EUVIMEDEUVIMED entdecken
Crossref

CGM-Based Blood Glucose Prediction Model With LSTM Encoder–Decoder Architecture

He Xu, Yi Zhang, Sixing Liu, Yimu Ji, Ming Lv, Peng Li

IEEE Sensors Journal · 01.02.2025 · 25 (3) · 5824-5839

DOI: 10.1109/jsen.2024.3517554 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.02.2025. Verfasst von He Xu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Jiangsu Key Development Planning Project, Six Talent Peaks Project in Jiangsu Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate prediction of blood glucose levels is crucial for automated treatment in diabetic patients. This study proposes a blood glucose prediction model based on an improved attention mechanism within a long short-term memory (LSTM) encoder-decoder (Att-E-D) architecture to enhance blood glucose prediction performance significantly. Compared to traditional encoder-decoder (E-D) architectures, the core improvement of this study lies in introducing an attention mechanism combined with a dynamic time warping (DTW) similar sequence search algorithm. Specifically, during the decoding phase of the Att-E-D architecture, the DTW-based similar sequence search algorithm is first utilized to retrieve the n most matching similar sequences from historical blood glucose data for the target prediction sequence. Then, at each time step, different attention weights are assigned to the encoded information. This enables the model to selectively focus on historical feature information with higher similarity to the current step, effectively enhancing neuron memory and reducing error propagation. Finally, after processing through a fully connected layer, the model outputs a prediction sequence for blood glucose trends over a future period. To validate the generalization ability of the Att-E-D model, comparative experiments were conducted using datasets from two different continuous glucose monitoring (CGM) sensors. The results demonstrate that the Att-E-D model significantly outperforms support vector regression (SVR), LSTM, gated recurrent unit (GRU), bidirectional LSTM (Bi-LSTM), Bi-GRU, and the basic E-D model in prediction accuracy, achieving the highest${R}^{{2}}$values of 0.952 and 0.972 on the two datasets, respectively, proving its superior ability to capture the long-term dependencies in blood glucose data.

Förderung

  • National Key Research and Development Program of China
  • Jiangsu Key Development Planning Project
  • Six Talent Peaks Project in Jiangsu Province
  • Postgraduate Research and Practice Innovation Program of Jiangsu Province

Zitieren

APA

Xu, H., Zhang, Y., Liu, S., Ji, Y., Lv, M., & Li, P. (2025). CGM-Based Blood Glucose Prediction Model With LSTM Encoder–Decoder Architecture. IEEE Sensors Journal, 25(3), 5824-5839. https://doi.org/10.1109/jsen.2024.3517554

Vancouver

Xu H, Zhang Y, Liu S, Ji Y, Lv M, Li P. CGM-Based Blood Glucose Prediction Model With LSTM Encoder–Decoder Architecture. IEEE Sensors Journal. 2025;25(3):5824-5839. doi:10.1109/jsen.2024.3517554

BibTeX
@article{Xu2025,
  author = {Xu, He and Zhang, Yi and Liu, Sixing and Ji, Yimu and Lv, Ming and Li, Peng},
  title = {CGM-Based Blood Glucose Prediction Model With LSTM Encoder–Decoder Architecture},
  journal = {IEEE Sensors Journal},
  year = {2025},
  volume = {25},
  number = {3},
  pages = {5824--5839},
  doi = {10.1109/jsen.2024.3517554}
}
Kostenlos starten →