Enhanced Atrial Fibrillation Prediction in ESUS Patients with Hypergraph-based Pre-training

TL;DR

This paper introduces hypergraph-based pre-training methods that leverage large stroke datasets to enhance atrial fibrillation prediction in ESUS patients, overcoming data limitations and improving accuracy.

Contribution

It presents novel hypergraph pre-training strategies that transfer learned embeddings from large cohorts to small ESUS datasets for better AF prediction.

Findings

Pre-training improves prediction accuracy over traditional models.

Hypergraph embeddings capture higher-order clinical interactions.

Framework is scalable and reduces feature dimensionality.

Abstract

Atrial fibrillation (AF) is a major complication following embolic stroke of undetermined source (ESUS), elevating the risk of recurrent stroke and mortality. Early identification is clinically important, yet existing tools face limitations in accuracy, scalability, and cost. Machine learning (ML) offers promise but is hindered by small ESUS cohorts and high-dimensional medical features. To address these challenges, we introduce supervised and unsupervised hypergraph-based pre-training strategies to improve AF prediction in ESUS patients. We first pre-train hypergraph-based patient embedding models on a large stroke cohort (7,780 patients) to capture salient features and higher-order interactions. The resulting embeddings are transferred to a smaller ESUS cohort (510 patients), reducing feature dimensionality while preserving clinically meaningful information, enabling effective prediction with lightweight models. Experiments show that both pre-training approaches outperform traditional models trained on raw data, improving accuracy and robustness. This framework offers a scalable and efficient solution for AF risk prediction after stroke.