based nutrition management guideline for PKU: An evidence- and consensus-based approach","volume":"118","author":"Singh","year":"2016","journal-title":"Mol. Genet. Metab."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"S10","DOI":"10.1016\/j.ymgme.2011.08.023","article-title":"Nutrition in phenylketonuria","volume":"104","author":"MacDonald","year":"2011","journal-title":"Mol. Genet. Metab."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"101602","DOI":"10.1016\/j.gim.2025.101602","article-title":"Phenylalanine hydroxylase deficiency diagnosis and management: A 2023 evidence-based clinical guideline of the American College of Medical Genetics and Genomics (ACMG)","volume":"28","author":"Smith","year":"2026","journal-title":"Genet. Med."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, X., Sun, Z., Xue, H., and An, R. (2025). Artificial intelligence applications to personalized dietary recommendations: A systematic review. Healthcare, 13.","DOI":"10.3390\/healthcare13121417"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kush, J.C. (2025). Exploring the uses of artificial intelligence and ChatGPT in therapeutic diet and nutrition. J. Data Sci. Intell. Syst., 1\u201310.","DOI":"10.47852\/bonviewJDSIS52025709"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e70295","DOI":"10.1111\/jep.70295","article-title":"Evaluating AI-generated meal plans for simulated diabetes profiles: A guideline-based comparison of three language models","volume":"31","author":"Bayram","year":"2025","journal-title":"J. Eval. Clin. Pract."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Gavai, A.K., and van Hillegersberg, J. (2025). AI-driven personalized nutrition: RAG-based digital health solution for obesity and type 2 diabetes. PLoS Digit. Health, 4.","DOI":"10.1371\/journal.pdig.0000758"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1007\/s10439-023-03227-9","article-title":"Exploring the potential of ChatGPT in personalized obesity treatment","volume":"51","author":"Arslan","year":"2023","journal-title":"Ann. Biomed. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1053\/j.jrn.2024.09.001","article-title":"Application of ChatGPT to support nutritional recommendations for dialysis patients: A qualitative and quantitative evaluation","volume":"34","author":"Wang","year":"2024","journal-title":"J. Ren. Nutr."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e70033","DOI":"10.1111\/jhn.70033","article-title":"Artificial intelligence-based diets: A role in the nutritional treatment of metabolic dysfunction-associated steatotic liver disease","volume":"38","author":"Kenger","year":"2025","journal-title":"J. Hum. Nutr. Diet."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kim, D.W., Park, J.S., Sharma, K., Velazquez, A., Li, L., Ostrominski, J.W., Tran, T., Per\u00e9z, R.H.S., and Shin, J.-H. (2024). Qualitative evaluation of artificial intelligence-generated weight management diet plans. Front. Nutr., 11.","DOI":"10.3389\/fnut.2024.1374834"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kaya Ka\u00e7ar, H., Ka\u00e7ar, 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","unstructured":"Bolat Yilmaz, A., Kenger, E.B., Ozlu Karahan, T., Saglam, D., and Bas, M. (2025). Guideline compliance of artificial intelligence-generated diet plans after bariatric surgery: A cross-sectional simulation comparing ChatGPT-4o, DeepSeek and Grok-3. Nutrients, 17."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1053\/j.jrn.2025.01.004","article-title":"Accuracy of current large language models and the retrieval-augmented generation model in determining dietary principles in chronic kidney disease","volume":"35","author":"Bingol","year":"2025","journal-title":"J. Ren. Nutr."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"CHART Collaborative (2025). Reporting guideline for chatbot health advice studies: The CHART statement. JAMA Netw. Open, 8, e2530220.","DOI":"10.1001\/jamanetworkopen.2025.30220"},{"key":"ref_18","unstructured":"Mavi Elma Grup (2026, September 16). BiayS Akademi: Besin \u0130\u00e7erik Analiz Yaz\u0131l\u0131m Sistemi. Available online: https:\/\/www.mavielmagrup.com\/biays-akademi."},{"key":"ref_19","unstructured":"T.C. Ministry of Health, General Directorate of Public Health (2022). T\u00fcrkiye Beslenme Rehberi (T\u00dcBER) 2022 [Turkey Dietary Guidelines 2022], Ministry of Health Publication No. 1031."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"413","DOI":"10.24953\/turkjped.2021.4098","article-title":"Recommendations on phenylketonuria in Turkey","volume":"64","author":"Mungan","year":"2022","journal-title":"Turk. J. Pediatr."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1186\/s13023-020-01391-y","article-title":"PKU dietary handbook to accompany PKU guidelines","volume":"15","author":"MacDonald","year":"2020","journal-title":"Orphanet J. Rare Dis."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1186\/s13023-025-03840-y","article-title":"Current state of the treatment landscape of phenylketonuria","volume":"20","author":"Nulmans","year":"2025","journal-title":"Orphanet J. Rare Dis."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"ehaf784.4379","DOI":"10.1093\/eurheartj\/ehaf784.4379","article-title":"Personalized approach to cardiovascular risk stratification: A randomized controlled trial evaluating the effectiveness of an AI-developed diet versus a standard Mediterranean diet","volume":"46","author":"Rozibaev","year":"2025","journal-title":"Eur. Heart J."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1038\/s41598-024-85003-w","article-title":"Evaluation of LLMs accuracy and consistency in the registered dietitian exam through prompt engineering and knowledge retrieval","volume":"15","author":"Azimi","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e78625","DOI":"10.2196\/78625","article-title":"Evaluating large language models and retrieval-augmented generation enhancement for delivering guideline-adherent nutrition information for cardiovascular disease prevention: Cross-sectional study","volume":"27","author":"Parameswaran","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"104702","DOI":"10.1016\/j.jbi.2024.104702","article-title":"Rare disease diagnosis using knowledge guided retrieval augmentation for ChatGPT","volume":"157","author":"Zelin","year":"2024","journal-title":"J. Biomed. Inform."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"101127","DOI":"10.1016\/j.ajcnut.2025.101127","article-title":"Language models in nutrition and dietetics: A scoping review","volume":"123","author":"Kent","year":"2026","journal-title":"Am. J. Clin. Nutr."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1038\/s41746-025-01519-z","article-title":"Retrieval augmented generation for 10 large language models and its generalizability in assessing medical fitness","volume":"8","author":"Ke","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"113031","DOI":"10.1016\/j.diabres.2025.113031","article-title":"Chat, Gemini and Claude at the dinner table: Assessing general-purpose AI tools for carbohydrate counting in the context of type 1 diabetes","volume":"231","author":"Goncalves","year":"2026","journal-title":"Diabetes Res. Clin. Pract."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"103355","DOI":"10.1016\/j.dsx.2025.103355","article-title":"Assessing the quality and guideline-concordance of AI-powered chatbots in nutritional management of diabetes","volume":"19","author":"Boutahar","year":"2025","journal-title":"Diabetes Metab. Syndr."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Su, Y., Wang, Y., He, J., Wang, H., A, X., Jiang, H., Lu, W., Zhou, W., and Li, L. (2024). Development and validation of machine-learning models of diet management for hyperphenylalaninemia: A multicenter retrospective study. BMC Med., 22.","DOI":"10.1186\/s12916-024-03602-w"}],"container-title":["Nutrients"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6643\/18\/19\/3158\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T08:48:24Z","timestamp":1791449304000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6643\/18\/19\/3158"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"references-count":31,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["nu18193158"],"URL":"https:\/\/doi.org\/10.3390\/nu18193158","relation":{},"ISSN":["2072-6643"],"issn-type":[{"value":"2072-6643","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]}}}