Phenotyping of Patients with Age-Related Macular Degeneration Using Artificial Intelligence-Driven Biomarker Patterns in OCT.

PURPOSE: To leverage artificial intelligence-based OCT analysis to classify age-related macular degeneration (AMD) images into distinct subgroups based on retinal layer and fluid biomarkers.

DESIGN

Retrospective analysis of a data set of retinal OCT images.

PARTICIPANTS

Anonymized data from 157 patients with AMD and 58 healthy volunteers.

METHODS

This study analyzed OCT scans from patients with AMD and healthy volunteers to extract retinal layer thickness and fluid biomarkers by artificial intelligence-driven image segmentation. We performed dimensionality reduction using parametric Uniform Manifold Approximation and Projection, followed by k-means clustering to partition the continuous disease space into 9 subphenotypes for analysis. Statistical analyses included linear mixed-effects modeling, analysis of variance, and Fisher exact tests to assess biomarker differences, visual acuity (VA), and lesion size across clusters. We mapped International Classification of Diseases, 10th Revision (ICD-10) codes to validate disease staging.

MAIN OUTCOME MEASURES: We examined the potential of artificial intelligence-driven biomarker patterns based on the comparison to traditional clinical measures such as VA, lesion size, and ICD-10 codes for different disease stages.

RESULTS

By dividing the continuous landscape into 9 regions for interpretability, we observed that each cluster was characterized by a distinct biomarker pattern. Clusters exhibited outer retinal thinning of varying degrees and showed significant differences in inner retinal layers, choroidal thickness, subretinal pigment epithelium material, and fluid presence compared with a healthy cohort, suggesting diverse AMD subtypes beyond simple characterization by VA and atrophic lesion size alone. The distribution of ICD-10 codes further supported the interpretation of the AMD landscape as a representation of AMD progression.

CONCLUSIONS

This study reveals a continuous AMD landscape based on OCT-derived biomarkers, suggesting the existence of subphenotypes beyond traditional staging methods. The findings further highlight the limitations of fundus-based disease classification and support the role of OCT scans in personalized disease management.

FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.