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

Automated recognition of corrupted arterial waveforms using neural network techniques.

T Pike1, R A Mustard

  • 1Department of Surgery, Wellesley Hospital, University of Toronto, Ontario, Canada.

Computers in Biology and Medicine
|May 1, 1992
PubMed
Summary

Researchers can now automate the detection of corrupted arterial pressure waveforms using a novel neural network. This computer science technique eliminates manual inspection, saving significant time in data acquisition.

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

The role of cholecystectomy following endoscopic sphincterotomy and bile duct stone removal.

Annals of the Royal College of Surgeons of England·2022
Same author

The ISIS pre-injector reconfiguration.

The Review of scientific instruments·2016
Same author

Cirsoid aneurysm secondary to an arteriovenous fistula of the facial artery and vein.

Dento maxillo facial radiology·2015
Same author

Re: 'Predicting postoperative mortality after colorectal surgery: a novel clinical model'.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2014
Same author

Re: Ratios derived from an array of standard haematological indices predict the oncological outcome in colon cancer.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2014
Same author

The Management of Thyrotoxicosis.

Canadian Medical Association journal·2010

Area of Science:

  • Biomedical Engineering
  • Computer Science
  • Physiology

Background:

  • Continuous physiological monitoring generates large datasets requiring extensive data processing.
  • Manual inspection of arterial pressure waveforms for signal integrity is time-consuming and labor-intensive.
  • Automated methods are needed to improve efficiency in analyzing physiological data.

Purpose of the Study:

  • To develop and validate a computer science technique for automatic detection of corrupted arterial pressure waveforms.
  • To eliminate the need for manual visual inspection of waveform data.
  • To enhance the efficiency of data acquisition systems in physiological research.

Main Methods:

  • Trained a simulated neural network to recognize patterns indicative of corrupted arterial pressure waveforms.

Related Experiment Videos

  • Developed a system for automated evaluation of arterial waveform validity.
  • Quantified system performance using false positive and false negative error rates.

    • Main Results:

    • The trained neural network successfully identified corrupted arterial pressure waveforms.
    • The automated system achieved an average false positive error rate of 2.2%.
    • The automated system achieved an average false negative error rate of 12.6%.

    Conclusions:

    • A simulated neural network can effectively automate the identification of corrupted arterial pressure waveforms.
    • This novel computer science approach significantly reduces the need for manual data validation.
    • The developed system offers a promising solution for improving data acquisition efficiency in physiological research.