GÜNÜMÜZ YAPAY ZEKA TEKNOLOJİLERİ İLE MENÜ PLANLAMASI VE BESİN ÖĞELERİ ANALİZİ: CHATGPT TABANLI BİR YAKLAŞIM

Abstract

Bu çalışma, huzurevlerindeki bireyler için yapay zeka tarafından oluşturulan menüleri besin öğesi içeriği, MIND diyeti uyumu ve besin öğesi örüntü profiline (NRF9.3) göre değerlendirilmesini amaçlamaktadır. Çalışmada yapay zeka programı olarak ChatGPT kullanılmış olup, programa birer aylık yaz ve kış menüleri oluşturtulmuş ve ardından bu menülerin besin öğesi içerikleri analiz edilmiştir. Menülerin, yaşlı bireylerin besin gereksinimlerini karşılama ve sağlıklı beslenmeye uygunluğu değerlendirilmiştir. Sonuçlara göre, program her iki menüde de MIND diyetine büyük ölçüde uyum sağlasa da, özellikle üzümsü meyve tüketiminin düşük olması, zeytinyağının birincil yağ kaynağı olarak yeterince yer almaması ve şarap tüketiminin bulunmaması tam skora ulaşılamamasına neden olmuştur. Besin yoğunluğu açısından, NRF9 puanları yüksek, ancak NRF9.3 puanları oldukça düşük bulunmuştur. Bu durum, menülerin besin öğesi açısından zengin olmasına rağmen yüksek doymuş yağ, eklenmiş şeker ve sodyum içermesi nedeniyle sağlık açısından optimal olmadığını göstermektedir. Besin öğesi içerikleri incelendiğinde ise; kış menüsünün karbonhidrat, posa, A vitamini, C vitamini, B1 vitamini, folik asit, sodyum, potasyum, magnezyum, çinko ve demir içeriğinin yaz menüsüne göre anlamlı derecede yüksek olduğu görülmüştür (p<0.05). Ancak, kış menüsü protein ve elzem amino asitler açısından daha düşüktür. Sonuç olarak, yapay zeka ile oluşturulan menüler genel olarak besleyici olsa da menülerin doymuş yağ, şeker ve sodyum içeriği açısından dengelenmesi gerekmektedir. Gelecek çalışmalarda daha fazla varyasyon içeren yapay zeka modellerinin test edilmesi ve menülerin yaşlı bireylerin bilişsel performansına etkisinin incelenmesi önerilmektedir.

Keywords

• Yaşlı
• Menü
• Yapay Zeka
• MIND Diyeti
• Besin Öğesi Örüntüsü

MENU PLANNING AND NUTRIENT ANALYSIS WITH CONTEMPORARY AI TECHNOLOGIES: A CHATGPT-BASED APPROACH

Abstract

This study aims to evaluate the nutrient content, adherence to the MIND diet, and nutrient profiling (NRF9.3) score of AI-generated menus for nursing home residents. ChatGPT was utilized as the AI program to generate one-month summer and winter menus, and the nutrient composition of these menus was subsequently analyzed. The menus were assessed in terms of their ability to meet the nutritional needs of older adults and their alignment with healthy eating guidelines. According to the results, although the AI-generated menus largely adhered to the MIND diet, certain limitations prevented a perfect score. Specifically, the consumption of berries was low, olive oil was not sufficiently included as the primary fat source, and there was no wine consumption. In terms of nutrient density, the NRF9 scores were high, whereas the NRF9.3 scores were significantly lower. This suggests that while the menus were nutrient-rich, they were not optimally healthy due to their high content of saturated fat, added sugars, and sodium. When analyzing the nutrient composition, the winter menu was found to have significantly higher levels of carbohydrates, fiber, vitamin A, vitamin C, vitamin B1, folic acid, sodium, potassium, magnesium, zinc, and iron compared to the summer menu (p<0.05). However, the winter menu had lower levels of protein and essential amino acids. In conclusion, while AI-generated menus were generally nutritious, they require adjustments to balance saturated fat, sugar, and sodium content. Future studies should explore AI models with greater variability and examine the effects of AI-generated menus on the cognitive performance of older adults.

