EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Diabetes: Non-Invasive Blood Glucose Monitoring Using Federated Learning with Biosensor Signals

Narmatha Chellamani iD, Saleh Ali Albelwi, Manimurugan Shanmuganathan iD, Palanisamy Amirthalingam iD, Anand Paul iD

Biosensors · 16.04.2025 · 15 (4) · 255

DOI: 10.3390/bios15040255 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biosensors, online erschienen am 16.04.2025. Verfasst von Narmatha Chellamani und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computers and Information Technology, University of Tabuk, Tabuk 71491, Saudi Arabia. Hauptthemen laut MEDLINE: Biosensing Techniques, Machine Learning, Blood Glucose, Diabetes Mellitus. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Tabuk, Deanship of Research and Graduate Studies at the University of Tabuk.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetes is a growing global health concern, affecting millions and leading to severe complications if not properly managed. The primary challenge in diabetes management is maintaining blood glucose levels (BGLs) within a safe range to prevent complications such as renal failure, cardiovascular disease, and neuropathy. Traditional methods, such as finger-prick testing, often result in low patient adherence due to discomfort, invasiveness, and inconvenience. Consequently, there is an increasing need for non-invasive techniques that provide accurate BGL measurements. Photoplethysmography (PPG), a photosensitive method that detects blood volume variations, has shown promise for non-invasive glucose monitoring. Deep neural networks (DNNs) applied to PPG signals can predict BGLs with high accuracy. However, training DNN models requires large and diverse datasets, which are typically distributed across multiple healthcare institutions. Privacy concerns and regulatory restrictions further limit data sharing, making conventional centralized machine learning (ML) approaches less effective. To address these challenges, this study proposes a federated learning (FL)-based solution that enables multiple healthcare organizations to collaboratively train a global model without sharing raw patient data, thereby enhancing model performance while ensuring data privacy and security. In the data preprocessing stage, continuous wavelet transform (CWT) is applied to smooth PPG signals and remove baseline drift. Adaptive cycle-based segmentation (ACBS) is then used for signal segmentation, followed by particle swarm optimization (PSO) for feature selection, optimizing classification accuracy. The proposed system was evaluated on diverse datasets, including VitalDB and MUST, under various conditions with data collected during surgery and anesthesia. The model achieved a root mean square error (RMSE) of 19.1 mg/dL, demonstrating superior predictive accuracy. Clarke error grid analysis (CEGA) confirmed the model’s clinical reliability, with 99.31% of predictions falling within clinically acceptable limits. The FL-based approach outperformed conventional deep learning models, making it a promising method for non-invasive, privacy-preserving glucose monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Biosensing TechniquesMachine LearningBlood GlucoseDiabetes MellitusBlood Glucose Self-MonitoringHumansPhotoplethysmographyNeural Networks, ComputerFederated Learning

Stichwörter der Autor:innen

Clarke error grid analysisdeep neural networks (DNNs)diabetes managementfederated learning (FL)healthcaremachine learningnon-invasive blood glucose monitoringphotoplethysmography (PPG)

Substanzen

Blood Glucose

Autor:innen und Institutionen

  • Faculty of Computers and Information Technology, University of Tabuk, Tabuk 71491, Saudi Arabia.
  • Department of Pharmacy Practice, Faculty of Pharmacy, University of Tabuk, Tabuk 71491, Saudi Arabia.
  • Biostatistics and Data Science Department, The School of Public Health, LSU Health Sciences Center New Orleans, New Orleans, LA 70112, USA.

ORCID-Profile: Narmatha Chellamani, Manimurugan Shanmuganathan, Palanisamy Amirthalingam, Anand Paul

Förderung

  • University of Tabuk
  • Deanship of Research and Graduate Studies at the University of Tabuk

Zitieren

APA

Chellamani, N., Albelwi, S. A., Shanmuganathan, M., Amirthalingam, P., & Paul, A. (2025). Diabetes: Non-Invasive Blood Glucose Monitoring Using Federated Learning with Biosensor Signals. Biosensors, 15(4), 255. https://doi.org/10.3390/bios15040255

Vancouver

Chellamani N, Albelwi SA, Shanmuganathan M, Amirthalingam P, Paul A. Diabetes: Non-Invasive Blood Glucose Monitoring Using Federated Learning with Biosensor Signals. Biosensors. 2025;15(4):255. doi:10.3390/bios15040255

BibTeX
@article{Chellamani2025,
  author = {Chellamani, Narmatha and Albelwi, Saleh Ali and Shanmuganathan, Manimurugan and Amirthalingam, Palanisamy and Paul, Anand},
  title = {Diabetes: Non-Invasive Blood Glucose Monitoring Using Federated Learning with Biosensor Signals},
  journal = {Biosensors},
  year = {2025},
  volume = {15},
  number = {4},
  pages = {255},
  doi = {10.3390/bios15040255}
}
Kostenlos starten →