{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T13:55:02Z","timestamp":1790603702115,"version":"4.1.0"},"reference-count":38,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"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: This study evaluated the nutrient calculation accuracy, reproducibility, and expert-rated clinical appropriateness and safety indicators of three-day diet plans generated for women with polycystic ovary syndrome (PCOS), recently proposed to be termed polyendocrine metabolic ovarian syndrome (PMOS). Methods: Anonymized data from six women with heterogeneous PMOS profiles, purposively selected from a single clinic, were converted into standardized Turkish prompts and submitted to ChatGPT-4, Claude Sonnet 4.6, Gemini 2.5 Flash, and Mistral 2.0 through free web interfaces. Three independent generations per case\u2013model combination yielded 216 daily menus. LLM-reported nutrient values were compared with BeBiS 9.0 calculations. Reproducibility was assessed using intraclass correlation coefficients (ICCs). Two experts independently evaluated the first generated plan for each case\u2013model combination using a study-specific clinical appropriateness rubric and red-flag checklist. Results: No model achieved consistently low error across nutrients. Claude Sonnet 4.6 showed the lowest percentage errors for energy, carbohydrate, and fiber; ChatGPT-4 for protein; and Mistral 2.0 for fat. Gemini 2.5 Flash showed the largest percentage errors across all nutrients and a mean energy bias of +531.1 kcal. ChatGPT-4 showed comparatively higher plan-level reproducibility, while the remaining models generally showed poor reproducibility. Claude Sonnet 4.6 had the highest descriptive clinical appropriateness scores and Gemini 2.5 Flash the lowest, but no pairwise differences remained significant after Holm correction. Gemini 2.5 Flash generated the most confirmed study-specific red flags (n = 28), with all six cases meeting the criterion for the \u201cmasked low-energy\u201d indicator. Conclusions: LLM-generated diet plans showed model-dependent calculation errors and limited reproducibility, and the present findings do not support their independent or unsupervised use as individualized clinical nutrition recommendations.<\/jats:p>","DOI":"10.3390\/nu18193205","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T12:46:29Z","timestamp":1790599589000},"page":"3205","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Nutrient Calculation Accuracy, Expert-Rated Clinical Appropriateness and Safety Indicators, and Reproducibility of Large Language Model-Generated Diet Plans for Polyendocrine Metabolic Ovarian Syndrome: A Real-Case-Based Evaluation"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5823-617X","authenticated-orcid":false,"given":"Ay\u015fenur","family":"\u00c7al\u0131k","sequence":"first","affiliation":[{"name":"Department of Nutrition and Dietetics, Faculty of Health Sciences, Istanbul Atlas University, Istanbul 34403, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3310-612X","authenticated-orcid":false,"given":"P\u0131nar Ece","family":"Demiray","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, Faculty of Health Sciences, Istanbul Atlas University, Istanbul 34403, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2765-2677","authenticated-orcid":false,"given":"Ay\u015fe Bet\u00fcl","family":"Bilen","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, Faculty of Health Sciences, Istanbul Atlas University, Istanbul 34403, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3397-9513","authenticated-orcid":false,"given":"G\u00fclen Ecem","family":"Kalkan","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, Faculty of Health Sciences, Istanbul Atlas University, Istanbul 34403, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5323-7154","authenticated-orcid":false,"given":"Muazzez","family":"Garipa\u011fao\u011flu","sequence":"additional","affiliation":[{"name":"Department of Nutrition and Dietetics, Faculty of Health Sciences, Fenerbah\u00e7e University, Istanbul 34758, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2447","DOI":"10.1210\/clinem\/dgad463","article-title":"Recommendations From the 2023 International Evidence-Based Guideline for the Assessment and Management of Polycystic Ovary Syndrome","volume":"108","author":"Teede","year":"2023","journal-title":"J. Clin. Endocrinol. Metab."