Mode
Text Size
Log in / Sign up

AI-based fluid volume quantification predicts visual acuity in neovascular AMD better than CST

AI-based fluid volume quantification predicts visual acuity in neovascular AMD better than CST
Photo by Shubham Dhage / Unsplash
Key Takeaway
Consider that AI-based fluid volume quantification may better predict visual acuity than CST in pretreated nAMD, but evidence is limited.

This randomized phase III clinical trial evaluated AI-based quantification of macular fluid volumes (intraretinal fluid [IRF], subretinal fluid [SRF], pigment epithelial detachment [PED]) versus central subfield thickness (CST) in 290 eyes of 290 participants with active neovascular age-related macular degeneration (nAMD), including both treatment-naïve and previously treated patients in a real-world setting. The primary outcome was the association between best-corrected visual acuity (BCVA) and quantitative macular fluid volumes.

Results showed that IRF volumes within each macular region were significantly greater in treatment-naïve patients. In pretreated patients, larger PED volumes contributed to higher CST values. The 6-mm fluid model (IRF and SRF) explained the largest proportion of BCVA variance, with adjusted R values of 0.140 for IRF and 0.225 for SRF. In contrast, CST explained only half as much BCVA variance in pretreated eyes. However, in the treatment-naïve subgroup, the fluid model fit was poorer compared to the CST model (adjusted R = 0.078 vs. 0.198).

Safety and tolerability data were not reported, and limitations were not specified in the available information. The study did not report follow-up duration, and effect sizes with confidence intervals were not provided for most outcomes, limiting the precision of the findings.

These results suggest that AI-based quantification of IRF and SRF volumes may be a more relevant surrogate for visual function loss or benefit in nAMD than CST, particularly in pretreated patients. However, the weaker performance in treatment-naïve eyes and the lack of reported safety data indicate that further research is needed before clinical adoption.

Study Details

Study typeRct
Sample sizen = 290
EvidenceLevel 2
PublishedMay 2026
View Original Abstract ↓
PURPOSE: To investigate the association between best-corrected visual acuity (BCVA) and quantitative macular fluid volumes, compared to central subfield thickness (CST) in treatment-naïve and previously treated patients with active neovascular age-related macular degeneration (nAMD). METHODS AND ANALYSIS: Baseline data were collected from 290 eyes of 290 participants consecutively enrolled in a prospective, randomized phase III clinical trial. Intraretinal fluid (IRF), subretinal fluid (SRF) and pigment epithelial detachment (PED) volumes were quantified and localized using an MDR-certified AI algorithm (Fluid Monitor, RetInSight). Fluid volumes and CST were included in linear regression models for comparison. RESULTS: Significantly greater IRF volumes within each macular region were observed in treatment-naïve patients, whereas larger PED volumes contributed to higher CST values in pretreated patients. In both subgroups, the largest proportion of BCVA variance could be explained by measuring IRF and SRF volumes within the entire 6-mm area (adjusted R = 0.140 and 0.225, respectively). In pre-treated eyes, CST explained only half as much BCVA variance as the 6-mm fluid model, and the model's fit was even poorer when compared to the CST model in the treatment-naïve subgroup (adjusted R = 0.078 vs. 0.198). CONCLUSION: The examination of IRF and SRF volumes significantly impacts BCVA in nAMD. The weaker association of CST highlights its limitations as a parameter of disease activity. These findings emphasize the necessity of distinct fluid volume quantification as a relevant surrogate for visual function loss or benefit in nAMD, with particular emphasis on treatment duration and fluid in regions beyond the central 1-mm.
Free Newsletter

Clinical research that matters. Delivered to your inbox.

Join thousands of clinicians and researchers. No spam, unsubscribe anytime.