EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Autonomic Signature-Driven Anesthesia Depth Monitoring with Biomimetic Wearable ECG and Knowledge Graph-Augmented Deep Networks

Aoran Bao, Cheng Ding

Sensors · 02.06.2026 · 26 (11) · 3498

DOI: 10.3390/s26113498 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.06.2026. Verfasst von Aoran Bao und 1 weiteren Autor:innen. Beteiligte Einrichtung: College of Smart Agriculture (College of Artificial Intelligence), Nanjing Agricultural University, Nanjing 210095, China. Hauptthemen laut MEDLINE: Anesthesia, Autonomic Nervous System, Biomimetics, Electrocardiography. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Opening Foundation of the State Key Laboratory of Transvascular Implantation Devices.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Considerable efforts have been devoted to accurately monitoring the depth of anesthesia to ensure patient safety during surgery. Traditional approaches typically rely on electroencephalogram (EEG)-based indices, such as the Bispectral Index (BIS), which require specialized equipment. In contrast, electrocardiogram (ECG) signals are widely available in clinical settings and can be conveniently acquired via wearable devices, while also exhibiting strong responsiveness to anesthetic agents. Inspired by biomimetic physiological regulation mechanisms, this study proposes a wearable-compatible ECG-based framework for depth-of-anesthesia detection that leverages autonomic nervous system characteristics and a knowledge graph-enhanced graph convolutional network (GCN). ECG recordings from 110 patients were preprocessed, and 20 anesthesia-related features were extracted, spanning morphological, statistical, spectral, heart rate variability (HRV), and entropy-based descriptors; feature selection methods identified 13 discriminative features. A patient-level knowledge graph was first constructed using the 88 training patients (1760 nodes), and test patient nodes were incorporated only after training was complete for inductive inference. Experimental results demonstrate that the proposed deep knowledge GCN achieves a test accuracy of 98.18% in distinguishing between awake and deep sleep anesthesia states, indicating that biomimetic, wearable-compatible ECG analysis combined with knowledge graph learning holds strong potential as a cost-effective alternative to traditional EEG-based anesthesia monitoring systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AnesthesiaAutonomic Nervous SystemBiomimeticsElectrocardiographyGraph Neural NetworksMonitoring, PhysiologicWearable Electronic DevicesHumansAlgorithmsElectroencephalographyHeart RateSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

depth of anesthesiaelectrocardiogram (ECG)graph convolution layersgraph neural network (GNN)

Autor:innen und Institutionen

  • College of Smart Agriculture (College of Artificial Intelligence), Nanjing Agricultural University, Nanjing 210095, China.
  • College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China.

Förderung

  • National Natural Science Foundation of China
  • Opening Foundation of the State Key Laboratory of Transvascular Implantation Devices

Zitieren

APA

Bao, A., & Ding, C. (2026). Autonomic Signature-Driven Anesthesia Depth Monitoring with Biomimetic Wearable ECG and Knowledge Graph-Augmented Deep Networks. Sensors, 26(11), 3498. https://doi.org/10.3390/s26113498

Vancouver

Bao A, Ding C. Autonomic Signature-Driven Anesthesia Depth Monitoring with Biomimetic Wearable ECG and Knowledge Graph-Augmented Deep Networks. Sensors. 2026;26(11):3498. doi:10.3390/s26113498

BibTeX
@article{Bao2026,
  author = {Bao, Aoran and Ding, Cheng},
  title = {Autonomic Signature-Driven Anesthesia Depth Monitoring with Biomimetic Wearable ECG and Knowledge Graph-Augmented Deep Networks},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3498},
  doi = {10.3390/s26113498}
}
Kostenlos starten →