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

Generalization of AI-Based Gestational Age Assessment Using Blind Sweep Ultrasonography.

JAMA network open·2026
Same author

Towards Conversational AI for Disease Management.

Nature·2026
Same author

Advancing conversational diagnostic AI with multimodal reasoning.

Nature medicine·2026
Same author

Retinopathy of prematurity: A global review of screening guidelines.

Survey of ophthalmology·2026
Same author

Anti-vascular endothelial growth factors in retinal and choroidal diseases - Present landscape.

Indian journal of ophthalmology·2026
Same author

Validation of the FIRST-ROP algorithm in a tertiary care center in Greece.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2026

Related Experiment Video

Updated: May 21, 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

2.6K

Performance of a Deep Learning Diabetic Retinopathy Algorithm in India.

Arthur Brant1, Preeti Singh2, Xiang Yin2

  • 1Oregon Vision and Pharmacy LLC, Keizer.

JAMA Network Open
|March 19, 2025
PubMed
Summary
This summary is machine-generated.

This study shows that the automated retinal disease assessment (ARDA) algorithm demonstrates high accuracy in detecting diabetic retinopathy (DR) and diabetic macular edema (DME) in a real-world clinical setting. The ARDA algorithm achieved over 96% sensitivity and specificity for severe DR detection.

More Related Videos

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.4K
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

5.6K

Related Experiment Videos

Last Updated: May 21, 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

2.6K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.4K
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

5.6K

Area of Science:

  • Ophthalmology
  • Medical Artificial Intelligence
  • Public Health

Background:

  • Prospective studies have evaluated artificial intelligence (AI) for diabetic retinopathy (DR) and diabetic macular edema (DME) detection, but clinical performance data post-deployment are limited.
  • Real-world validation of AI algorithms is crucial for understanding their effectiveness in diverse clinical settings.

Purpose of the Study:

  • To assess the clinical performance of the automated retinal disease assessment (ARDA) algorithm in a post-deployment setting.
  • To compare the ARDA algorithm's grading of fundus photographs against expert ophthalmologist adjudication for DR and DME detection.

Main Methods:

  • A cross-sectional analysis of fundus photographs from patients screened using ARDA at Aravind Eye Hospital, India.
  • Images were adjudicated by US ophthalmologists for DR and DME, with ARDA's output compared against these grades.
  • Analysis included sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for various stages of DR.

Main Results:

  • ARDA demonstrated high sensitivity (97.0%) and specificity (96.4%) for severe nonproliferative DR (NPDR) or proliferative DR (PDR).
  • The algorithm achieved 95.9% sensitivity and 94.9% specificity for sight-threatening DR (STDR).
  • The miss rate for clinically significant DR requiring referral was 0%, with a negative predictive value of 99.9% for severe NPDR/PDR.

Conclusions:

  • The ARDA algorithm exhibits excellent clinical performance in detecting DR and DME in a large-scale, post-deployment setting.
  • The findings support the utility of ARDA as a reliable tool for DR screening, aligning with regulatory recommendations for algorithm monitoring.
  • Continued monitoring and publication of AI algorithm performance are essential for ensuring patient safety and effective clinical integration.