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

Distinct sensory and autonomic involvement in hypermobile Ehlers-Danlos syndrome compared with idiopathic small fiber neuropathy: a multimodal study.

Scientific reports·2026
Same author

Inter-centre heterogeneity, temporal evolution, and factors associated with treatment selection and outcomes in chronic inflammatory demyelinating polyradiculoneuropathy: a multicentre, combined prospective and retrospective observational study.

EClinicalMedicine·2026
Same author

Muscle biopsy in genomic era: real-world diagnostic and clinical implications over 10 years.

Journal of neurology·2026
Same author

A Quantitative Assessment of Upper Limb Motor Function Across Disease Stages in Hereditary Transthyretin Amyloidosis.

Journal of the peripheral nervous system : JPNS·2026
Same author

Deep Phenotyping of F64L Mutation in a Multicentric Cohort of Patisiran-Treated Hereditary Transthyretin Amyloidosis Patients (Patisiranitaly).

European journal of neurology·2026
Same author

Use of High-Efficacy Therapy in Children With Multiple Sclerosis to Prevent Long-Term Disability.

Neurology·2026

Related Experiment Video

Updated: Dec 18, 2025

Nerve Ultrasound Protocol to Detect Dysimmune Neuropathies
08:56

Nerve Ultrasound Protocol to Detect Dysimmune Neuropathies

Published on: October 7, 2021

3.1K

Electrodiagnostic accuracy in polyneuropathies: supervised learning algorithms as a tool for practitioners.

Antonino Uncini1, Graziano Aretusi2,3, Fiore Manganelli4

  • 1Department of Neuroscience, Imaging and Clinical Sciences, University "G. d'Annunzio", Via Luigi Polacchi 11, 66100, Chieti-Pescara, Italy. uncini@unich.it.

Neurological Sciences : Official Journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology
|June 11, 2020
PubMed
Summary
This summary is machine-generated.

Supervised learning algorithms (SLAs) like Support Vector Machine (SVM) demonstrate high accuracy in diagnosing polyneuropathies, outperforming neurophysiologists. This suggests SLAs can aid in electrodiagnosis, especially for less experienced practitioners.

Keywords:
Diagnostic accuracyElectrodiagnosisPolyneuropathiesSupervised learning algorithms

More Related Videos

Utility of Dissociated Intrinsic Hand Muscle Atrophy in the Diagnosis of Amyotrophic Lateral Sclerosis
08:16

Utility of Dissociated Intrinsic Hand Muscle Atrophy in the Diagnosis of Amyotrophic Lateral Sclerosis

Published on: March 4, 2014

32.9K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.9K

Related Experiment Videos

Last Updated: Dec 18, 2025

Nerve Ultrasound Protocol to Detect Dysimmune Neuropathies
08:56

Nerve Ultrasound Protocol to Detect Dysimmune Neuropathies

Published on: October 7, 2021

3.1K
Utility of Dissociated Intrinsic Hand Muscle Atrophy in the Diagnosis of Amyotrophic Lateral Sclerosis
08:16

Utility of Dissociated Intrinsic Hand Muscle Atrophy in the Diagnosis of Amyotrophic Lateral Sclerosis

Published on: March 4, 2014

32.9K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.9K

Area of Science:

  • Neurology
  • Machine Learning
  • Biomedical Engineering

Background:

  • Misdiagnosis in polyneuropathy electrodiagnostic interpretation is a significant clinical challenge.
  • Accurate differentiation between various polyneuropathy types is crucial for effective treatment.

Purpose of the Study:

  • To evaluate the electrodiagnostic accuracy of supervised learning algorithms (SLAs) compared to human neurophysiologists.
  • To identify the most accurate SLA for polyneuropathy diagnosis.

Main Methods:

  • Trained and tested three SLAs (shrinkage discriminant analysis, multinomial logistic regression, support vector machine) on 434 subjects across five diagnostic classes.
  • Utilized a 90% training set and 10% test set with tenfold cross-validation for SLA performance evaluation.
  • Compared SLA accuracy, precision, sensitivity, and specificity against neurophysiologists (experts and trainees).

Main Results:

  • Support Vector Machine (SVM) achieved the highest diagnostic accuracy (90.5% training, 93.2% test sets).
  • SVM outperformed all neurophysiologists, whose accuracy ranged from 54.5% to 81.8%.
  • SVM ranked first in multidimensional comparison analysis.

Conclusions:

  • Support Vector Machine (SVM) demonstrates high electrodiagnostic accuracy for polyneuropathies.
  • SLAs, particularly SVM, show potential as a diagnostic support system in electrodiagnosis.
  • Implementing SLAs could enhance diagnostic consistency and support less experienced neurophysiologists.