Dataset Information

Probabilistic Forecasting of Anti-VEGF Treatment Frequency in Neovascular Age-Related Macular Degeneration.

ABSTRACT:

Purpose

To probabilistically forecast needed anti-vascular endothelial growth factor (anti-VEGF) treatment frequency using volumetric spectral domain-optical coherence tomography (SD-OCT) biomarkers in neovascular age-related macular degeneration from real-world settings.

Methods

SD-OCT volume scans were segmented with a custom deep-learning-based analysis pipeline. Retinal thickness and reflectivity values were extracted for the central and the four inner Early Treatment Diabetic Retinopathy Study (ETDRS) subfields for six retinal layers (inner retina, outer nuclear layer, inner segments [IS], outer segments [OS], retinal pigment epithelium-drusen complex [RPEDC] and the choroid). Machine-learning models were probed to predict the anti-VEGF treatment frequency within the next 12 months. Probabilistic forecasting was performed using natural gradient boosting (NGBoost), which outputs a full probability distribution. The mean absolute error (MAE) between the predicted versus actual anti-VEGF treatment frequency was the primary outcome measure.

Results

In a total of 138 visits of 99 eyes with neovascular AMD (96 patients) from two clinical centers, the prediction of future anti-VEGF treatment frequency was observed with an accuracy (MAE [95% confidence interval]) of 2.60 injections/year [2.25-2.96] (R2 = 0.390) using random forest regression and 2.66 injections/year [2.31-3.01] (R2 = 0.094) using NGBoost, respectively. Prediction intervals were well calibrated and reflected the true uncertainty of NGBoost-based predictions. Standard deviation of RPEDC-thickness in the central ETDRS-subfield constituted an important predictor across models.

Conclusions

The proposed, fully automated pipeline enables probabilistic forecasting of future anti-VEGF treatment frequency in real-world settings.

Translational relevance

Prediction of a probability distribution allows the physician to inspect the underlying uncertainty. Predictive uncertainty estimates are essential to highlight cases where human-inspection and/or reversion to a fallback alternative is warranted.

SUBMITTER: Pfau M

PROVIDER: S-EPMC8254013 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundTo reduce the treatment burden for patients with neovascular age-related macular degeneration (nvAMD), emerging therapies targeting vascular endothelial growth factor (VEGF) are being designed to extend the interval between treatments, thereby minimizing the number of intraocular injections. However, which patients will benefit from longer-acting agents is not clear.MethodsEyes with nvAMD (n = 122) underwent 3 consecutive monthly injections with currently available anti-VEGF therapies, followed by a treat-and-extend protocol. Patients who remained quiescent 12 weeks from their prior treatment entered a treatment pause and were switched to pro re nata (PRN) treatment (based on vision, clinical exam, and/or imaging studies). Proteomic analysis was performed on aqueous fluid to identify proteins that correlate with patients' response to treatment.ResultsAt the end of 1 year, 38 of 122 eyes (31%) entered a treatment pause (≥30 weeks). Conversely, 21 of 122 eyes (17%) failed extension and required monthly treatment at the end of year 1. Proteomic analysis of aqueous fluid identified proteins that correlated with patients' response to treatment, including proteins previously implicated in AMD pathogenesis. Interestingly, apolipoprotein-B100 (ApoB100), a principal component of drusen implicated in the progression of nonneovascular AMD, was increased in treated patients who required less frequent injections. ApoB100 expression was higher in AMD eyes compared with controls but was lower in eyes that develop choroidal neovascularization (CNV), consistent with a protective role. Accordingly, mice overexpressing ApoB100 were partially protected from laser-induced CNV.FundingThis work was supported by the National Eye Institute, National Institutes of Health grants R01EY029750, R01EY025705, and R01 EY27961; the Research to Prevent Blindness, Inc.; the Alcon Research Institute; and Johns Hopkins University through the Robert Bond Welch and Branna and Irving Sisenwein professorships in ophthalmology.ConclusionAqueous biomarkers could help identify patients with nvAMD who may not require or benefit from long-term treatment with anti-VEGF therapy.