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

Estimating respiratory system compliance during mechanical ventilation using artificial neural networks.

Gaetano Perchiazzi1, Rocco Giuliani, Loreta Ruggiero

  • 1*Department of Clinical Physiology, Uppsala University Hospital, Sweden; and †Department of Emergency and Transplantation, Bari University Hospital, Italy.

Anesthesia and Analgesia
|September 23, 2003
PubMed
Summary

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

Extracellular matrix remodeling modifies structural responses to ventilator-induced lung injury: a multiscale correlative imaging study.

Respiratory research·2026
Same author

Hypotension and pulmonary atelectasis during general anaesthesia: a randomised crossover laboratory study.

British journal of anaesthesia·2026
Same author

Nitric oxide and its role in the management of hypoxaemia in the anaesthetised horse-a narrative review.

Veterinary anaesthesia and analgesia·2026
Same author

Innovation in intensive care: a framework to turn ideas and concepts into actionable solutions.

Intensive care medicine·2026
Same author

Computed Tomography Yield and Predictors of Pulmonary Embolism in Mechanically Ventilated Patients-A Retrospective Study.

Acta anaesthesiologica Scandinavica·2026
Same author

The focal index: a quantitative approach to morphological sub-phenotyping of COVID-19 patients with acute respiratory distress syndrome: a pilot study.

Intensive care medicine experimental·2025

Artificial neural networks (ANN) can estimate respiratory system static compliance (C(RS)) during mechanical ventilation without pausing inspiration. This technology offers a promising alternative for continuous monitoring in intensive care settings.

Area of Science:

  • Biomedical Engineering
  • Respiratory Physiology
  • Artificial Intelligence in Medicine

Background:

  • Estimating respiratory system static compliance (C(RS)) is crucial for mechanical ventilation management.
  • Current methods often require an end-inspiratory pause, interrupting ventilation and potentially causing patient distress.
  • Continuous and non-invasive methods for C(RS) estimation are highly desirable.

Purpose of the Study:

  • To evaluate the efficacy of artificial neural networks (ANN) in estimating C(RS) during volume-controlled mechanical ventilation.
  • To determine if ANN can provide accurate C(RS) measurements without the need for an end-inspiratory pause.
  • To assess the performance of ANN in both healthy and acute lung injury conditions.

Main Methods:

  • A porcine model of acute lung injury was used to simulate various respiratory conditions.

Related Experiment Videos

  • Artificial neural networks were trained using volume-pressure loops from breaths preceding an end-inspiratory pause.
  • The trained ANN estimated C(RS) prospectively, and results were compared to the interrupter technique (IT).

    • Main Results:

    • The ANN accurately estimated C(RS) with a low bias of -0.67 +/- 1.52 mL/cm H(2)O compared to the IT.
    • The ANN successfully extracted C(RS) information from the volume-pressure loop without requiring an inspiratory hold.
    • The model demonstrated reliable performance across different respiratory mechanics.

    Conclusions:

    • Artificial neural networks can reliably estimate respiratory system static compliance during continuous mechanical ventilation.
    • This ANN-based approach eliminates the need to interrupt ventilation for C(RS) measurement.
    • The technology holds potential for real-time respiratory monitoring and improved patient management.