{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:21:03Z","timestamp":1791908463515,"version":"4.3.4"},"reference-count":47,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"vor","delay-in-days":6,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Evaluation Clinical Practice"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>This synthetic simulation, using no real patient data, study aimed to evaluate and compare the performance of three prominent large language models (LLMs)\u2014ChatGPT\u20104.1, Grok\u20103 and DeepSeek\u2014in generating medical nutrition therapy aligned dietary plans for adults with type 2 diabetes mellitus (T2DM).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A simulation\u2010based design was employed using 24 standardized virtual patient profiles differentiated by gender and body mass index (BMI) category. Each LLM was prompted in Turkish to generate 3\u2010day meal plans. Outputs were assessed for energy and macro\u2010\/micronutrient accuracy, adherence to national and international T2DM guidelines and alignment with the nutrition care process (NCP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>ChatGPT\u20104.1 showed the highest alignment with energy requirements (70.9%) but overestimated fat intake. Grok\u20103 demonstrated superior energy accuracy (83.1%) but failed to meet several micronutrient targets. DeepSeek adjusted protein intake according to BMI but underdelivered carbohydrates. None of the models demonstrated full concordance with the NCP framework, particularly in the diagnosis and monitoring components. Frequent hallucinations and lack of clinical contextualization were noted. Integration of retrieval\u2010augmented generation (RAG) was identified as a potential improvement strategy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>While LLMs showed promise in generating baseline dietary guidance in a simulated context, these results reflected concordance with guideline documents only and concordance with guideline documents only and should not be interpreted as evidence of equivalence to dietitian\u2010led care. These findings reflected model behaviour in synthetic scenarios only and highlighted the need for RAG integration and expert supervision before any clinical application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/jep.70295","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:17:15Z","timestamp":1759882635000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Evaluating AI\u2010Generated Meal Plans for Simulated Diabetes Profiles: A Guideline\u2010Based Comparison of Three Language Models"],"prefix":"10.1111","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7073-2907","authenticated-orcid":false,"given":"Hatice Merve","family":"Bayram","sequence":"first","affiliation":[{"name":"Department of Nutrition and Dietetics, Faculty of Health Sciences Istanbul Gelisim University Istanbul Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3356-7332","authenticated-orcid":false,"given":"Sedat","family":"Arslan","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, Faculty of Health Sciences Bandirma Onyedi Eylul University Balikesir Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7982-6988","authenticated-orcid":false,"given":"Arda","family":"Ozturkcan","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, Faculty of Health Sciences Istanbul Gelisim University Istanbul Turkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,10,7]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41392-024-01951-9"},{"key":"e_1_2_9_3_1","unstructured":"\u201cIDF Global Clinical Practice Recommendations for Managing Type 2 Diabetes \u201d International Diabetes Federation 2015 https:\/\/idf.org\/media\/uploads\/2025\/04\/IDF_Rec_2025.pdf."},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-053541"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.2337\/dci19-0014"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1159\/000357331"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.3945\/ajcn.116.139626"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.3390\/antiox12040904"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/nu9080848"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2017.12.016"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1042\/BSR20222151"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2021.645260"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.2196\/31977"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13137835"},{"key":"e_1_2_9_15_1","doi-asserted-by":"crossref","unstructured":"C.Kosaraju S.Chiruguri N.Mohammad B. T.Jetty andG.Gali \u201cA Model for Analysis of Diseases Based on Nutrition Deficiency