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1093\/humupd\/dmaf030","article-title":"Prevalence of Polycystic Ovary Syndrome: A Global and Regional Systematic Review and Meta-Analysis","volume":"32","author":"Neven","year":"2026","journal-title":"Hum. Reprod. Update"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2329","DOI":"10.1016\/S0140-6736(26)00717-8","article-title":"Polyendocrine Metabolic Ovarian Syndrome, the New Name for Polycystic Ovary Syndrome: A Multistep Global Consensus Process","volume":"407","author":"Teede","year":"2026","journal-title":"Lancet"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Cowan, S., Lim, S., Alycia, C., Pirotta, S., Thomson, R., Gibson-Helm, M., Blackmore, R., Naderpoor, N., Bennett, C., and Ee, C. (2023). Lifestyle Management in Polycystic Ovary Syndrome\u2014Beyond Diet and Physical Activity. BMC Endocr. Disord., 23.","DOI":"10.1186\/s12902-022-01208-y"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1038\/s41572-024-00511-3","article-title":"Polycystic Ovary Syndrome","volume":"10","author":"Teede","year":"2024","journal-title":"Nat. Rev. Dis. Primers"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Belkhouribchia, J., and Pen, J.J. (2025). Large Language Models in Clinical Nutrition: An Overview of Its Applications, Capabilities, Limitations, and Potential Future Prospects. Front. Nutr., 12.","DOI":"10.3389\/fnut.2025.1635682"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Panayotova, G.G. (2025). Artificial Intelligence in Nutrition and Dietetics: A Comprehensive Review of Current Research. Healthcare, 13.","DOI":"10.3390\/healthcare13202579"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.nutres.2024.07.002","article-title":"Can the AI Tools ChatGPT and Bard Generate Energy, Macro- and Micro-Nutrient Sufficient Meal Plans for Different Dietary Patterns?","volume":"128","author":"Hieronimus","year":"2024","journal-title":"Nutr. Res."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"112076","DOI":"10.1016\/j.nut.2023.112076","article-title":"The Credibility of Dietary Advice Formulated by ChatGPT: Robo-Diets for People with Food Allergies","volume":"112","author":"Niszczota","year":"2023","journal-title":"Nutrition"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Karakas, P.E., Calik, A., Bilen, A.B., Kandemir, K., and Alphan, M.E. (2026). Large Language Models as Clinical Nutrition Decision Tools: Quantitative Bias and Guideline Deviation in Type 2 Diabetes Meal Planning. Healthcare, 14.","DOI":"10.3390\/healthcare14060739"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ghaderzadeh, M., Garavand, A., and Salehnasab, C. (2025). Artificial Intelligence in Polycystic Ovary Syndrome: A Systematic Review of Diagnostic and Predictive Applications. BMC Med. Inf. Decis. Mak., 25.","DOI":"10.1186\/s12911-025-03255-6"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1007\/s11547-025-02032-9","article-title":"Artificial Intelligence in Polycystic Ovarian Syndrome Management: Past, Present, and Future","volume":"130","author":"Wang","year":"2025","journal-title":"Radiol. Med."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zad, Z., Jiang, V.S., Wolf, A.T., Wang, T., Cheng, J.J., Paschalidis, I.C., and Mahalingaiah, S. (2024). Predicting Polycystic Ovary Syndrome with Machine Learning Algorithms from Electronic Health Records. Front. Endocrinol., 15.","DOI":"10.3389\/fendo.2024.1298628"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.nutres.2024.11.005","article-title":"Evaluating Reliability, Quality, and Readability of ChatGPT\u2019s Nutritional Recommendations for Women with Polycystic Ovary Syndrome","volume":"133","author":"Ulug","year":"2025","journal-title":"Nutr. Res."},{"key":"ref_15","unstructured":"(2026, March 24). OpenAI ChatGPT-4. Available online: https:\/\/chat.openai.com."},{"key":"ref_16","unstructured":"(2026, March 25). Anthropic Claude Sonnet 4.6. Available online: https:\/\/claude.ai."},{"key":"ref_17","unstructured":"(2026, March 25). Google Gemini 2.5 Flash. Available online: https:\/\/gemini.google.com."},{"key":"ref_18","unstructured":"(2026, March 28). Mistral AI Mistral 2.0. Available online: https:\/\/mistral.ai\/."},{"key":"ref_19","unstructured":"BeBiS (2019). Ebispro for Windows, Stuttgart, Germany; Turkish Version (BeBiS 9.0), Pasifik Elektrik Elektronik Ltd. \u015eti."},{"key":"ref_20","unstructured":"Mulvihill, C., Young, M., Kettle, R., and Mariani, A. (2025). NG246 Overweight and Obesity Management (NICE Guideline), National Institute for Health and Care Excellence."},{"key":"ref_21","unstructured":"(2006). Dietary Reference Intakes Research Synthesis: Workshop Summary, National Academies Press."