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

Comparison of three arterial pulse waveform classification techniques

J Allen1, A Murray

  • 1Regional Medical Physics Department, Freeman Hospital, Newcastle upon Tyne, UK.

Journal of Medical Engineering & Technology
|May 1, 1996
PubMed
Summary
This summary is machine-generated.

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

To what extent does g impact on conceptual, practical and social adaptive functioning in clinically referred children?

Journal of intellectual disability research : JIDR·2013
Same author

Platelet reactivity changes significantly throughout all trimesters of pregnancy compared with the nonpregnant state: a prospective study.

BJOG : an international journal of obstetrics and gynaecology·2013
Same author

An implementation of a spike-response model with escape noise using an avalanche diode.

IEEE transactions on biomedical circuits and systems·2013
Same author

Expression profiling of type 2 diabetes susceptibility genes in the pancreatic islets, adipose tissue and liver of obese mice.

Experimental and clinical endocrinology & diabetes : official journal, German Society of Endocrinology [and] German Diabetes Association·2013
Same author

A prospective study of systemic sclerosis-related digital ulcers: prevalence, location, and functional impact.

Scandinavian journal of rheumatology·2013
Same author

Mechanical testing of lid speculae and relationship to postoperative ptosis.

Eye (London, England)·2013
Same journal

News and Product Update.

Journal of medical engineering & technology·2026
Same journal

PMMA based ultra miniaturized implantable antenna for biotelemetry applications.

Journal of medical engineering & technology·2026
Same journal

Comparative machine learning for accurate EEG-based epileptic seizure state classification using sub-band analysis.

Journal of medical engineering & technology·2026
Same journal

Genetic algorithm-optimized machine learning approaches for EEG-based silent speech decoding.

Journal of medical engineering & technology·2026
Same journal

Power transition signatures of vibroarthrographic spectrograms for diagnosing knee joint pathologies.

Journal of medical engineering & technology·2026
Same journal

News and product update.

Journal of medical engineering & technology·2026
See all related articles

Artificial neural networks accurately detect lower limb arterial disease from peripheral pulse waveforms. This advanced technique shows superior diagnostic performance compared to traditional methods for peripheral vascular disease detection.

Area of Science:

  • Biomedical Engineering
  • Cardiovascular Diagnostics
  • Machine Learning in Medicine

Background:

  • Peripheral vascular disease (PVD) alters peripheral pulse waveforms, making them potential diagnostic indicators.
  • Photoelectric plethysmography (PPG) captures pulse waveforms, offering a non-invasive method for assessment.
  • Established classification techniques exist but their comparative performance in PVD detection from PPG is not fully elucidated.

Purpose of the Study:

  • To compare the diagnostic performance of three classification techniques: linear discriminant classifier, k-nearest neighbour classifier, and artificial neural network.
  • To evaluate the ability of these classifiers to detect lower limb arterial disease using PPG pulse waveforms.
  • To determine which classification method offers the highest accuracy in diagnosing PVD.

Related Experiment Videos

Main Methods:

  • PPG pulse waveforms and Doppler ultrasound ankle-to-brachial pressure indices (ABPI) were collected from 366 legs.
  • Waveform data from 100 legs served as training data for each classifier.
  • Classifications from a further 266 legs were compared against ABPI diagnoses.

Main Results:

  • The artificial neural network achieved the highest diagnostic accuracy (80%).
  • The k-nearest neighbour classifier (k=27) showed 76% accuracy, and the linear discriminant classifier achieved 71% accuracy.
  • The artificial neural network demonstrated the highest Kappa measure of agreement (57%), indicating superior performance beyond chance.

Conclusions:

  • Artificial neural networks can effectively classify arterial pulse waveforms for PVD detection.
  • ANNs outperform k-nearest neighbour and linear discriminant classifiers in diagnosing lower limb arterial disease from PPG data.
  • This study highlights the potential of machine learning for identifying subtle vascular abnormalities from pulse waveform analysis.