aiqbench analysis
This research introduces Clinical Graph-JEPA, a framework that leverages Joint Embedding Predictive Architectures (JEPA) to construct dynamic, predictive knowledge graphs from clinical records like MIMIC-IV. By treating the graph as a latent representation of patient state rather than a static artifact, the method significantly improves edge recovery and relation inference compared to standard extraction techniques. The approach demonstrates that injecting discharge-note embeddings into note-grounded entities yields substantial gains in measuring missing clinical relations without data leakage.
Clinical Graph-JEPA: Predictive Patient-State Knowledge Graphs for Cognitive Decision Support
arXiv:2608.22583v1 Announce Type: cross Abstract: Clinical records contain rich evidence about patient state, but converting that evidence into reliable, structured knowledge graphs remains difficult because extraction errors, ontology mismatch, missing relations, and temporal ambiguity can propagate into downstream systems. We propose a clinical knowledge graph construction and refinement framework that combines multi-agent relation proposal, ontology-aware normalization, deterministic evidence scoring, and JEPA-based latent refinement. Rather than treating a clinical knowledge graph as a static extraction artifact, we treat it as a predictive patient-state representation. For each admission, the system constructs an evidence-scored graph from structured MIMIC-IV records and inferred clinical cross-links, then learns to recover held-out clinical relations from the observed graph context. We evaluate the refiner with leakage-free leave-one-out edge recovery (MRR and Hits@k) and held-out batch-mask evaluation (AUC and MRR). To isolate the contribution of discharge-note context, we compare a note-embedding-free configuration with a note-augmented configuration that injects real discharge-note representations only into note-grounded entities. Under the same cohort and evaluation protocol, entity-grounded note injection improves overall leave-one-out MRR by 31% relative improvement.
Abstract:Clinical records contain rich evidence about patient state, but converting that evidence into reliable, structured knowledge graphs remains difficult because extraction errors, ontology mismatch, missing relations, and temporal ambiguity can propagate into downstream systems. We propose a clinical knowledge graph construction and refinement framework that combines multi-agent relation proposal, ontology-aware normalization, deterministic evidence scoring, and JEPA-based latent refinement. Rather than treating a clinical knowledge graph as a static extraction artifact, we treat it as a predictive patient-state representation. For each admission, the system constructs an evidence-scored graph from structured MIMIC-IV records and inferred clinical cross-links, then learns to recover held-out clinical relations from the observed graph context. We evaluate the refiner with leakage-free leave-one-out edge recovery (MRR and Hits@k) and held-out batch-mask evaluation (AUC and MRR). To isolate the contribution of discharge-note context, we compare a note-embedding-free configuration with a note-augmented configuration that injects real discharge-note representations only into note-grounded entities. Under the same cohort and evaluation protocol, entity-grounded note injection improves overall leave-one-out MRR by 31% relative improvement.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2608.22583 [cs.LG]
(or arXiv:2608.22583v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.22583 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 266 words
Related coverage
Trajectory-Aware Clinical Risk Prediction via Severity-Grounded Knowledge Graphs and Retrieval-Augmented Generation
arXiv · Oct 2, 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026
Feedback-Robust AI for Patient Knowledge Graphs
arXiv · Sep 30, 2026
Microsoft’s AI chief says superintelligence is near, but won’t take your job
The Verge · Jun 8, 2026