Comparison of AI Models for Data Extraction in Glucometers

Genivaldo Braynner Teixeira do Carmo; Julyanne Maria dos Santos Correia; Ronaldo Rodrigues da Silva Filho; Pablo Azevedo Sampaio; Robson Wagner Albuquerque de Medeiros

doi:10.22456/2175-2745.142648

Authors

Genivaldo Braynner Teixeira do Carmo Universidade Federal Rural de Pernambuco (UFRPE) https://orcid.org/0009-0008-5479-3014
Julyanne Maria dos Santos Correia Universidade Federal Rural de Pernambuco (UFRPE) https://orcid.org/0009-0001-0805-157X
Ronaldo Rodrigues da Silva Filho Universidade Federal Rural de Pernambuco (UFRPE) https://orcid.org/0009-0003-1700-1595
Pablo Azevedo Sampaio Universidade Federal Rural de Pernambuco (UFRPE)
Robson Wagner Albuquerque de Medeiros Universidade Federal Rural de Pernambuco (UFRPE) https://orcid.org/0000-0001-5870-1510

DOI:

https://doi.org/10.22456/2175-2745.142648

Keywords:

diabetes monitoring, artificial intelligence, prompt engineering, glucose meter data extraction

Abstract

Diabetes is a chronic condition that requires continuous monitoring of blood glucose levels, making glucose meters essential tools for managing patients’ health. This study compares three Artificial Intelligence models — Gemini, GPT-4o, and Llava 1.5 — to identify which one extracts glucose, date, and time data from these devices’ images with greater accuracy and efficiency. Through prompt engineering techniques, the aim is to optimize the extraction process, making it more reliable and automated, contributing to more precise and accessible glucose monitoring.

Downloads

Download data is not yet available.

References

[1] International Diabetes Federation. IDF Diabetes Atlas. 10th ed. International Diabetes Federation, 2021. Disponível em: ⟨https://www.diabetesatlas.org⟩.

[2] SAEEDI, P. et al. Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: Results from the International Diabetes Federation Diabetes Atlas, 9th edition. Diabetes Research and Clinical Practice, v. 157, p. 107843, 2019.

[3] SOHN, J.; HO, W. Cellular and systemic mechanisms for glucose sensing and homeostasis. Pflügers Archiv - European Journal of Physiology, v. 472, p. 1547–1561, 2020.

[4] POLONSKY, W. H. et al. Structured self-monitoring of blood glucose significantly reduces A1C levels in poorly controlled, noninsulin-treated type 2 diabetes: Results from the structured testing program study. Diabetes Care, v. 34, n. 2, p. 262–267, 2011.

[5] NERY, M. Hipoglicemia como fator complicador no tratamento do diabetes melito tipo 1. Arquivos Brasileiros de Endocrinologia e Metabologia, 2008.

[6] DHATARIYA LEONOR CORSINO, G. E. U. K. Management of diabetes and hyperglycemia in hospitalized patients. MDText.com, Inc., 2000.

[7] MARIO, C. D. et al. Role of continuous glucose monitoring in diabetic patients at high cardiovascular risk: an expert-based multidisciplinary Delphi consensus. Cardiovascular Diabetology, v. 21, p. 164, 2022.

[8] National Institute of Diabetes and Digestive and Kidney Diseases. Blood Glucose Control Studies for Type 1 Diabetes: DCCT EDIC. 2023. Accessed: 2024-09-09. Disponível em: ⟨https://www.niddk.nih.gov/about-niddk/research-areas/diabetes/blood-glucose-control-studies-type-1-diabetes-dcct-edic⟩.

[9] SKYLER, J. S. Effects of glycemic control on diabetes complications and on the prevention of diabetes. Clinical Diabetes, v. 22, n. 4, p. 162–166, 2004.

[10] WEINSTOCK, R. S. et al. The role of blood glucose monitoring in diabetes management. ADA Clinical Compendia, v. 2020, n. 3, p. No Pagination Specified, 2020.

[11] BRUEN, D. et al. Glucose sensing for diabetes monitoring: Recent developments. Sensors, v. 17, n. 8, 2017. ISSN 1424-8220. Disponível em: ⟨https://www.mdpi.com/1424-8220/17/8/1866⟩.

[12] KASWAN, K. S. et al. Generative AI: A review on models and applications. 2023 International Conference on Communication, Security and Artificial Intelligence (ICCSAI), 2023.

[13] ALQAHTANI, H.; KAVAKLI-THORNE, M.; KUMAR, G. Applications of generative adversarial networks (GANs): An updated review. Archives of Computational Methods in Engineering, v. 28, p. 525–552, 2021.

[14] ROMAGNOLI, A. et al. Healthcare systems and artificial intelligence: Focus on challenges and the international regulatory framework. Pharmaceutical Research, v. 41, p. 721–730, 2024.

[15] CAIN, W. Prompting change: Exploring prompt engineering in large language model AI and its potential to transform education. TechTrends, v. 68, p. 47–57, 2024.

[16] RATNAYAKE, H.; WANG, C. A prompting framework to enhance language model output. In: LIU, T. et al. (Ed.). AI 2023: Advances in Artificial Intelligence. Singapore: Springer, 2024. (Lecture Notes in Computer Science, v. 14472).

[17] Accu-Chek. Monitor de Glicemia Accu-Chek Guide. ⟨https://www.accu-chek.com.br/monitores-de-glicemia/guide⟩. Accessed: September 14, 2024.

[18] SHOMEE, H. H.; SAMS, A. License plate detection and recognition system for all types of Bangladeshi vehicles using multi-step deep learning model. In: 2021 Digital Image Computing: Techniques and Applications (DICTA). [S.l.: s.n.], 2021. p. 01–07.

[19] MITCHELL, M. et al. Midge: Generating image descriptions from computer vision detections. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics. [S.l.: s.n.], 2012. p. 747–756.

[20] TUMANYAN, N. et al. Plug-and-play diffusion features for text-driven image-to-image translation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. [S.l.: s.n.], 2023. p. 1921–1930.

[21] NITAYAVARDHANA, P. et al. Streamlining data recording through optical character recognition: A prospective multi-center study in intensive care units. Critical Care, v. 29, n. 1, p. 117, 2025.

[22] LOBO, P. et al. Smart scan of medical device displays to integrate with a mHealth application. Heliyon, v. 9, n. 6, p. e16297, 2023.