Keywords

• Elderly
• Menu
• Artificial Intelligence
• MIND diet
• Nutrient Pattern

References

1. Abzhanova, S., Baybolova, L., Zhaksylykova, G., Tayeva, A., & Kulazhanov, T. (2023). Development of meat products for the nutrition of the elderly. Human Nutrition & Metabolism, 33, 200201. https://doi.org/10.1016/j.hnm.2023.200201
2. Alhammadi, K., Santos-Roldán, L., & Cabeza-Ramírez, L. J. (2021). A Theoretical framework on the determinants of food purchasing behavior of the elderly: a bibliometric review with scientific mapping in web of science. Foods, 10(3), 688. https://doi.org/10.3390/foods10030688
3. Arslan, S. (2024). Decoding dietary myths: The role of ChatGPT in modern nutrition. Clinical Nutrition ESPEN, 60, 285-288. https://doi.org/10.1016/j.clnesp.2024.02.022
4. Arslan, S. (2025). ChatGPT is no nutrition encyclopedia, but does it need to be?. Clinical Nutrition ESPEN, 66, 213-214. https://doi.org/10.1016/j.clnesp.2025.01.055
5. Başer, M. Y., & Olcay, A. (2022). Akıllı turizmde yapay zekâ teknolojisi. Gaziantep University Journal of Social Sciences, 21(3), 1795-1817. https://doi.org/10.21547/jss.1084783
6. Baykasoğlu, A., Taşkıran, D., & Akkoyun, H. G. (2016). Toplu beslenme için menü planlama karar destek sistemi geliştirilmesi ve uygulanması. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 31(1).
7. Benvenuti, L., & De Santis, A. (2020). Making a sustainable diet acceptable: an emerging programming model with applications to schools and nursing homes menus. Frontiers in Nutrition, 7, 562833. https://doi.org/10.3389/fnut.2020.562833
8. Beslenme Bilgi Sistemi (BeBiS). (2021). Versiyon 9, İstanbul.

