1. MMC
  2. All Volumes and Issues
  3. Volume 13, Number 1, 2026
  4. Unsupervised Learning for Optimal Personalized Dietary Menus to Prevent Diabetes and Cardiovascular Diseases

Unsupervised Learning for Optimal Personalized Dietary Menus to Prevent Diabetes and Cardiovascular Diseases

MMC.
2026;
Volume 13, Number 1
: pp. 1–32
Received: November 06, 2025
Revised: January 03, 2026
Accepted: January 11, 2026

Bouhanch Z., Ahourag A., Lahbabi H., El Moutaouakil K., Ouzineb M., Cheggour M., Chellak S., Baizri H.  Unsupervised Learning for Optimal Personalized Dietary Menus to Prevent Diabetes and Cardiovascular Diseases.  Mathematical Modeling and Computing. Vol. 13, No. 1, pp. 1–32 (2026)

Authors:
  1. Z. Bouhanch
  2. A. Ahourag
  3. H. Lahbabi
  4. K. El Moutaouakil
  5. M. Ouzineb
  6. M. Cheggour
  7. S. Chellak
  8. H. Baizri
1
Laboratory of Mathematics and Data Science, Polydisciplinary Faculty of Taza, Sidi Mohamed Ben Abdellah University of Fez, Taza, Morocco
2
Laboratory of Mathematics and Data Science, Polydisciplinary Faculty of Taza, Sidi Mohamed Ben Abdellah University of Fez, Taza, Morocco
3
Laboratory of Mathematics and Data Science, Polydisciplinary Faculty of Taza, Sidi Mohamed Ben Abdellah University of Fez, Taza, Morocco
4
Laboratory of Mathematics and Data Science, Polydisciplinary Faculty of Taza, Sidi Mohamed Ben Abdellah University of Fez, Taza, Morocco
5
National Institute for Statistics and Applied Economics, Rabat, Morocco
6
Department of Biology, Cadi Ayyad University, Semlalia, Marrakech, Morocco
7
Department of Biology, Cadi Ayyad Universityy, Semlalia, Marrakech, Morocco
8
Biosciences and Health Research Laboratory, Diabetes and Metabolic Diseases Endocrinology Service, Avicenne Military Hospital, FMP, UCA of Marrakech, Morocco

Healthy diets can slow disease progression, but their effectiveness may decrease.  Patients often give up these diets due to limited food choices, unappetizing meals, and reduced physical activity from cutting calories.  To address this, we developed an intelligent nutritional balance system to prevent cardio-diabetic diseases.  This system creates diets that optimize cholesterol and glycemic control through the following steps: (a) Characterizing Moroccan foods based on 19 nutrients and their glycemic load, (b) Classifying foods using a Gaussian mixture model, (c) Modeling the optimal diet with a fuzzy mathematical model using recommendations from the WHO, USDA, and FAO, (d) Solving the model with a genetic algorithm, (e) Translating portions and food groups to meet constraints, and (f) Resolving the final model using the backtracking method.  We implemented this strategy based on the main foods consumed in Morocco, considering different levels of belief (0.25, 0.5, 0.75) regarding the glycemic load of these foods.  The results show that the custom artificial diets align with WHO, USDA, FAO, and DGA recommendations.  The menus are flexible, allowing for substituting expensive or rare foods with more affordable and readily available alternatives without compromising the quality of the diets.

Gaussian Mixture Model (GMM)
Fuzzy CMeans (FCM)
ranking function
glycemic load
total cholesterol
genetic algorithm (GA)
Fuzzy Optimization Programming (FOP)
Constraint Satisfaction Programming (CSP)
  1. Diet and physical activity: a public health priority.  World Health Organization (2021).
  2. WHO and FAO announce global initiative to promote consumption of fruit and vegetables.  World Health Organization (2003).
  3. Food information to consumers – legislation.  EU (2017).
  4. Lopez A. D., Mathers C. D., Ezzati M., Jamison D. T., Murray C. J.  Global and regional burden of disease and risk factors, 2001: systematic analysis of population health data.  Lancet.  367 (9524), 1747–1757 (2006).
