Vol. 24 No. 4 (2025): Mapana Journal of Sciences
Research Articles

Predictive Modeling for Blood Sugar Levels and Personalized Dietary Recommendations using Machine Learning Approach

  • Velmurugan S
Velmurugan S
Assistant Professor

Published 2025-12-19

Keywords

  • Machine learning, nutrition, diabetes, algorithm, patient, food recommendation

Copyright (c) 2025

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Abstract

The prevalence of diabetes and metabolic disorders is increasing globally, necessitating effective management of blood sugar levels. Advances in machine learning offer innovative solutions for predicting sugar levels and providing personalized food recommendations. Current treatments, including oral hypoglycemic agents and insulin, often have serious side effects. This research models the sugar content in food based on nutritional data, using machine learning to find relationships between nutrients like carbohydrates, starch, protein, fat, calcium, iodine, iron, potassium, and sugar levels. The model then recommends suitable foods based on an individual's blood sugar levels. Results show that the proposed model accurately predicts sugar content in food and provides appropriate recommendations for diabetic patients with 97% accuracy.

References

  1. Roshan Birjais and Ashish Kumar Mourya, "Prediction and diagnosis of future diabetes risk: a machine learning approach, "Springer Nature Switzerland, vol.1, no.1112,August 2019.
  2. Tabish SA, "Is Diabetes Becoming the Biggest Epidemic of the Twenty-first Century?," Int JHealthSci (Qassim), July 2007.
  3. Saeedi P and Petersohn I, "Global and regional diabetes prevalence estimates for 2019 andprojections for 2030 and 2045: Results from the International Diabetes Federation DiabetesAtlas,9th edition,"Elsevier B.V., vol.157, September2019.
  4. Osama Gheith and Nashwa Farouk, "Diabetic kidney disease: world wide difference ofprevalence," JournalofNephropharmacology,vol.5,pp.49-56,October2015.
  5. VatikaSibal, "Food: identity of culture and religion," ResearchGate, vol. 6, pp. 10908-10915, September2018.
  6. Kimber M Simmons and Aaron W Michels, "Type 1 diabetes: A predictable disease," WorldJournalofDiabetes,vol.6(3),pp.380-390, April2015.
  7. Lindy Kahanovitz, Patrick M. Sluss, and Steven J. Russell, "Type 1 Diabetes - A ClinicalPerspective,"Pointcare, pp. 37-40,March2017.
  8. Benito-Vicente A, Jebari S, Larrea-Sebal A, Siddiqi H, Uribe KB, Ostolaza H, Martín C. Galicia-GarciaU,"PathophysiologyofType2Diabetes Mellitus," Int JMolSci., August 2020.
  9. Asif Mohammad, "The prevention and control the type-2 diabetes by changing lifestyle and dietary pattern,"J Educ HealthPromot,Feb2014.
  10. Xiang AH, Page KA Buchanan TA, "Gestational diabetes mellitus: risks and management during and after pregnancy," NatRevEndocrinol, pp.639-649,November2012.
  11. Adelaide A. Bampoe-Addo, Stephen K. Armoo, Firibu K. Saalia, Francis Gatsi, Baffour Sarkodie-Mensah Robert A. Sowah, "Design and Development of Diabetes Management System UsingMachine Learning," International Journal of Telemedicine and Application, vol. 2020, p. 17, July2020.
  12. SalliahShafi Bhat and Gufran Ahmad Ansari, "Predictions of Diabetes and Diet RecommendationSystem for Diabetic Patients using Machine Learning Techniques," International Conference forEmergingTechnology, pp.1-5, May2021.
  13. Kushan De Silva, Siew Lim, and Aya Mousa, "Nutritional markers of undiagnosed type 2 diabetesin adults: Findings of a machine learning analysis with external validation and benchmarking,"PLOS ONE,p. 21, May2021.
  14. Hyerim Kim, Dong Hoon Lim , and Yoona Kim , "Classification and Prediction on the Effects ofNutritional Intake on Overweight/Obesity, Dyslipidemia, Hypertension and Type 2 DiabetesMellitus Using Deep Learning Model: 4–7th Korea National Health and Nutrition ExaminationSurvey," International Journal of Environmental Research and Public Health, vol. 18, no. 11, p.18,May2021.
  15. Yajie Guo, Zihua Huang, and Dan Sang, "The Role of Nutrition in the Prevention and Interventionof Type 2 Diabetes," Frontiers in Bioengineering and Biotechnology, vol. 8, p. 15, September2020.
  16. "Food Recommendation Using Machine Learning for Physical Activities in Patients with Type 1Diabetes,"17thScandinavianConferenceonHealthInformatics,pp.45-49, Nov2019.
  17. Raj Kumar B. and LathaK. , "DFRS: Diet food recommendation system for diabetic patientsbased on ontology," ternational Journal of Applied Engineering Research, vol. 10, pp. 2765-2770,January2015.
  18. FaizI. , Mukhtar H. , and Khan S. , "An integrated approach of diet and exerciserecommendations for diabetes patients," 2014 IEEE 16th International Conference on e-HealthNetworking,Applications andServices(Healthcom), pp. 537-542,2014.
  19. Esra’aAlshdaifat, Doa’aAlshdaifat, and Ayoub Alsarhan, "The Effect of PreprocessingTechniques, Applied to Numeric Features, on Classification Algorithms’ Performance," MDPI, p.23,January2021.
  20. Jie Cai, Jiawei Luo, and Shulin Wang, "Feature selection in machine learning: A newperspective,"Neurocomputing, vol. 300,pp.70-79,2018.
  21. Sevilla Joaquin, "Importance of input data normalization for the application of neural networksto complex industrial problems," Nuclear Science, IEEE Transactions on, vol. 44, pp. 1464-1468,July1997.