ScholarDeck

AI / informaticsNPJ digital medicine · 2026

Treatment effects prediction and clinical decision-making system for retinal vein occlusion by artificial intelligence.

He-Yan Li, Jin-Jie Guo, Guo-Jiao Song … Lei Shao

Read paper

OphthalmologyAI / informatics

AI system predicted need for retreatment in retinal vein occlusion with high accuracy

Treatment effects prediction and clinical decision-making system for retinal vein occlusion by artificial intelligence.

He-Yan Li … Lei Shao

NPJ digital medicine · 2026

Background

Retinal vein occlusion (retinal vein occlusion) is a chronic retinal vascular disease that often requires repeated anti-VEGF injections and long-term follow-up.

Results

AI correctly flagged which patients would need repeat treatment most of the time

internal test dataset

0.854AUC

external test dataset

0.744AUC

More results

However, predicting treatment responses across different follow-up timepoints remains clinically challenging.

To address this issue, we developed an AI system integrating generative adversarial networks (generative adversarial networks), UNet + +, and ResNet-101 to generate post-treatment OCT and fundus images and support clinical decision-making.

More results

The generated images demonstrated favorable visual quality, as evaluated by mean absolute error (mean absolute error), peak signal-to-noise ratio (peak signal-to-noise ratio), and structural similarity index measure (structural similarity index measure).

“

Conclusion

Clinicians' predictive performance also improved with AI assistance.

Post

Treatment effects prediction and clinical decision-making system for retinal vein occlusion by artificial intelligence.

AI system predicted need for retreatment in retinal vein occlusion with high accuracy

Related papers