},{"key":"ref_22","unstructured":"Standing Committee for the Review of the Dietary Reference Intake Framework, Food and Nutrition Board, Health and Medicine Division, and National Academies of Sciences, Engineering, and Medicine (2024). Rethinking the Acceptable Macronutrient Distribution Range for the 21st Century: A Letter Report, National Academies Press."},{"key":"ref_23","unstructured":"IBM Corp (IBM SPSS Statistics, 2017). IBM SPSS Statistics, version 25."},{"key":"ref_24","unstructured":"(2026, August 19). Jamovi. The Jamovi Project. Available online: https:\/\/www.jamovi.org."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research","volume":"15","author":"Koo","year":"2016","journal-title":"J. Chiropr. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","article-title":"Statistical Methods for Assessing Agreement between Two Methods of Clinical Measurement","volume":"1","author":"Bland","year":"1986","journal-title":"Lancet"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Kaya Ka\u00e7ar, H., Ka\u00e7ar, \u00d6.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_28","doi-asserted-by":"crossref","unstructured":"Dobrowolski, H. (2026). An Analysis of the Nutritional Value of Diets Generated by Large Language Models Under Average User Conditions\u20143(LM)Diet Study. Nutrients, 18.","DOI":"10.3390\/nu18142363"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e70639","DOI":"10.1002\/fsn3.70639","article-title":"ChatGPT -4o for Weight Management: Comparison of Different Diet Models","volume":"13","author":"Kenger","year":"2025","journal-title":"Food Sci. Nutr."},{"key":"ref_30","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_31","doi-asserted-by":"crossref","unstructured":"Bolat Yilmaz, A., Kenger, E.B., Ozlu Karahan, T., Saglam, D., and Bas, M. (2025). Guideline Compliance of Artificial Intelligence\u2013Generated Diet Plans After Bariatric Surgery: A Cross-Sectional Simulation Comparing ChatGPT-4o, DeepSeek and Grok-3. Nutrients, 17.","DOI":"10.3390\/nu17243957"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"mzaf134","DOI":"10.1093\/intqhc\/mzaf134","article-title":"Patient Safety and Quality Implications of Large Language Model Use in Healthcare: A Risk-Stratified Assessment of Artificial Intelligence-Assisted Medical Consultations","volume":"38","author":"Esmaeilzadeh","year":"2026","journal-title":"Int. J. Qual. Health Care"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1053\/j.jrn.2025.02.008","article-title":"Still a Long Way to Go, the Potential of ChatGPT in Personalized Dietary Prescription, From a Perspective of a Clinical Dietitian","volume":"35","author":"You","year":"2025","journal-title":"J. Ren. Nutr."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1038\/s43856-025-01159-0","article-title":"DietAI24 as a Framework for Comprehensive Nutrition Estimation Using Multimodal Large Language Models","volume":"5","author":"Yan","year":"2025","journal-title":"Commun. Med."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Brinkley, S., Gallo-Franco, J.J., V\u00e1zquez-Manjarrez, N., Chaura, J., Quartey, N.K.A., Toulabi, S.B., Odenkirk, M.T., Jermendi, E., Laporte, M.-A., and Lutterodt, H.E. (2025). The State of Food Composition Databases: Data Attributes and FAIR Data Harmonization in the Era of Digital Innovation. Front. Nutr., 12.","DOI":"10.3389\/fnut.2025.1552367"},{"key":"ref_36","unstructured":"World Health Organization (2025). Ethics and Governance of Artificial Intelligence for Health: Guidance on Large Multi-Modal Models, World Health Organization."},{"key":"ref_37","unstructured":"U.S. Food and Drug Administration (2024). Health Canada, Medicines and Healthcare Products Regulatory Agency Transparency for Machine Learning-Enabled Medical Devices: Guiding Principles."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1079","DOI":"10.1016\/j.cell.2015.11.001","article-title":"Personalized Nutrition by Prediction of Glycemic Responses","volume":"163","author":"Zeevi","year":"2015","journal-title":"Cell"}],"container-title":["Nutrients"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6643\/18\/19\/3205\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T12:56:45Z","timestamp":1790600205000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6643\/18\/19\/3205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":38,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["nu18193205"],"URL":"https:\/\/doi.org\/10.3390\/nu18193205","relation":{},"ISSN":["2072-6643"],"issn-type":[{"value":"2072-6643","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]}}}