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

Learning ensemble classifiers for diabetic retinopathy assessment.

Emran Saleh1, Jerzy Błaszczyński2, Antonio Moreno1

  • 1Departament d'Enginyeria Informàtica i Matemàtiques, Universitat Rovira i Virgili, Tarragona, Spain.

Artificial Intelligence in Medicine
|October 11, 2017
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

Exogenous Mitochondrial Transfer in Differentiating Brown Adipocytes and AGPAT2-Deficient Preadipocytes.

Journal of visualized experiments : JoVE·2026
Same author

DDFU-Net: A Deep Decoder-Focused U-Net Model for Retinal Lesion Segmentation.

Annals of biomedical engineering·2026
Same author

S<sup>2</sup>CIE: semantic, syntactic, and context-based information extraction for AOP development.

Environment international·2025
Same author

Peptidylarginine Deiminase (PAD) Inhibitor Optimization through Displacement of a Trapped Water Molecule.

ACS medicinal chemistry letters·2025
Same author

Coil or plug-assisted retrograde transvenous obliteration (CARTO/PARTO) for treating portal hypertensive variceal bleeding: A multicenter, real-world 10-year retrospective study.

Hepatology (Baltimore, Md.)·2025
Same author

Two Handheld Retinograph Devices Evaluated by Ophthalmologists and an Artificial Intelligence Algorithm.

Journal of clinical medicine·2024

Diabetic retinopathy screening can be improved using new AI tools. These methods help identify high-risk patients, optimizing resource allocation and reducing costs for diabetic eye disease detection.

Area of Science:

  • Medical informatics
  • Machine learning
  • Computational biology

Background:

  • Diabetic retinopathy is a common diabetes complication.
  • Annual eye screenings are resource-intensive.
  • Improved risk stratification is needed for efficient screening.

Purpose of the Study:

  • To develop AI-driven tools for diabetic retinopathy risk assessment.
  • To enable personalized screening frequencies based on patient risk.
  • To optimize resource allocation in diabetes care.

Main Methods:

  • Utilized ensemble classifiers: fuzzy random forest and dominance-based rough set balanced rule ensemble.
  • Employed a small set of key risk factors for classification.
  • Evaluated classifier performance using specificity and sensitivity metrics.
Keywords:
Class imbalanceDecision support systemsDiabetic retinopathyDominance-based rough set approachEnsemble classifiersFuzzy decision treesRandom forestRule-based models

Related Experiment Videos

Main Results:

  • Achieved specificity and sensitivity levels exceeding 80%.
  • Demonstrated the potential of ensemble classifiers in predicting diabetic retinopathy risk.
  • Identified key risk factors for developing the condition.

Conclusions:

  • The study presents a successful initial step towards a personalized decision support system.
  • These AI tools can assist physicians in clinical practice for diabetic retinopathy management.
  • Potential for improved resource utilization in diabetic patient eye care.