Training Together, Diagnosing Better: Federated Learning for Collagen VI-Related Dystrophies

2025-12-18

AI Summary

Rare diseases like collagen VI-related dystrophies (COL6-RD) suffer from scarce, fragmented, and privacy-restricted data, impeding development of robust machine learning–based diagnostic models. Method: We propose the first cross-institutional federated learning framework for COL6-RD diagnosis, leveraging multi-center, distributed immunofluorescence images of dermal fibroblasts. A convolutional neural network is collaboratively trained without raw data leaving local sites, enabling precise subtyping of three pathogenic mechanisms: exon skipping, glycine substitutions, and pseudoexon insertions. Contribution/Results: This work pioneers federated learning for mechanism-level pathological diagnosis in COL6-RD, overcoming data silos and privacy constraints. The framework achieves an F1-score of 0.82—significantly surpassing single-center baselines (0.57–0.75). It further supports clinical interpretation of variants of uncertain significance (VUS) and prioritizes novel pathogenic variant screening, demonstrating strong generalizability and interpretability.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Multi-modal Vision
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The application of Machine Learning (ML) to the diagnosis of rare diseases, such as collagen VI-related dystrophies (COL6-RD), is fundamentally limited by the scarcity and fragmentation of available data. Attempts to expand sampling across hospitals, institutions, or countries with differing regulations face severe privacy, regulatory, and logistical obstacles that are often difficult to overcome. The Federated Learning (FL) provides a promising solution by enabling collaborative model training across decentralized datasets while keeping patient data local and private. Here, we report a novel global FL initiative using the Sherpa.ai FL platform, which leverages FL across distributed datasets in two international organizations for the diagnosis of COL6-RD, using collagen VI immunofluorescence microscopy images from patient-derived fibroblast cultures. Our solution resulted in an ML model capable of classifying collagen VI patient images into the three primary pathogenic mechanism groups associated with COL6-RD: exon skipping, glycine substitution, and pseudoexon insertion. This new approach achieved an F1-score of 0.82, outperforming single-organization models (0.57-0.75). These results demonstrate that FL substantially improves diagnostic utility and generalizability compared to isolated institutional models. Beyond enabling more accurate diagnosis, we anticipate that this approach will support the interpretation of variants of uncertain significance and guide the prioritization of sequencing strategies to identify novel pathogenic variants.

Problem

• Diagnosing rare collagen VI dystrophies with fragmented patient data across institutions
• Overcoming privacy and regulatory barriers in multi-center medical data sharing
• Improving diagnostic accuracy for genetic variants using decentralized collaborative learning

Innovation

• Federated Learning enables collaborative training across decentralized datasets
• Sherpa.ai platform leverages distributed data from international organizations
• Model classifies collagen VI images into three pathogenic mechanism groups