EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction and accuracy improvement of insulin pump in-fusion deviation based on LSTM and PID

Leijie Wang, Xudong Guo, Qiuyue Peng iD, Hongmei Zhang, Yuan Yang, Hongyan Wang, Yongxin Wang, Haofang Liang, Wuyi Ming, Zhen Zhang

PLOS One · 2025

DOI: 10.1371/journal.pone.0324261 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Leijie Wang und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Dongguan University of Technology, Dongguan, China. Hauptthemen laut MEDLINE: Insulin Infusion Systems, Neural Networks, Computer, Insulin. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Basic and Applied Basic Research Foundation, Guangdong Provincial Key Laboratory of Manufacturing Equipment Digitization.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In order to further improve the injection precision of the PH300 insulin pump, this paper optimizes and improves the mechanical structure and control algorithm of the PH300. The improved PH300 uses a proportional-integral-derivative controller based on back propagation neural network (BP-PID) algorithm to control operation, and the experimental results show that the minimum effective single infusion dose of the improved PH300 is 0.047 U, which is reduced by 50.52%. The deviation reduction of low-dose infusion (0.1U-0.9U) ranged from 1.47% to 10.87%, with a mean of 4.91%. The mean deviation of the improved PH300 decreases by 12.85% after a 24h low basal rate (0.5U/h) injection. In addition, Long Short-Term Memory (LSTM) was used to predict the deviation during injection, and the predicted values were uniformly compensated for in subsequent injection experiments. The LSTM model performed best with a training set of 85%, a test set of 15%, an epoch of 300, a batch number of 256, and 32 hidden layer neurons. After compensation, the mean infusion deviation for large doses was reduced by 12.05%, and the maximum deviation by 14.12%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Insulin Infusion SystemsNeural Networks, ComputerInsulinAlgorithmsHumans

Substanzen

Insulin

Autor:innen und Institutionen

  • School of Mechanical Engineering, Dongguan University of Technology, Dongguan, China.
  • Mechanical and Electrical Engineering Institute, Zhengzhou University of Light Industry, Zhengzhou, China.
  • Department Emergency of Internal Medicine, Hubei Provincial Hospital of Traditional Chinese Medicine, Wuhan, China.
  • Zhengzhou Phray Technology co., Ltd., Zhengzhou, China.
  • Laboratory of Regenerative Medicine in Sports Science, School of Sports Science, South China Normal University, Guangzhou, China.
  • Guangdong HUST Industrial Technology Research Institute, Guangdong Provincial Key Laboratory of Digital Manufacturing Equipment, Dongguan, China.

ORCID-Profile: Qiuyue Peng

Förderung

  • Guangdong Basic and Applied Basic Research Foundation
  • Guangdong Provincial Key Laboratory of Manufacturing Equipment Digitization

Zitieren

APA

Wang, L., Guo, X., Peng, Q., Zhang, H., Yang, Y., Wang, H., Wang, Y., Liang, H., Ming, W., & Zhang, Z. (2025). Prediction and accuracy improvement of insulin pump in-fusion deviation based on LSTM and PID. PLOS One. https://doi.org/10.1371/journal.pone.0324261

Vancouver

Wang L, Guo X, Peng Q, Zhang H, Yang Y, Wang H, et al. Prediction and accuracy improvement of insulin pump in-fusion deviation based on LSTM and PID. PLOS One. 2025. doi:10.1371/journal.pone.0324261

BibTeX
@article{Wang2025,
  author = {Wang, Leijie and Guo, Xudong and Peng, Qiuyue and Zhang, Hongmei and Yang, Yuan and Wang, Hongyan and Wang, Yongxin and Liang, Haofang and Ming, Wuyi and Zhang, Zhen},
  title = {Prediction and accuracy improvement of insulin pump in-fusion deviation based on LSTM and PID},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0324261}
}
Kostenlos starten →