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 Video

Updated: Mar 23, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.9K

Diabetic peripheral neuropathy class prediction by multicategory support vector machine model: a cross-sectional

Maryam Kazemi1, Abbas Moghimbeigi1,2, Javad Kiani3,4

  • 1Department of Biostatistics, School of Public Health, Hamadan University of Medical Sciences, Hamadan, Iran.

Epidemiology and Health
|April 2, 2016
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

Morning vs. afternoon saliva: limited diurnal variation in ion composition of unstimulated whole saliva.

Clinical oral investigations·2026
Same author

The role of preemptive analgesia with various analgesic drugs in patients undergoing orthopedic surgeries: A systematic review 2015-2020.

Journal of orthopaedics·2026
Same author

Evaluation of cervical healing in a rat model using alginate hydrogel embedded with platelet-rich plasma.

Molecular biology reports·2026
Same author

Probabilistic risk assessment of occupational exposure to respirable crystalline silica among ceramic workers in an industrial town in Iran: a Monte Carlo simulation approach.

Scientific reports·2026
Same author

Examining the Performance of ChatGPT in Comprehensive Pre-Internship Exam: The Potential of Artificial Intelligence in Medical Education.

Health science reports·2026
Same author

Neurofeedback as an Adjunct to Pharmacotherapy in OCD: A Randomized Controlled Trial on Symptom Reduction.

Applied psychophysiology and biofeedback·2026

This study shows a multicategory support vector machine (MSVM) model can predict diabetic neuropathy severity with 76% accuracy using balanced data. This approach aids in managing diabetic complications and preventing amputations.

Area of Science:

  • Medical Informatics
  • Machine Learning in Healthcare
  • Diabetology

Background:

  • Diabetes mellitus is a global epidemic, with diabetic neuropathy being a common and severe complication.
  • Diabetic neuropathy can lead to debilitating outcomes, including lower limb amputations.
  • Accurate prediction of neuropathy severity is crucial for timely intervention.

Purpose of the Study:

  • To develop and evaluate a multicategory support vector machine (MSVM) model for predicting diabetic peripheral neuropathy severity.
  • To classify neuropathy into four distinct severity categories using patient demographic and clinical data.
  • To assess the effectiveness of MSVM with different strategies and kernel functions on an unbalanced dataset.

Main Methods:

  • Data from 600 patients at the Diabetes Center of Hamadan, Iran, were collected using questionnaires, including the Neuropathy Disability Score (NDS).
Keywords:
ClassificationDiabetic neuropathyLogistic modelsSupport vector machine

More Related Videos

Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

20.6K

Related Experiment Videos

Last Updated: Mar 23, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.9K
Cross-Modal Multivariate Pattern Analysis
13:51

Cross-Modal Multivariate Pattern Analysis

Published on: November 9, 2011

20.6K
  • A multicategory support vector machine (MSVM) was employed with one-against-all and one-against-one strategies, utilizing RBF, linear, and polynomial kernels.
  • The synthetic minority class oversampling technique (SMOTE) was applied to address dataset imbalance, and model performance was evaluated using mean accuracy.

    • Main Results:

    • A balanced dataset combined with the RBF kernel and a one-against-one MSVM strategy achieved approximately 76% accuracy in predicting diabetic neuropathy class.
    • The study demonstrated the utility of data balancing techniques in improving classification performance for medical datasets.

    Conclusions:

    • The MSVM model, particularly when trained on a balanced dataset, shows significant potential for accurately predicting diabetic neuropathy severity.
    • Further research is recommended to explore the applicability of this MSVM approach for predicting other complex diseases.
    • This predictive model can support clinical decision-making and potentially reduce the incidence of severe diabetic complications.