Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence

Key points

• Post-discharge risk prediction from electronic health records (EHRs) is difficult because many dependencies that link discharge-time observations to downstream complications, such as comorbidity cascades and drug-disease interactions, are absent from the record.1
• External medical knowledge graphs (KGs) can supply these missing dependencies, but tracing them demands three properties: KG exploration must remain cost-bounded, retrieved evidence must be differentiated by source quality, and the resulting rationale must be citable for retrospective review.1
• Large language models (LLMs) can plan and verify over structured evidence, making them natural candidates for KG reasoning, but existing LLM-based methods do not satisfy these three properties jointly.1
• Across 8 diseases and 3 prediction horizons on MIMIC-III and MIMIC-IV, BAR improves AUPRC by 3.4 points over the strongest baseline, raises citation precision from 59.8% to 77.9%, and consumes only 62-65% of the budget cap.1

Sources (1)

• [1]Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 04:36 AM

  In this paper, we propose BAR, a Budget-Aware LLM Reasoning framework over medical KGs with three contributions.

  Post-discharge risk prediction from electronic health records (EHRs) is difficult because many dependencies that link discharge-time observations to downstream complications, such as comorbidity cascades and drug-disease interactions, are absent from the record.

Extractive summary: sentences quoted from the sources.