  5. Hebden L., O'Leary F., Rangan A., Singgih Lie E., Hirani V., Allman-Farinelli M.  Fruit consumption and adiposity status in adults: A systematic review of current evidence.  Critical Reviews in Food Science and Nutrition.  57 (12), 2526–2540 (2017).
  6. Shmerling R. H.  When dieting doesn't work.  Harvard Health Publishing (2020).
  7. https://www.health.harvard.edu/blog/when-dieting-doesnt-work-2020052519889.
  8. Kruger J., Blanck H. M., Gillespie C.  Dietary and physical activity behaviors among adults successful at weight loss maintenance.  International Journal of Behavioral Nutrition and Physical Activity.  3 (1), 17 (2006).
  9. Khan M. A. B., Hashim M. J., King J. K., Govender R. D., Mustafa H., Al-Kaabi J. M.  Epidemiology of type 2 diabetes–global burden of disease and forecasted trends.  Journal of Epidemiology and Global Health.  10 (1), 107–111 (2020).
  10. Slyper A., Jurva J., Pleuss J., Hoffmann R., Gutterman D.  Influence of glycemic load on HDL cholesterol in youth.  The American Journal of Clinical Nutrition.  81 (2), 376–379 (2005).
  11. Soltani M., Gerami S., Far Z. G., Rajabzadeh-Dehkordi M., Dehzad M. J., Najafi M., Faghih S.  Higher Glycemic Index and Load Could Increase Risk of Dyslipidemia.  International Journal of Nutrition Sciences.  8 (3), 150–157 (2023).
  12. Fernandes A. C., Marinho A. R., Lopes C., Ramos E.  Dietary glycemic load and its association with glucose metabolism and lipid profile in young adults.  Nutrition, Metabolism and Cardiovascular Diseases.  32 (1), 125–133 (2022).
  13. American Heart Association.  Cholesterol and Cardiovascular Disease.  https://www.heart.org (2021).
  14. Dantzig G.  Linear Programming and Extensions.  Princeton University Press, United States of America (2016).
  15. Orešković P., Kljusurić J. G., Šatalić Z.  Computer generated vegan menus: The importance of food composition data base choice.  Journal of Food Composition and Analysis. 37, 112–118 (2015).
  16. Masset G., Monsivais P., Maillot M., Darmon N., Drewnowski A.  Diet optimization methods can help translate dietary guidelines into a cancer prevention food plan.  The Journal of Nutrition.  139 (8), 1541–1548 (2009).
  17. Donati M., Menozzi D., Zighetti C., Rosi A., Zinetti A., Scazzina F.  Towards a sustainable diet combining economic, environmental and nutritional objectives.  Appetite.  106, 48–57 (2016).
  18. Van Mierlo K., Rohmer S., Gerdessen J. C.  A model for composing meat replacers: Reducing the environmental impact of our food consumption pattern while retaining its nutritional value.  Journal of Cleaner Production.  165, 930–950 (2017).
  19. Taniguchi E.  Concepts of city logistics for sustainable and liveable cities.  Procedia – Social and Behavioral Sciences.  151, 310–317 (2014).
  20. Koenen M. F., Balvert M., Fleuren H.  Bi-objective goal programming for balancing costs vs. nutritional adequacy.  Frontiers in Nutrition.  9, 1056205 (2022).
  21. Bas E.  A robust optimization approach to diet problem with overall glycemic load as objective function.  Applied Mathematical Modelling.  38 (19–20), 4926–4940 (2014).
  22. El Moutaouakil K., Ahourag A., Chakir S., Kabbaj Z., Chellack S., Cheggour M., Baizri H.  Hybrid firefly genetic algorithm and integral fuzzy quadratic programming to an optimal Moroccan diet.  Mathematical Modeling and Computing.  10 (2), 338–350 (2023).
  23. El Moutaouakil K., Ahourag A., Chellak S., Cheggour M., Baizri H., Bahri A.  Quadratic Programming and Triangular Numbers Ranking to an Optimal Moroccan Diet with Minimal Glycemic Load.  Statistics, Optimization & Information Computing.  11 (1), 85–94 (2023).
  24. El Moutaouakil K., Ahourag A., Chellak S., Baïzri H., Cheggour M.  Fuzzy Deep Daily Nutrients Requirements Representation.  Revue d'Intelligence Artificielle.  36 (2), 263–269 (2022).
