A new study has shown that artificial intelligence (AI) can help track how well a new treatment works for people neovascular age-related macular degeneration (nAMD).
The retrospective real-world study analysed patients with treatment-resistant nAMD who switched to Faricimab following inadequate responses to ranibizumab or aflibercept.
Researchers used a deep learning algorithm to measure specific features in the eye using optical coherence tomography (OCT). The AI identified and measured key indicators such as fluid buildup and tissue changes in a total of 46 eyes from 41 patients, over nine months.
The AI tool found significant reductions in fluid and tissue swelling, which remained stable through the end of the study. One measure, central retinal thickness, dropped from an average of 342.7 micrometres at the start to 296.6 micrometres at three months, and 310.2 micrometres at nine months.
… the findings highlight the potential of AI-driven biomarker segmentation as a precise and scalable tool for monitoring disease progression in treatment-resistant nAMD
The number of days between eye injections increased from a median of 35 to 56 days. Vision remained stable, and people who started with more swelling tended to show more improvement and needed injections less often.
Study authors said the findings highlight the potential of AI-driven biomarker segmentation as a precise and scalable tool for monitoring disease progression in treatment-resistant nAMD.
They said Faricimab demonstrated significant and sustained anatomical improvements, allowing for extended treatment intervals while maintaining disease stability.
“Future research should focus on refining AI models to improve predictive accuracy and assessing long-term outcomes to further optimise disease management,” the study concluded.
Reference
- Hafner, M., Eckardt, F., Siedlecki, J. et al. Deep learning assisted analysis of biomarker changes in refractory neovascular AMD after switch to faricimab. Int J Retin Vitr2025;11(44). doi: 10.1186/s40942-025-00669-2.