Using Random Forest \u201d 7th International Conference on Communication and Electronics Systems (ICCES) 2022 1527\u201331 https:\/\/doi.org\/10.1109\/ICCES54183.2022.9835805.","DOI":"10.1109\/ICCES54183.2022.9835805"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1108\/bfj-02-2024-0158"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41430-024-01476-y"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clnesp.2024.02.022"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1177\/02601060251329070"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/fi16070219"},{"key":"e_1_2_9_21_1","unstructured":"S.Singh S.Bansal A. E.Saddik andM.Saini \u201cFrom ChatGPT to DeepSeek AI: A Comprehensive Analysis of Evolution Deviation and Future Implications in AI\u2010Language Models \u201d arXiv Preprint 2025 arXiv:2504.03219."},{"key":"e_1_2_9_22_1","unstructured":"M.Mirzazada \u201cElon Musk's xAI Releases Grok 3 Its Latest Flagship AI Model [Internet] \u201d 2025 https:\/\/anewz.tv\/science\/artificial-intelligence\/3045\/."},{"key":"e_1_2_9_23_1","unstructured":"K.Wiggers \u201cElon Musk's AI Company xAI Releases Its Latest Flagship AI Grok 3 \u201d TechCrunch 2025 https:\/\/techcrunch.com\/2025\/02\/17\/elon-musks-ai-company-xai-releases-its-latest-flagship-ai-grok-3\/."},{"key":"e_1_2_9_24_1","unstructured":"E.Gibney \u201cGrok 3: What To Know About Musk's New AI \u201d Nature 2025 https:\/\/www.nature.com\/articles\/d41586-025-00229-6."},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/clinpract13050104"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm13247810"},{"key":"e_1_2_9_27_1","unstructured":"\u201cGPT\u20104.1 [Internet] \u201d OpenAI 2025 https:\/\/openai.com\/index\/gpt-4-1."},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.34297\/AJBSR.2025.25.003362"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.04.003"},{"key":"e_1_2_9_30_1","unstructured":"\u201cTurkey Health Survey \u201d Turkish Statistical Institute 2022https:\/\/data.tuik.gov.tr\/Bulten\/Index?p=Turkiye-Saglik-Arastirmasi-2022-49747."},{"key":"e_1_2_9_31_1","unstructured":"\u201cDiyabet Tan\u0131 ve Tedavi Rehberi \u201d National Diabetes Consensus Group 2023."},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.2337\/dc24-S008"},{"key":"e_1_2_9_33_1","unstructured":"\u201cClinical Guidance for Diabetes [Internet] \u201d CDCD 2024 https:\/\/www.guidelinecentral.com\/guideline\/14119\/."},{"key":"e_1_2_9_34_1","unstructured":"\u201cDiabetes Mellitus ve Komplikasyonlar\u0131n\u0131n Tan\u0131 Tedavi Ve \u0130zlem K\u0131lavuzu \u201d Turkish Endocrine and Metabolism Association 2024."},{"key":"e_1_2_9_35_1","unstructured":"\u201cDiyabet Tan\u0131 ve Tedavi Rehberi \u201d Turkish Diabetes Foundation 2025."},{"key":"e_1_2_9_36_1","unstructured":"\u201cNutrition Care Manual [Internet] \u201d Academy of Nutrition and Dietetics 2022 https:\/\/www.nutritioncaremanual.org."},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1093\/ajcn\/51.2.241"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfca.2025.107850"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/jhn.70033"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.3390\/nu17040607"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12884-020-03352-6"},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","unstructured":"I.Azimi M.Qi L.Wang A. M.Rahmani andY.Li \u201cAccuracy and Consistency of LLMs in the Registered Dietitian Exam: The Impact of Prompt Engineering and Knowledge Retrieval \u201d arXiv Preprint 2024 arXiv:2408.02964.","DOI":"10.1038\/s41598-024-85003-w"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.2196\/58041"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000758"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01519-z"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.3390\/medicina60030445"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare13050556"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-2120-0_11"}],"container-title":["Journal of Evaluation in Clinical Practice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jep.70295","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T12:01:49Z","timestamp":1763899309000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/jep.70295"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":47,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1111\/jep.70295"],"URL":"https:\/\/doi.org\/10.1111\/jep.70295","archive":["Portico"],"relation":{},"ISSN":["1356-1294","1365-2753"],"issn-type":[{"value":"1356-1294","type":"print"},{"value":"1365-2753","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]},"assertion":[{"value":"2025-07-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70295"}}