Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning
Quick Answer
This paper shows that Lung-R1, a pulmonary LLM guided by the LungKG knowledge graph, achieves state-of-the-art performance with an EMR Diagnosis score of 4.3583, outperforming previous models by 0.1476 points.
Quick Take
Lung-R1, a pulmonary LLM guided by the LungKG knowledge graph, achieves state-of-the-art performance with an EMR Diagnosis score of 4.3583, outperforming previous models by 0.1476 points. This model integrates patient-specific reasoning, addressing the Pulmonary Knowledge-to-Diagnosis Gap effectively. It demonstrates significant advancements in pulmonary disease diagnosis using electronic medical records.
Key Points
- LungKG features 59,038 nodes and 164,308 edges across 15 entity types.
- Lung-R1 was trained using KG-constrained reasoning-chain construction and reinforcement learning.
- The model achieved state-of-the-art results in Choice, Pulmonary-QA, and EMR Diagnosis.
- Lung-R1's EMR Diagnosis score surpasses the strongest non-Lung-R1 baseline.
- This research highlights the importance of structured knowledge in medical diagnostics.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 11675v1 Announce Type: new Abstract: Diagnosing pulmonary diseases requires integrating heterogeneous evidence amid phenotypic variability and cross-disease overlap. Although large language models (LLMs) have shown progress on pulmonary knowledge question answering (QA) and information-processing tasks, reliable pulmonary diagnosis requires patient-specific, relation-aware reasoning over electronic medical record (EMR) evidence rather than isolated knowledge recall.
We define this gap between pulmonary knowledge and case-level diagnostic reasoning as the Pulmonary Knowledge-to-Diagnosis Gap. To address it, we introduce LungKG, the first structured pulmonary knowledge graph for diagnostic knowledge organization and record-grounded reasoning. LungKG contains 59,038 nodes and 164,308 edges across 15 entity types and 112 relation types, serving as both a reusable pulmonary knowledge resource and the foundation for LungKG-guided model adaptation.
Built on LungKG, we propose Lung-R1, a LungKG-guided pulmonary LLM trained through KG-constrained reasoning-chain construction and KG-guided reinforcement learning. In a 20-system evaluation, Lung-R1-14B achieves state-of-the-art performance across Choice, Pulmonary-QA, and EMR Diagnosis, reaching an EMR Diagnosis score of 4. 3583 and surpassing the strongest non-Lung-R1 baseline by 0. 1476 points. These results demonstrate the value of LungKG-guided training for EMR-based pulmonary diagnosis.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Arbor introduces a multi-agent framework utilizing structured tree search for optimizing LLM inference, achieving up to 193% throughput-latency improvement compared to vendor-optimized systems. It employs an Orchestrator and Critic agent for stability and coordination, demonstrating hardware-agnostic performance with minimal variance.