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

System construction for sui generis right of digital sequence information on genetic resources in China.

Yi chuan = Hereditas·2026
Same author

Modified Double Filtration Plasmapheresis Exchange for Managing Sepsis-Induced Shock.

Clinical laboratory·2026
Same author

The clinical and genetic profiles, management, and treatment outcomes of familial exudative vitreoretinopathy.

Survey of ophthalmology·2026
Same author

Neuropeptide Y co-opts neuronal ensembles for memory lability and stability.

Nature neuroscience·2026
Same author

More Trustworthy Prediction of Elastic Modulus of Recycled Aggregate Concrete Using MCBE and TabPFN.

Materials (Basel, Switzerland)·2025
Same author

Xiaoyaosan alleviates CUMS rat by promoting hippocampal neurogenesis via modulating the JNK/GluR1 signaling pathway.

Journal of affective disorders·2025

Related Experiment Video

Updated: Sep 21, 2025

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats
07:41

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats

Published on: October 23, 2020

6.0K

The Validation of Deep Learning-Based Grading Model for Diabetic Retinopathy.

Wen-Fei Zhang1,2, Dong-Hong Li3, Qi-Jie Wei3

  • 1Department of Ophthalmology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, China.

Frontiers in Medicine
|June 2, 2022
PubMed
Summary

Deep learning software EyeWisdom V1 shows high accuracy in diagnosing diabetic retinopathy (DR) from fundus images. This AI tool offers reliable grading and referral recommendations for diabetic patients.

Keywords:
artificial intelligencediabetic retinopathyeye wisdom V1sensitivityspecificityvalidation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Retinal Pathophysiological Evaluation in a Rat Model
09:11

Retinal Pathophysiological Evaluation in a Rat Model

Published on: May 6, 2022

4.8K

Related Experiment Videos

Last Updated: Sep 21, 2025

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats
07:41

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats

Published on: October 23, 2020

6.0K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Retinal Pathophysiological Evaluation in a Rat Model
09:11

Retinal Pathophysiological Evaluation in a Rat Model

Published on: May 6, 2022

4.8K

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Diabetic retinopathy (DR) is a leading cause of vision loss in diabetic patients.
  • Early detection and grading of DR are crucial for timely intervention and prevention of blindness.
  • Current diagnostic methods rely on manual grading of fundus images, which can be time-consuming and subjective.

Purpose of the Study:

  • To evaluate the diagnostic performance of EyeWisdom V1, a deep learning-based artificial intelligence (AI) software, for detecting and grading diabetic retinopathy.
  • To assess the reliability of EyeWisdom V1 in providing referral recommendations for diabetic patients.

Main Methods:

  • A prospective, multicenter, double-blind, and self-controlled clinical trial was conducted.
  • Non-dilated posterior pole fundus images from 630 diabetic patients (1,089 images) were analyzed.
  • EyeWisdom V1's diagnoses were compared against manual grading by ophthalmologists, considered the gold standard.

Main Results:

  • EyeWisdom V1 demonstrated high sensitivity (98.23%) and NPV (96.23%) for any DR detection.
  • For referral DR, the AI achieved a sensitivity of 92.96% and specificity of 93.32%, with an AUC of 0.958.
  • The software showed strong agreement with manual grading, indicated by a kappa score of 0.860.

Conclusions:

  • EyeWisdom V1 provides reliable diabetic retinopathy grading and referral recommendations.
  • The AI software shows potential to assist ophthalmologists in managing diabetic eye care.
  • AI-powered tools like EyeWisdom V1 can enhance the efficiency and accuracy of DR screening.