DT-BEHRT: Disease Trajectory-aware Transformer for Interpretable Patient Representation Learning

ICLR 2026 Conference Submission13310 Authors

Keywords: Electronic Health Records (EHR), Predictive Modeling, Clinical Interpretability

TL;DR: We present DT-BEHRT, a graph-enhanced transformer that models disease trajectories in EHR to improve predictive performance and clinical interpretability.

Abstract: The growing adoption of electronic health record (EHR) systems has provided unprecedented opportunities for predictive modeling to guide clinical decision making. Structured EHRs contain longitudinal observations of patients across hospital visits, where each visit is represented by a set of medical codes. While sequence-based, graph-based, and graph-enhanced sequence approaches have been developed to capture rich code interactions over time or within the same visits, they often overlook the inherent heterogeneous roles of medical codes arising from distinct clinical characteristics and contexts. To this end, in this study we propose the Disease Trajectory-aware Transformer for EHR (DT-BEHRT), a graph-enhanced sequential architecture that disentangles disease trajectories by explicitly modeling diagnosis-centric interactions within organ systems and capturing asynchronous progression patterns. To further enhance the representation robustness, we design a tailored pre-training methodology that combines trajectory-level code masking with ontology-informed ancestor prediction, promoting semantic alignment across multiple modeling modules. Extensive experiments on multiple benchmark datasets demonstrate that DT-BEHRT achieves strong predictive performance and provides interpretable patient representations that align with clinicians’ disease-centered reasoning.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 13310