9. Berendsen, A. A., Kramer, C. S., & De Groot, L. C. (2019). The newly developed elderly nutrient-rich food score is a useful tool to assess nutrient density in European older adults. Frontiers in nutrition, 6, 119. https://doi.org/10.3389/fnut.2019.00119
10. Berendsen, A. M., Kang, J. H., Feskens, E. J., de Groot, C. P. G. M., Grodstein, F., & van de Rest, O. (2018). Association of long-term adherence to the mind diet with cognitive function and cognitive decline in American women. The Journal of Nutrition, Health & Aging, 22(2), 222-229. https://doi.org/10.1007/s12603-017-0909-0
11. Buckinx, F., Allepaerts, S., Paquot, N., Reginster, J. Y., De Cock, C., Petermans, J., & Bruyère, O. (2017). Energy and nutrient content of food served and consumed by nursing home residents. The Journal of Nutrition, Health & Aging, 21, 727-732.
12. Burger, C., Kiesswetter, E., Gietl, A., Pfannes, U., Arens-Azevêdo, U., Sieber, C. C., & Volkert, D. (2017). Size matters! Differences in nutritional care between small, medium and large nursing homes in Germany. The Journal of Nutrition, Health & Aging, 21(4), 464-472. https://doi.org/10.1007/s12603-016-0767-1
13. Burger, C., Kiesswetter, E., Alber, R., Pfannes, U., Arens-Azevedo, U., & Volkert, D. (2019). Texture modified diet in German nursing homes: availability, best practices and association with nursing home characteristics. BMC geriatrics, 19, 1-11. https://doi.org/10.1186/s12877-019-1286-9
14. Carrier, N., West, G. E., & Ouellet, D. (2009). Dining experience, foodservices and staffing are associated with quality of life in elderly nursing home residents. JNHA-The Journal of Nutrition, Health and Aging, 13, 565-570. https://doi.org/10.1007/s12603-009-0108-8
15. Davutoğlu, N. A. C. İ., & Yıldız, E. (2020). Turizm 4.0'dan gastronomi 4.0'a giden yolda: Geleceğin restoranlari ve yönetimi. Akademik Sosyal Araştırmalar Dergisi, 8(109). https://doi.org/10.29228/asos.45504
16. Demirel, Y., Bilici, S., & Köksal, E. (2018). Özel ve devlet huzurevleri menülerinin kalite ve yeterlilik açısından değerlendirmesi. Beslenme ve Diyet Dergisi, 46(1), 24-29. https://doi.org/10.33076/2018.BDD.284
17. Dikmen, D., & Pekcan, G. (2013). Besin ögesi örüntü profili: toplu beslenme hizmeti veren kuruluşlarda uygulanan menülerin değerlendirilmesi. Beslenme ve Diyet Dergisi, 41(3), 234- 241.
18. Doğan, M. (2022). Menü planlama ve standart reçeteler. In Toplu Beslenme Sistemleri ve Catering Hizmetleri Yönetimi. Nobel Akademik Yayınları, Ankara.
19. Dülgaroğlu, O. (2024). Turizmde teknolojileri ve robotlaşma yapay zekâ: Oğuzhan Dülgaroğlu. Uluslararası Turizm, Ekonomi ve İşletme Bilimleri Dergisi (IJTEBS) E-ISSN: 2602-4411, 8(2), 82-95.
20. Drewnowski, A. (2009). Defining nutrient density: development and validation of the nutrient rich foods ındex. Journal of the American College of Nutrition, 28(4), 421S-426S. doi: https://doi.org/10.1080/07315724.2009.10718106
21. EFSA (2009). European food safety authority. review of labelling reference intake values-scientific opinion of the panel on dietetic products, nutrition and allergies on a request from the commission related to the review of labelling reference intake values for selected nutritional elements. EFSA J. 7:1008. https://doi.org/10.2903/j.efsa.20 09.1008
22. Ercan, F. (2020). Turizm pazarlamasında yapay zekâ teknolojilerinin kullanımı ve uygulama örnekleri. Ankara Hacı Bayram Veli Üniversitesi Turizm Fakültesi Dergisi, 23(2), 394-410. 1 https://doi.org/0.34189/tfd.23.02.009
23. Ersoy, S., & Derin, D. Ö. (2023). Yapay zekanın beslenme biliminde kullanımı. Sağlık Bilimlerinde Yapay Zeka Dergisi, 3(2), 9-13.
24. Erul, E., & Işın, A. (2023). ChatGPT ile sohbetler: Turizmde ChatGPT’nin önemi (Chats with ChatGPT. Journal of Tourism and Gastronomy Studies, 11(1), 780-793. https://doi.org/10.21325/jotags.2023.1217
25. Fonseca, S. C. F., Barroso, S. C., & Santos, M. C. T. (2024). Enhancing elderly nutrition: a qualitative evaluation of menus in a social solidarity ınstitution in the North of Portugal. Nutrients, 16(5), 753. https://doi.org/10.3390/nu16050753
26. Grøndahl, V. A., & Aagaard, H. (2016). Older people's involvement in activities related to meals in nursing homes. International Journal of Older People Nursing, 11(3), 204-213. https://doi.org/10.1111/opn.12111
27. Grieger, J. A., & Nowson, C. A. (2007). Nutrient intake and plate waste from an Australian residential care facility. European journal of clinical nutrition, 61(5), 655-663. https://doi.org/10.1038/sj.ejcn.1602565
28. Hosking, D. E., Eramudugolla, R., Cherbuin, N., & Anstey, K. J. (2019). MIND not Mediterranean diet related to 12-year incidence of cognitive impairment in an Australian longitudinal cohort study. Alzheimer's & Dementia, 15(4), 581-589. https://doi.org/10.1016/j.jalz.2018.12.011
29. Irie, K., Fujii, N., Kokuryo, D., & Kaihara, T. (2020). A Study on Menu Planning Method for Managed Meal-Consideration of the Cost of Ordering Ingredients. In Advances in Production Management Systems. Towards Smart and Digital Manufacturing: IFIP WG 5.7 International Conference, APMS 2020, Novi Sad, Serbia, August 30–September 3, 2020, Proceedings, Part II (pp. 679-685). Springer International Publishing. https://doi.org/10.1007/978-3-030-57997-5_78
