Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication
UID-preserving multimodal framework plus GAVEL LLM judge improves clinical timeline reconstruction, boosting event recovery 43% over prior matching.
The paper introduces a UID-preserving framework linking each narrative clinical event to its source span through text-only estimation, structured-evidence retrieval, timestamped source-row grounding, and joint revision. GAVEL, an LLM judge, compares UID-aligned timelines against narrative and structured records. Across six open-weight models and 40 mixed-critical-care summaries, GLM 5.2 multimodal revision improved temporal agreement without reducing event recovery and performed competitively with clinician annotations, while DeepSeek V3.2 did not benefit from multimodality. The pipeline achieves 43% increased event recovery with occurrence-level provenance.
- UIDs preserve event retention; source-row linkage supports temporal placement.
- GAVEL LLM judge findings mostly upheld by blinded human review.
- 43% increased event recovery with occurrence-level provenance.
- Multimodal revision helps GLM 5.2 but not DeepSeek V3.2.
From the original article
1 min read at arxiv.orgClinical timelines support treatment-window analysis and leakage-free modeling, but discharge summaries often obscure chronology and structured EHR tables describe only part of the patient course.
By Sayantan Kumar · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.