Araştırma Makalesi

A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction

Cilt: 5 Sayı: 1 27 Haziran 2025
PDF İndir
EN TR

A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction

Öz

Diabetes mellitus, a chronic disease affecting millions of people worldwide, requires monitoring and management of glucose levels to reduce the risks of hyperglycemia and hypoglycemia. Technological advancements have enabled the development of various digital tools, including continuous glucose monitors (CGMs) for effective management of this disease. However, these tools only provide alerts after glucose levels exceed critical thresholds, which causes delays in taking necessary precautions. To address this issue, various artificial intelligence (AI)-based models have been developed to predict glucose levels in advance. Traditional AI approaches, however, often rely on standardized datasets, limiting their ability to achieve the accuracy required for individualized treatment. Therefore, it is crucial to develop personalized prediction models that can be trained using the individual data of patients. Here, this paper introduces a personalized glucose prediction approach that employs a three-parameter unscented Kalman filter (UKF) to predict future glucose levels using CGM data, as well as basal and bolus insulin values. Experiments on OhioT1DM dataset show the advantage of our proposed approach over the baseline KF and UKF for glucose prediction in terms of Root Mean Square Error. Furthermore, the proposed approach is embedded into a custom-designed cross-platform smartphone application, GlucoThinker Advance, capable of providing offline access to the proposed personalized glucose prediction approach to ensure continuous support without requiring an internet connection.

Anahtar Kelimeler

Kaynakça

  1. S. Gül, E. Ü. Avdal, S. Önal, B. N. Dündar, B. Ö. Pamuk, and Z. Doğan, "Diyabette tıbbi bakım standartlarında değişiklikler," İzmir Katip Çelebi Üniversitesi Sağlık Bilimleri Fakültesi Dergisi, vol. 5, no. 1, pp. 25-29, 2020.
  2. D. J. Magliano and E. J. Boyko, "IDF Diabetes Atlas," 2022.
  3. W. H. Organization, Global diffusion of eHealth: making universal health coverage achievable: report of the third global survey on eHealth. World Health Organization, 2017.
  4. Ö. A. Koca, A. Türköz, and V. Kılıç, "Tip 1 Diyabette Çok Katmanlı GRU Tabanlı Glikoz Tahmini," Avrupa Bilim ve Teknoloji Dergisi, no. 52, pp. 80-86, 2023.
  5. L. Heinemann, "Continuous glucose monitoring (CGM) or blood glucose monitoring (BGM): interactions and implications," Journal of Diabetes Science and Technology, vol. 12, no. 4, pp. 873-879, 2018.
  6. Ö. A. Koca, H. Ö. Kabak, and V. Kılıç, "Attention-based multilayer GRU decoder for on-site glucose prediction on smartphone," The Journal of Supercomputing, vol. 80, no. 17, pp. 25616-25639, 2024.
  7. M. M. Kebede and C. R. Pischke, "Popular diabetes apps and the impact of diabetes app use on self-care behaviour: a survey among the digital community of persons with diabetes on social media," Frontiers in Endocrinology, vol. 10, p. 135, 2019.
  8. J. Daniels, P. Herrero, and P. Georgiou, "A multitask learning approach to personalized blood glucose prediction," IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 1, pp. 436-445, 2021.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Yapay Zeka (Diğer)

Bölüm

Araştırma Makalesi

Yayımlanma Tarihi

27 Haziran 2025

Gönderilme Tarihi

1 Ocak 2025

Kabul Tarihi

25 Mart 2025

Yayımlandığı Sayı

Yıl 2025 Cilt: 5 Sayı: 1

Kaynak Göster

APA
Ayfer, E., Koca, Ö. A., & Kılıç, V. (2025). A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction. Journal of Artificial Intelligence and Data Science, 5(1), 1-11. https://izlik.org/JA67KK89RK
AMA
1.Ayfer E, Koca ÖA, Kılıç V. A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction. Journal of Artificial Intelligence and Data Science. 2025;5(1):1-11. https://izlik.org/JA67KK89RK
Chicago
Ayfer, Ece, Ömer Atılım Koca, ve Volkan Kılıç. 2025. “A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction”. Journal of Artificial Intelligence and Data Science 5 (1): 1-11. https://izlik.org/JA67KK89RK.
EndNote
Ayfer E, Koca ÖA, Kılıç V (01 Haziran 2025) A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction. Journal of Artificial Intelligence and Data Science 5 1 1–11.
IEEE
[1]E. Ayfer, Ö. A. Koca, ve V. Kılıç, “A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction”, Journal of Artificial Intelligence and Data Science, c. 5, sy 1, ss. 1–11, Haz. 2025, [çevrimiçi]. Erişim adresi: https://izlik.org/JA67KK89RK
ISNAD
Ayfer, Ece - Koca, Ömer Atılım - Kılıç, Volkan. “A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction”. Journal of Artificial Intelligence and Data Science 5/1 (01 Haziran 2025): 1-11. https://izlik.org/JA67KK89RK.
JAMA
1.Ayfer E, Koca ÖA, Kılıç V. A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction. Journal of Artificial Intelligence and Data Science. 2025;5:1–11.
MLA
Ayfer, Ece, vd. “A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction”. Journal of Artificial Intelligence and Data Science, c. 5, sy 1, Haziran 2025, ss. 1-11, https://izlik.org/JA67KK89RK.
Vancouver
1.Ece Ayfer, Ömer Atılım Koca, Volkan Kılıç. A Comparative Analysis of Unscented Kalman Filter for Smartphone-Based Multi-Parametric Glucose Prediction. Journal of Artificial Intelligence and Data Science [Internet]. 01 Haziran 2025;5(1):1-11. Erişim adresi: https://izlik.org/JA67KK89RK