  25. El Moutaouakil K., Saliha C., Hicham B.  Optimal fuzzy deep daily nutrients requirements representation: Application to optimal Morocco diet problem.  Mathematical Modeling and Computing.  9 (3), 607–615 (2022).
  26. O'Brien K. O., Zavaleta N., Caulfield L. E., Wen J., Abrams S. A.  Prenatal Iron Supplements Impair Zinc Absorption in Pregnant Peruvian Women.  The Journal of Nutrition.  130 (9), 2251–2255 (2022).
  27. Weaver C. M., Gordon C. M., Janz K. F., Kalkwarf H. J., Lappe J. M., Lewis R., O'Karma M., Wallace T. C., Zemel B. S.  The National Osteoporosis Foundation's position statement on peak bone mass development and lifestyle factors: a systematic review and implementation recommendations.  Osteoporosis International.  27, 1281–1386 (2016).
  28. Zimmermann M. B., Chassard C., Rohner F., N'Goran E. K., Nindjin C., Dostal A., Utzinger J., Ghattas H., Lacroix C., Hurrell R. F.  The effects of iron fortification on the gut microbiota in African children: a randomized controlled trial in Côte d'Ivoire.  The American Journal of Clinical Nutrition.  92 (6), 1406–1415 (2010).
  29. U.S. Department of Health and Human Services and U.S. Department of Agriculture. Dietary guidelines for Americans (2005).
  30. El Moutaouakil K., El Ouissari A., Palade V., Charroud A., Olaru A., Baïzri H., Chellak S., Cheggour M.  Multi-Objective Optimization for Controlling the Dynamics of the Diabetic Population.  Mathematics.  11 (13), 2957 (2023).
  31. El Moutaouakil K., Palade V., Safouan S., Charroud A.  FP-Conv-CM: Fuzzy Probabilistic Convolution C-Means.  Mathematics.  11 (8), 1931 (2023).
  32. Ahourag A., El Moutaouakil K., Chellak S., Baizri H., Cheggour M.  Multi-criteria optimization for optimal nutrition of Moroccan diabetics.  2022 International Conference on Intelligent Systems and Computer Vision (ISCV).  1–6 (2022).
  33. Mohiuddin A., Seraj R., Islam S. M. S.  The $k$-means algorithm: A comprehensive survey and performance evaluation.  Electronics.  9 (8), 1295 (2020).
  34. Ahourag A., El Moutaouakil K., Cheggour M., Chellak S., Baizri H.  Multiobjective Optimization to Optimal Moroccan Diet Using Genetic Algorithm.  International Journal for Engineering Modelling.  36 (1), 67–79 (2023).
  35. El Moutaouakil K., Saliha C., Hicham B., Mouna C.  Intelligent Local Search Optimization Methods to Optimal Morocco Regime.  IntechOpen (2003).
  36. Nama S., Sharma S., Saha A. K., Gandomi A. H.  A quantum mutation-based backtracking search algorithm.  Artificial Intelligence Review.  55, 3019–3073 (2022).
  37. Kim J.-H., Kim K.-H., Yoo S.-H.  Evaluating and ranking the mining damage prevention programs in South Korea: An application of the fuzzy set theory.  Resources Policy.  78, 102873 (2022).
  38. El Moutaouakil K., Cheggour M., Chellak S., Baizri H.  Metaheuristics Optimization Algorithm to an Optimal Moroccan Diet.  2021 7th Annual International Conference on Network and Information Systems for Computers (ICNISC).  364–368 (2021).
  39. Bas E.  A three-step methodology for GI classification, GL estimation of foods by fuzzy c-means classification and fuzzy pattern recognition, and an LP-based diet model for glycaemic control.  Food Research International.  83, 1–13 (2016).
  40. Nitesh S., Chawda B., Vasant A.  An improved $K$-medoids clustering approach based on the crow search algorithm.  Journal of Computational Mathematics and Data Science.  3, 100034 (2022).
