GraD-IBD: Graph Representation Learning from Diagnosis Trajectories for Early Detection of Inflammatory Bowel Disease

2026-05-26

AI Summary

This work addresses the challenge of modeling irregular, hierarchical ICD diagnosis sequences for early risk prediction of inflammatory bowel disease (IBD), a task often hindered by computational inefficiency and modeling complexity. To this end, the authors propose a time-directed graph-based graph neural network approach that reconstructs patients’ longitudinal ICD trajectories into a temporal graph structure by grouping codes within clinical visits. A context-aware, time-decay message-passing mechanism is designed to effectively capture temporal dependencies while substantially reducing computational complexity. Evaluated on real-world clinical data, the proposed method significantly outperforms existing models in early IBD detection performance and achieves lower computational overhead.

Abstract

International Classification of Diseases (ICD) is a globally recognized coding system that records diagnostic events during each patient encounter, providing a standardized data foundation for various clinical tasks. However, the irregular and hierarchical nature of ICD code sequences poses challenges for N-D lattice-based sequential modeling methods, leading to overly complex model designs. In this paper, we propose GraD-IBD, a graph diagnosis model that reformulates longitudinal ICD trajectories as visit-bucketized, temporally directed graphs to detect the risk of inflammatory bowel disease (IBD). A novel context-aware, time-decay message passing mechanism was developed to capture temporal dependencies while reducing model complexity. The experimental results using a real-world clinical dataset demonstrated consistent and robust improvements in IBD detection over state-of-the-art methods, with significant reductions in computational complexity compared to sequential models. These findings highlight the potential of graph representation learning to enable efficient, scalable, and accurate disease risk prediction from longitudinal ICD diagnosis codes.

Problem

• Inflammatory Bowel Disease
• ICD codes
• diagnosis trajectories
• early detection
• graph representation learning

Innovation

• graph representation learning
• diagnosis trajectories
• time-decay message passing
• ICD codes
• inflammatory bowel disease