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

A novel electrocardiogram-synchronized laser Doppler holography system for cardiac cycle-resolved retinal hemodynamics: development and validation.

Scientific reports·2026
Same author

Retinal imaging and supervised learning predict hospitalizations and kidney and heart-lung damage in sickle cell disease.

Blood advances·2026
Same author

Elevated prevalence of age-related macular degeneration in a low-income urban primary care setting.

Discover public health·2026
Same author

The Sleeping Wolf - Widefield OCT Angiography Revelations of Insidious Systemic Lupus Erythematous-Associated Retinal Vasculitis.

Retinal cases & brief reports·2026
Same author

Subretinal drusenoid deposits are strongly associated with coexistent high-risk vascular diseases.

BMJ open ophthalmology·2026
Same author

Re: Chen et al.: High-density lipoproteins associated with age-related macular degeneration in the All of Us research program (Ophthalmology. 2025;132:684-691).

Ophthalmology·2025

Related Experiment Video

Updated: Sep 24, 2025

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

Automated diabetic retinopathy screening for primary care settings using deep learning.

Alauddin Bhuiyan1,2, Arun Govindaiah1, Avnish Deobhakta2

  • 1iHealthScreen Inc, NY, USA.

Intelligence-Based Medicine
|May 9, 2022
PubMed
Summary

An AI tool for diabetic retinopathy (DR) screening shows high accuracy in detecting referable DR. This automated system offers a promising solution for early diagnosis and prevention of blindness in primary care settings.

Keywords:
Deep learningDiabetic retinopathyFundus imaging

More Related Videos

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.8K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.7K

Related Experiment Videos

Last Updated: Sep 24, 2025

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
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.8K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.7K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic Retinopathy (DR) is a leading cause of blindness in developed countries.
  • Early detection of DR is crucial for preventing vision loss.
  • Automated screening tools can improve DR detection in primary care.

Purpose of the Study:

  • To validate a cloud-based, AI-powered tool for automated screening of Diabetic Retinopathy.
  • To assess the tool's performance on large public datasets and in real-world primary care settings.

Main Methods:

  • Deep learning techniques were used to develop the AI screening model.
  • The model was trained on 88,702 images from Kaggle and validated on 1,748 images from Messidor-2.
  • Prospective validation was conducted using 264 images from two diabetes clinics.

Main Results:

  • The AI tool achieved high sensitivity (99.21%) and specificity (97.59%) on the Kaggle dataset (AUC: 0.9992).
  • External validation on Messidor-2 showed sensitivity of 97.63% and specificity of 99.49% (AUC: 0.9985).
  • In primary care, the tool demonstrated 92.3% sensitivity and 94.8% specificity.

Conclusions:

  • The AI-based DR screening tool exhibits state-of-the-art performance.
  • The tool's accuracy and reliability make it suitable for early DR screening and diagnosis in primary care.