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 Experiment Videos

Electrical impedance cardiography using artificial neural networks

A P Mulavara1, W D Timmons, M S Nair

  • 1Department of Biomedical Engineering, The University of Akron, OH 44325-0302, USA.

Annals of Biomedical Engineering
|July 14, 1998
PubMed
Summary

Artificial neural networks accurately estimate stroke volume using thoracic electrical impedance. This method offers a user-friendly alternative to traditional biophysical approaches for non-invasive stroke volume measurement.

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

Sensory network segregation as a predictor of post spaceflight balance impairments and sensory re-weighting.

NPJ microgravity·2025
Same author

The microgravity environment affects sensorimotor adaptation and its neural correlates.

Cerebral cortex (New York, N.Y. : 1991)·2025
Same author

Daily artificial gravity partially mitigates vestibular processing changes associated with head-down tilt bedrest.

NPJ microgravity·2024
Same author

Gender differences in PTSD severity and pain outcomes: baseline results from the LAMP trial.

medRxiv : the preprint server for health sciences·2023
Same author

SARS-CoV-2 omicron variants are susceptible in vitro to Artemisia annua hot water extracts.

Journal of ethnopharmacology·2023
Same author

Artelon as a Bio-Scaffold to Augment Collateral Ligament Repair after Knee Dislocation.

Malaysian orthopaedic journal·2022

Area of Science:

  • Biomedical Engineering
  • Computational Neuroscience

Background:

  • Estimating stroke volume non-invasively is crucial for cardiovascular monitoring.
  • Traditional biophysical methods for stroke volume estimation often rely on simplifying assumptions.
  • Thoracic electrical bioimpedance offers a potentially rich source of physiological data.

Purpose of the Study:

  • To evaluate the efficacy of artificial neural networks (ANNs) in estimating stroke volume.
  • To compare ANN performance against established biophysical methods.
  • To explore the relationship between thoracic bioimpedance signals and stroke volume.

Main Methods:

  • Utilized pre-processed thoracic impedance plethysmograph signals from 20 healthy subjects.
  • Trained ANNs using standard back-propagation with Doppler stroke volume estimates as the target output.

Related Experiment Videos

  • Compared ANN performance with two classical biophysical approaches.

    • Main Results:

    • The best ANN achieved a coefficient of determination (R2) of 77.38% compared to Doppler estimates.
    • Classical biophysical methods showed significantly lower R2 values (8.20% and 9.90%).
    • ANN residuals exhibited a significant zero mean Gaussian distribution, indicating model validity.

    Conclusions:

    • Artificial neural networks demonstrate a powerful capability for estimating stroke volume from thoracic electrical impedance.
    • ANNs present a promising, assumption-free alternative to conventional methods for stroke volume assessment.
    • A potential invertible relationship between thoracic bioimpedance and stroke volume is suggested by the findings.