30. Karube, K., Yamada, T., Takanokura, M., Kakehi, M., & Taki, S. (2016). Analysis and improvement plans for rehabilitation schedule and service times: A day care nursing home. In The 13th International Conference on Industrial Management, Japan, Hiroshima.
31. Kılınç, G. E. (2024). Yapay Zekâ ve Beslenme. Sağlık & Bilim 2024: Beslenme-I, 7.Efeakademi Yayınları, İstanbul.
32. Kıvrak, O., Çelik, C., Hatipoğlu, S., & Koç, K. (2024). Yapay Zeka Destekli Gastronomi Turizmi: Turistlerin Damak Tadına Göre Kişisel Restoran Öneri Sistemleri. With Contributions of Tudam, 26.
33. Lavriša, Ž., Pravst, I., Krušič, S., Hren, N., Gregorič, N., Hren, I., ... & Hristov, H. (2024). Nutrition among nursing home residents: results from the NutriCare study. Frontiers in Nutrition, 11, 1423658. https://doi.org/10.3389/fnut.2024.1423658
34. Leij-Halfwerk, S., Verwijs, M. H., van Houdt, S., Borkent, J. W., Guaitoli, P. R., Pelgrim, T., ... & MaNuEL Consortium. (2019). Prevalence of protein-energy malnutrition risk in European older adults in community, residential and hospital settings, according to 22 malnutrition screening tools validated for use in adults≥ 65 years: a systematic review and meta-analysis. Maturitas, 126, 80-89. https://doi.org/10.1016/j.maturitas.2019.05.006
35. Lengyel, C. O., Zello, G. A., Smith, J. T., & Whiting, S. J. (2003). Evaluation of menu and food service practices of long-term care facilities of a health district in Canada. Journal of Nutrition for the Elderly, 22(3), 29-42. https://doi.org/10.1300/J052v22n03_03
36. Lin, G., Tang, J., Zeng, Y., Zhang, L., Ouyang, W., & Tang, Y. (2025). Association of serum n-3 and n-6 docosapentaenoic acids with cognitive performance in elderly adults: National Health and Nutrition Examination Survey 2011–2014. The Journal of Nutritional Biochemistry, 135, 109773. https://doi.org/10.1016/j.jnutbio.2024.109773
37. Milà, R., Abellana, R., & Farran, A. (2009). Nutritional assessment of the menus in five geriatric homes and their adaptation to the recomended intakes for the elderly population. Actividad Dietética, 13(02), 51-8.
38. McEvoy, C. T., Guyer, H., Langa, K. M., & Yaffe, K. (2017). Neuroprotective diets are associated with better cognitive function: the health and retirement study. Journal of the American Geriatrics Society, 65(8), 1857-1862. https://doi.org/10.1111/jgs.14922
39. Newberry, C., & Dakin, G. (2021). Nutrition and weight management in the elderly. Clinics in Geriatric Medicine, 37(1), 131-140. https://doi.org/10.1016/j.cger.2020.08.010
40. NNR. Nordic Council of Ministers. Nordic Nutrition Recommendations (2012). Integrating Nutrition and Physical Activity. Copenhagen K: Nordic Council of Ministers (2014).
41. Oruç, K. O. (2014). Bulanık hedef programlama ile menü planlama. Journal of Management and Economics Research, 12(23), 33-51. http://dx.doi.org/10.11611/JMER242
42. Rahayu, S., Daulima, N. H. C., & Putri, Y. S. E. (2018). The experience of older people living in an elderly residential home (Panti Sosial Tresna Werdha): a phenomenology. Enfermeria clinica, 28(1), 79-82. https://doi.org/10.1016/S1130-8621(18)30042-1
43. Rodríguez-Rejón, A. I., Ruiz-López, M. D., Malafarina, V., Puerta, A., Zuñiga, A., & Artacho, R. (2017). Menus offered in long-term care homes: Quality of meal service and nutritional analysis. Nutrición Hospitalaria, 34(3), 584-592. http://dx.doi.org/10.20960/nh.941
44. Topal, G. G., Sevim, S., Gumus, D., & Kizil, M. (2018). Evaluation of the adherence to the mind diet of different nursing homes in Ankara. Journal of nutrition, health & aging, 22(2), 222-9.
45. Türkay, B. (2024). Turist tipolojisine göre tur planlamasında yapay zekâ teknolojisinin kullanımı: Sürdürülebilir yaratıcı turizm ve eko-gastronomi deneyimi üzerine karşılaştırmalı bir uygulama (Use of Artificial Intelligence Technology in Tour Planning According to Tourist. Journal of Tourism & Gastronomy Studies, 12(3), 1876-1896. https://doi.org/10.21325/jotags.2024.1466
46. Türkiye İstatistik Kurumu (TÜİK). (2023). İstatistiklerle Yaşlılar, 2023. https://data.tuik.gov.tr/Bulten/Index?p=Istatistiklerle-Yaslilar-2023-53710#:~:text=T%C3%9C%C4%B0K%20Kurumsal&text=Ya%C5%9Fl%C4%B1%20n%C3%BCfus%20olarak%20kabul%20edilen,10%2C2'ye%20y%C3%BCkseldi.
47. Türkiye Beslenme Rehberi, TÜBER (2022). T.C. Sağlık Bakanlığı Yayın No: 1031, Ankara. Ülker, İ., & Çamli, A. (2023). Beslenme ve diyetetik uygulamalarında yapay zeka. Beslenme ve Diyet Dergisi, 51(2), 76-84. https://doi.org/10.33076/2023.BDD.1730
48. Yiğit, S. (2023). Yapay zekâ gastronomi eğitimine katkı sunabilir mi? ChatGPT Örneği (Can Artificial Intelligence Contribute to Gastronomy Education? Example of ChatGPT). Journal of Tourism & Gastronomy Studies, 11(3), 1970-1982. https://doi.org/10.21325/jotags.2023.1276
49. Waimaleongora‐ek, P., & Prinyawiwatkul, W. (2021). Comparison of discriminability of common food acceptance scales for the elderly. International Journal of Food Science & Technology, 56(1), 148-157. https://doi.org/10.1111/ijfs.14614