EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management

Pardis Sadeghi iD, Shahriar Noroozizadeh iD, Rania Alshawabkeh iD, Nian Xiang Sun iD

Biosensors · 01.03.2025 · 15 (3) · 152

DOI: 10.3390/bios15030152 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biosensors, online erschienen am 01.03.2025. Verfasst von Pardis Sadeghi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Electrical & Computer Engineering, W.M. Keck Laboratory for Integrated Ferroics, Northeastern University, Boston, MA 02115, USA. Hauptthemen laut MEDLINE: Biosensing Techniques, Machine Learning, Diabetes Mellitus, Glucose. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation Center for Pandemic Insights (NSF CPI), Trinity Challenge, U.S. National Science Foundation Center for Pandemic Insights (NSF CPI), Natural Sciences and Engineering Research Council of Canada (NSERC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Developing reliable noninvasive diagnostic and monitoring systems for diabetes remains a significant challenge, especially in the e-healthcare domain, due to computational inefficiencies and limited predictive accuracy in current approaches. The current study integrates machine learning with a molecularly imprinted polymer biosensor for detecting D-glucose in the exhaled breath condensate or aerosol. Advanced models, such as Convolutional Neural Networks and Recurrent Neural Networks, were used to analyze resistance signals, while classical algorithms served as benchmarks. To address challenges like data imbalance, limited samples, and inter-sensor variability, synthetic data generation methods like Synthetic Minority Oversampling Technique and Generative Adversarial Networks were employed. This framework aims to classify clinically relevant glucose levels accurately, enabling non-invasive diabetes monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Biosensing TechniquesMachine LearningDiabetes MellitusGlucoseHumansNeural Networks, ComputerAlgorithms

Stichwörter der Autor:innen

CNNsD-glucoseGANsRNNsSMOTEbiosensorsdiabetesmolecularly imprinted polymer

Substanzen

Glucose

Autor:innen und Institutionen

  • Electrical & Computer Engineering, W.M. Keck Laboratory for Integrated Ferroics, Northeastern University, Boston, MA 02115, USA.
  • Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
  • Heinz College, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
  • Winchester Technologies, LLC, Burlington, MA 01803, USA.

ORCID-Profile: Pardis Sadeghi, Shahriar Noroozizadeh, Rania Alshawabkeh, Nian Xiang Sun

Förderung

  • National Science Foundation Center for Pandemic Insights (NSF CPI)
  • Trinity Challenge, U.S. National Science Foundation Center for Pandemic Insights (NSF CPI)
  • Natural Sciences and Engineering Research Council of Canada (NSERC)

Zitieren

APA

Sadeghi, P., Noroozizadeh, S., Alshawabkeh, R., & Sun, N. X. (2025). Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management. Biosensors, 15(3), 152. https://doi.org/10.3390/bios15030152

Vancouver

Sadeghi P, Noroozizadeh S, Alshawabkeh R, Sun NX. Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management. Biosensors. 2025;15(3):152. doi:10.3390/bios15030152

BibTeX
@article{Sadeghi2025,
  author = {Sadeghi, Pardis and Noroozizadeh, Shahriar and Alshawabkeh, Rania and Sun, Nian Xiang},
  title = {Machine Learning-Driven D-Glucose Prediction Using a Novel Biosensor for Non-Invasive Diabetes Management},
  journal = {Biosensors},
  year = {2025},
  volume = {15},
  number = {3},
  pages = {152},
  doi = {10.3390/bios15030152}
}
Kostenlos starten →