Clustering disease trajectories in contrastive feature space for biomarker discovery in age-related macular degeneration

TL;DR

This paper introduces a novel contrastive learning-based method to analyze temporal disease progression in AMD, enabling discovery of interpretable biomarkers predictive of disease conversion and surpassing traditional static grading systems.

Contribution

It presents the first approach to automatically identify dynamic biomarkers in AMD by modeling patient trajectories in a contrastive feature space and clustering these to reveal progression patterns.

Findings

Biomarkers predicted conversion to late AMD.

Clusters aligned with known disease progression patterns.

Method outperforms static grading in predictive power.

Abstract

Age-related macular degeneration (AMD) is the leading cause of blindness in the elderly. Current grading systems based on imaging biomarkers only coarsely group disease stages into broad categories and are unable to predict future disease progression. It is widely believed that this is due to their focus on a single point in time, disregarding the dynamic nature of the disease. In this work, we present the first method to automatically discover biomarkers that capture temporal dynamics of disease progression. Our method represents patient time series as trajectories in a latent feature space built with contrastive learning. Then, individual trajectories are partitioned into atomic sub-sequences that encode transitions between disease states. These are clustered using a newly introduced distance metric. In quantitative experiments we found our method yields temporal biomarkers that are predictive of conversion to late AMD. Furthermore, these clusters were highly interpretable to ophthalmologists who confirmed that many of the clusters represent dynamics that have previously been linked to the progression of AMD, even though they are currently not included in any clinical grading system.