Contact : 9561854529 Email : submitpaper@ijaea.com editorinchief.ijaea@gmail.com Working Hours: 9am to 9PM

International Journal of Advanced Engineering Application

ISSN: 3048-6807

Submit Paper Apply for Reviewer

Leveraging Computer Vision and Machine Learning for Automated Meal-Related Insulin Dosage in Diabetes Management

Author(s):Achintya Pandey1, Khushi Pal2, Harsh Kumar Sharma3, Anjali Singh4, Harsh Vikram Srivastav5

Affiliation: 1,2,3,4,5AKTU University, Ajay Kumar Garg Engineering College, Ghaziabad, India

Page No: 43-53

Volume issue & Publishing Year: Volume 2 Issue 5 ,May-2025

Journal: International Journal of Advanced Engineering Application (IJAEA)

ISSN NO: 3048-6807

DOI: https://doi.org/10.5281/zenodo.17763314

Download PDF

Article Indexing:

Abstract:
Effective management of meal-related insulin dosing remains a critical challenge in diabetes care, often leading
to errors that can significantly impact glycemic control and longterm health outcomes. This study proposes an advanced
solution to address these challenges by integrating computer vision and machine learning technologies into diabetes
management. The research begins by thoroughly analysing the limitations of current insulin dosing practices, with a focus
on identifying common errors and their consequences on patient health. Extensive data collection and user experience
analysis are conducted to gain a comprehensive understanding of existing practices and inform the design of a more
accurate, efficient system. The proposed system is designed to leverage image recognition to identify various food items and
accurately estimate their macronutrient content. Based on these estimations, the system calculates individualized insulin
doses tailored to each users specific insulin sensitivity and needs. To ensure safety and minimize risks, robust error checking
mechanisms are incorporated, emphasizing accuracy and reliability in the insulin dosing process. This research
demonstrates the potential of combining machine learning and computer vision to improve the precision and personalization
of insulin dosing. The proposed solution offers a promising advancement in diabetes care, with the potential to significantly
enhance patient quality of life by reducing dosing errors and optimizing glycemic control.

Keywords: Diabetes management, Meal-related insulin administration, Image recognition, Macronutrient estimation, LeNet-5

Reference:

  • [1] T. Kushner, M. D. Breton, and S. Sankaranarayanan, “Multi-hour blood glucose prediction in type 1 diabetes: A patient-specific approach using shallow neural network models,” Diabetes Technol. Ther., vol. 22, no. 12, pp. 883–891, 2020.
  • [2] K. Cresswell, M. Callaghan, S. Khan, Z. Sheikh, H. Mozaffar, and A. Sheikh, “Investigating the use of data-driven artificial intelligence in computerised decision support systems for health and social care: A systematic review,” Health Informatics J., vol. 26, no. 3, pp. 2138–2147, 2020.
  • [3] A. K. Patra and A. Nanda, “An automatic insulin infusion system based on Kalman filtering model predictive control technique,” J. Dyn. Syst., Meas., Control, vol. 143, no. 2, p. 021004, 2021.
  • [4] A. K. Patra and P. K. Rout, “An automatic insulin infusion system based on LQG control technique,” Int. J. Biomed. Eng. Technol., vol. 17, no. 3, pp. 252–275, 2015.
  • [5] H. J. Hawas and K. Lewenstein, “The design of an insulin pump—Preliminary requirements,” in Recent Advances in Mechatronics. Berlin, Heidelberg: Springer, 2010, pp. 329–334.
  • [6] A. K. Patra and P. K. Rout, “Backstepping sliding mode Gaussian insulin injection control for blood glucose regulation in type I diabetes patient,” J. Dyn. Syst., Meas., Control, vol. 140, no. 9, p. 091006, 2018.
  • [7] A. J. Karter, U. Subramanian, C. Saha, J. C. Crosson, M. M. Parker, B. E. Swain, et al., “Barriers to insulin initiation: The translating research into action for diabetes insulin starts project,” Diabetes Care, vol. 33, no. 4, pp. 733–735, 2010.
  • [8] Y. Sokol, S. Lapta, K. Kolisnyk, V. Makarov, Y. Semerenko, M. Mikityuk, et al., “Automatic insulin correction system,” in Proc. 2022 IEEE 3rd KhPI Week Adv. Technol. (KhPIWeek), 2022, pp. 1–4.
  • [9] L. C. Harrison, M. C. Honeyman, C. E. Steele, N. L. Stone, E. Sarugeri, E. Bonifacio, et al., “Pancreatic β-cell function and immune responses to insulin after administration of intranasal insulin to humans at risk for type 1 diabetes,” Diabetes Care, vol. 27, no. 10, pp. 2348–2355, 2004.
  • [10] S. Bahendeka, R. Kaushik, A. B. Swai, F. Otieno, S. Bajaj, S. Kalra, et al., “EADSG guidelines: Insulin storage and optimisation of injection technique in diabetes management,” Diabetes Ther., vol. 10, pp. 341–366, 2019.
  • [11] S. M. Gharghory and D. A. El-Dib, “Fuzzy control system for regulating the blood glucose level of diabetes patients implemented on FPGA,” J. Circuits Syst. Comput., vol. 25, no. 12, p. 1650161, 2016.
  • [12] G. B. Bolli, D. Kerr, R. Thomas, E. Torlone, A. Sola-Gazagnes, E. Vitacolonna, et al., “Comparison of a multiple daily insulin injection regimen (basal once-daily glargine plus mealtime lispro) and continuous subcutaneous insulin infusion (lispro) in type 1 diabetes: A randomized open parallel multicenter study,” Diabetes Care, vol. 32, no. 7, pp. 1170–1176, 2009.
  • [13] P. Liu, X. Qiu, and X. Huang, “Recurrent neural network for text classification with multi-task learning,” arXiv preprint arXiv:1605.05101, 2016.
  • [14] S. Barro, A. Sanchez, and J. M. Vilar, “A semantic plagiarism–detection algorithm,” Inf. Sci., vol. 170, no. 1, pp. 70–81, 2005.
  • [15] A. Vaswani, N. Shazeer, N. Parmar, et al., “Attention is all you need,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2017.
  • [16] D. Jurafsky and J. H. Martin, *Speech and Language Processing*, 3rd ed. Pearson, 2019.