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: Jan 19, 2026

Tear-Derived Exosomal miR-15a as New Diagnostic Tool for Diabetic Retinopathy
07:45

Tear-Derived Exosomal miR-15a as New Diagnostic Tool for Diabetic Retinopathy

Published on: December 30, 2025

245

Deep learning algorithm predicts diabetic retinopathy progression in individual patients.

Filippo Arcadu1,2, Fethallah Benmansour1,2, Andreas Maunz1,2

  • 11Roche Informatics, Roche, Basel, Switzerland.

NPJ Digital Medicine
|September 26, 2019
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

The role of interleukin-6 in diabetic retinal disease: pathophysiology and therapeutic targeting.

Frontiers in immunology·2026
Same author

Interleukin 6 Inhibition With Vamikibart for Uveitic Macular Edema: The Phase 1 DOVETAIL Nonrandomized Clinical Trial.

JAMA ophthalmology·2026
Same author

Correction: Artificial intelligence-based analysis of retinal fluid volume dynamics in neovascular age-related macular degeneration and association with vision and atrophy.

Eye (London, England)·2026
Same author

Targeting IL-6 Receptor Signaling with Satralizumab in Thyroid Eye Disease: Design of the Phase 3 SatraGO-1 and SatraGO-2 Trials.

Ophthalmology and therapy·2025
Same author

Progression of diabetic retinopathy in a longitudinal real-world study of patients in primary care.

BMC ophthalmology·2025
Same author

Author Response: Letter to the Editor Regarding "Intraretinal Hyper-Reflective Foci Are Almost Universally Present and Co-Localize With Intraretinal Fluid in Diabetic Macular Edema".

Investigative ophthalmology & visual science·2025
This summary is machine-generated.

A new deep learning algorithm predicts diabetic retinopathy (DR) progression using single-visit fundus photos. This may enable earlier intervention and improved patient monitoring for this leading cause of vision loss.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic retinopathy (DR) is a major cause of vision loss globally, with increasing prevalence.
  • Predicting DR progression is crucial for timely intervention and management.

Purpose of the Study:

  • To develop and evaluate a deep learning (DL) algorithm for predicting diabetic retinopathy progression using color fundus photographs (CFPs).
  • To assess the feasibility of predicting DR worsening from a single patient visit's imaging data.

Main Methods:

  • Deep learning models were trained to predict a 2-step worsening on the Early Treatment Diabetic Retinopathy Diabetic Retinopathy Severity Scale.
  • Models used CFPs from a single visit as input, with progression assessed at 6, 12, and 24 months by human graders.
Keywords:
Macular degenerationPredictive markersVision disorders

More Related Videos

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression
04:36

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Published on: January 12, 2024

1.6K
Studying Diabetes Through the Eyes of a Fish: Microdissection, Visualization, and Analysis of the Adult tgfli:EGFP Zebrafish Retinal Vasculature
10:07

Studying Diabetes Through the Eyes of a Fish: Microdissection, Visualization, and Analysis of the Adult tgfli:EGFP Zebrafish Retinal Vasculature

Published on: December 26, 2017

14.0K

Related Experiment Videos

Last Updated: Jan 19, 2026

Tear-Derived Exosomal miR-15a as New Diagnostic Tool for Diabetic Retinopathy
07:45

Tear-Derived Exosomal miR-15a as New Diagnostic Tool for Diabetic Retinopathy

Published on: December 30, 2025

245
Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression
04:36

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Published on: January 12, 2024

1.6K
Studying Diabetes Through the Eyes of a Fish: Microdissection, Visualization, and Analysis of the Adult tgfli:EGFP Zebrafish Retinal Vasculature
10:07

Studying Diabetes Through the Eyes of a Fish: Microdissection, Visualization, and Analysis of the Adult tgfli:EGFP Zebrafish Retinal Vasculature

Published on: December 26, 2017

14.0K
  • Model performance was evaluated using the area under the curve (AUC).

    • Main Results:

    • One model achieved an AUC of 0.79 for predicting DR progression at 12 months.
    • Peripheral retinal fields and microvascular abnormalities were identified as important predictive features.
    • The study demonstrated the feasibility of predicting DR progression from single-visit CFPs.

    Conclusions:

    • A DL algorithm can effectively predict diabetic retinopathy progression using readily available fundus photographs.
    • This technology holds potential for earlier diagnosis, targeted monitoring, and improved clinical trial recruitment for DR.
    • Further development with larger datasets could enhance the algorithm's clinical utility for managing vision loss due to DR.