GraD-IBD: Graph Representation Learning from Diagnosis Trajectories for Early Detection of Inflammatory Bowel Disease
arXiv:2605.27799v1 Announce Type: new 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 t
The increasing availability of digitized patient data and advancements in graph neural networks are enabling more sophisticated AI applications in healthcare.
This development can significantly improve early disease detection, leading to better patient outcomes and potentially reducing healthcare costs by leveraging existing medical record systems.
The proposed GraD-IBD model offers a novel, more efficient way to leverage longitudinal diagnosis trajectories for early disease detection, departing from traditional sequential modeling.
- · Healthcare providers
- · Patients with chronic diseases
- · AI in healthcare companies
- · Medical data analytics firms
- · Traditional diagnostic methods
- · Healthcare systems with poor data integration
Early and more accurate diagnosis of diseases like Inflammatory Bowel Disease will become more common.
This could lead to a shift in how chronic diseases are managed, moving towards preventative and early intervention strategies.
The success of such models could accelerate the adoption of graph-based AI for other complex medical diagnoses and predictions globally.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI