Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A CDK4/6 inhibitor-armed oncolytic adenovirus reverses T cell exhaustion through the Rb-p65-CCL5 pathway and potentiates the antitumor activity of anti-PD-1 or CAR-T therapy in colorectal cancer.

Frontiers in immunology·2026
Same author

Clinical features of type A aortic dissection initially presenting with neurological symptoms: a single-center case series.

Frontiers in neurology·2026
Same author

Phenotypic image dataset of naturally grown shiitake mushrooms across multiple varieties and growth stages.

Scientific data·2026
Same author

A High-Humidity-Tolerant Electrolyte for High-Voltage Lithium-Metal Batteries.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Glutathione peroxidase gene regulates heat stress response via trehalose synthesis in Pleurotus ostreatus.

Applied microbiology and biotechnology·2026
Same author

Patient activation and its influencing factors among maintenance hemodialysis patients: a cross-sectional study in China.

BMC nephrology·2026

Related Experiment Video

Updated: Jan 13, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K

A Machine Learning Approach for Real-Time Detection of Inadequate Sedation Using Non-EEG Physiological Signals.

Huiquan Wang1, Chunliang Jiang1,2, Guanjun Liu2

  • 1School of Control Science and Engineering, Tiangong University, Tianjin 300387, China.

Bioengineering (Basel, Switzerland)
|October 29, 2025
PubMed
Summary
This summary is machine-generated.

A new machine learning model detects inadequate sedation using non-EEG physiological data. This approach offers a practical, interpretable solution for real-time monitoring in various settings.

Keywords:
bispectral indexinadequate sedationmachine learningnon-EEG physiological signalsout-of-hospital

More Related Videos

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits
10:25

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits

Published on: March 27, 2021

6.5K
A Bedside, Single Burr Hole Approach to Multimodality Monitoring in Severe Brain Injury
06:18

A Bedside, Single Burr Hole Approach to Multimodality Monitoring in Severe Brain Injury

Published on: March 26, 2019

9.5K

Related Experiment Videos

Last Updated: Jan 13, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.3K
Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits
10:25

Multi-system Monitoring for Identification of Seizures, Arrhythmias and Apnea in Conscious Restrained Rabbits

Published on: March 27, 2021

6.5K
A Bedside, Single Burr Hole Approach to Multimodality Monitoring in Severe Brain Injury
06:18

A Bedside, Single Burr Hole Approach to Multimodality Monitoring in Severe Brain Injury

Published on: March 26, 2019

9.5K

Area of Science:

  • Anesthesiology and Critical Care Medicine
  • Biomedical Engineering
  • Machine Learning in Healthcare

Background:

  • Inadequate sedation during anesthesia poses risks like patient discomfort and intraoperative awareness.
  • Conventional electroencephalography (EEG)-based monitoring is often impractical in out-of-hospital settings due to equipment and artifact issues.
  • Development of alternative, non-EEG monitoring methods is crucial for patient safety.

Purpose of the Study:

  • To develop and evaluate a machine learning model for detecting inadequate sedation using non-EEG physiological data.
  • To assess the performance and interpretability of the developed model.
  • To explore the feasibility of integrating such a model into portable monitoring systems.

Main Methods:

  • A machine learning model was developed using 27 features (demographics, vital signs, heart rate variability) from the VitalDB database.
  • Inadequate sedation was defined as a bispectral index (BIS) > 60.
  • Four temporal windows and four algorithms were evaluated, with model interpretability assessed using Shapley Additive Explanations (SHAP).

Main Results:

  • The Light Gradient Boosting Machine (LGBM) algorithm achieved the highest performance (AUC=0.825, ACC=0.741) with a 2s time window.
  • Extending the time window to 20s showed a marginal improvement in performance metrics.
  • Feature selection identified 12 key parameters, maintaining accuracy with reduced model complexity.

Conclusions:

  • Non-EEG-based physiological data can be effectively used for real-time detection of inadequate sedation.
  • The developed machine learning model is interpretable, resource-efficient, and scalable.
  • The model holds significant potential for integration into portable monitoring systems for prehospital, emergency, and low-resource settings.