  41. Goldberg D. E.  Genetic Algorithms in Search, Optimization, and Machine Learning.  Addison-Wesley, Reading (1989).
  42. Agushaka J. O., Ezugwu A. E., Abualigah L., Alharbi S. K., Khalifa H. A. E.-W.  Efficient initialization methods for population-based metaheuristic algorithms: a comparative study.  Archives of Computational Methods in Engineering.  30 (3), 1727–1787 (2023).
  43. Sharma S., Kumar V.  Application of Genetic Algorithms in Healthcare: A Review.  Next Generation Healthcare Informatics.  75–86 (2022).
  44. Zhou J., Hua Z.  A correlation guided genetic algorithm and its application to feature selection.  Applied Soft Computing.  123, 108964 (2022).
  45. Bäck Th., Eiben A. E., van der Vaart N. A. L.  An empirical study on gas without parameters.  Parallel Problem Solving from Nature PPSN VI. 315–324 (2000).
  46. Galván-López E., McDermott J., O'Neill M., Brabazon A.  Towards an understanding of locality in genetic programming.  GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computation.  901–908 (2010).
  47. De Jong K. A.  Evolutionary Computation. MIT Press, Cambridge, MA (2002).
  48. Crepinsek M., Liu S. H., Mernik M.  Exploration and exploitation in evolutionary algorithms: A survey.  ACM Computing Surveys (CSUR).  45 (3), 35 (2013).
  49. Sharma H. K., Majumder S., Biswas A., Prentkovskis O., Kar S., Skačkauskas P.  A Study on Decision-Making of the Indian Railways Reservation System during COVID-19.  Journal of Advanced Transportation.  2022,  7685375 (2022).
  50. Sivanandam S. N., Deepa S. N.  Principles of Soft Computing.  Wiley, New Delhi (2013).
  51. Zhou J., Hua Z.  A correlation guided genetic algorithm and its application to feature selection.  Applied Soft Computing.  123, 108964 (2022).
  52. Umbarkar A. J., Sheth P. D.  Crossover operators in genetic algorithms: a review.  ICTACT Journal on Soft Computing.  6 (1), 1083–1092 (2015).
  53. Vasconcelos J. A., Ramirez J. A., Takahashi R. H. C., Saldanha R. R.  Improvements in genetic algorithms.  IEEE Transactions on Magnetics.  37 (5), 3414–3417 (2001).
  54. Biere A., Heule M., Van Maaren H., Walsh T. (Eds.).  Handbook of Satisfiability. Vol. 185. IOS Press (2009). 
  55. Watson D.  A Practical Approach to Compiler Construction.  Springer Cham (2017).
  56. Programme Al-Khawarizmi:  Liste des 45 projets retenus pour financement.
  57. Nachate S., Kabbaj Z., Chakir S., Idrissi A., El Moutaouakil K., Baizri H., Cheggour M., Chellak S.   Quelles méthodes d’enquête alimentaire pour les diabétiques de type 2?  Annales d'Endocrinologie.  84 (1), 192 (2023).
  58. El Moutaouakil K., Yahyaouy A., Chellak S., Baizri H.  An optimized gradient dynamic-neuro-weighted-fuzzy clustering method: Application in the nutrition field.  International Journal of Fuzzy Systems.  24, 3731–3744 (2022).
  59. El Ouissari A., El Moutaouakil K.  Genetic algorithm applied to fractional optimal control of a diabetic patient.  Ufa Mathematical Journal.  15 (3), 129–147 (2023).
  60. El Moutaouakil K., El Ouissari A., Baizri H., Chellak S., Cheggour M.  Multi-objectives optimization and convolution fuzzy C-means: control of diabetic population dynamic.  RAIRO, Operations Research.  56 (5), 3245–3256 (2022).
  61. Asenjo Conrado F.  Variations in the nutritive values of foods.  The American Journal of Clinical Nutrition.  11 (5), 368–376 (1962).
  62. Fanzo J., McLaren R., Davis C., Choufani J.  Climate change and variability: What are the risks for nutrition, diets, and food systems?  International Food Policy Research Institute.  1645 (2017).
  63. Donhouedé J. C., Salako K. V., Assogbadjo A. E., Ribeiro-Barros A. I., Ribeiro N.  The relative role of soil, climate, and genotype in the variation of nutritional value of Annona senegalensis fruits and leaves.  Heliyon.  9 (8), e19012 (2023).