Trust the Edge, Doubt the Arrow: Auditing Validation Signals for Text-Mined Clinical Causal

In a leakage-controlled causal QA benchmark, lift-only retrieval achieves 35.7% accuracy; conservative causal demotion achieves 37.2% while reducing evidence-unsupported answers from 17.3% to 6.1% at fixed retrieval recall. It comes from a paper posted to arXiv on 20 October 2026. Clinical causal retrieval-augmented generation systems increasingly use knowledge graphs (KGs) mined from notes, yet extracted assertions remain candidates that require audit for patient-level EHR support and direction. We construct a directed candidate graph from 328,839 MIMIC-IV discharge summaries using LLM extraction and UMLS normalization, and evaluate three signals against SemMedDB: within-admission co-occurrence lift, cross-admission diagnosis-coding temporal precedence, and literature corroboration. Lift filters unsupported co-mentions and provides useful EHR support, but not causal proof. Coding order is a weak direction signal: among the 686 candidates where it commits, it reaches 54.2% agreement with SemMedDB, below the extractor's 69.4% on the same subset. Literature corroboration supplies independent direction evidence but covers only 30.4% of candidate relations. A MIMIC-III replication yields the same pattern: extractor direction remains stable (70.5%), whereas coding-order direction is near chance (50.9%). Thus, text-mined clinical causal candidate KGs are best treated as EHR-supported but direction-uncertain. We release code, aggregate summaries, and scripts to regenerate restricted outputs.

Why it counts

In a leakage-controlled causal QA benchmark, lift-only retrieval achieves 35.7% accuracy; conservative causal demotion achieves 37.2% while reducing evidence-unsupported answers from 17.3% to 6.1% at fixed retrieval recall.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.