2606.11675v1 Jun 10, 2026 cs.AI

Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning

Yuming Yang
Yuming Yang
Citations: 13
h-index: 2
Jiang Zhong
Jiang Zhong
Citations: 32
h-index: 3
Haoyang Zeng
Haoyang Zeng
Citations: 4
h-index: 1
Yuanxi Fu
Yuanxi Fu
Citations: 193
h-index: 9
Rongzhen Li
Rongzhen Li
Citations: 111
h-index: 5
Xiao Sun
Xiao Sun
Citations: 1
h-index: 1
Jingwang Huang
Jingwang Huang
Citations: 16
h-index: 2
Gujie Shao
Gujie Shao
Citations: 8
h-index: 1
Guohui Xiang
Guohui Xiang
Citations: 0
h-index: 0
Quanbo Lu
Quanbo Lu
Citations: 12
h-index: 2
Dongfan Ye
Dongfan Ye
Citations: 41
h-index: 2
Xuetao Chen
Xuetao Chen
Citations: 20
h-index: 1
Kaiwen Wei
Kaiwen Wei
Citations: 6
h-index: 2
Zhizhen Xu
Zhizhen Xu
Citations: 20
h-index: 3

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.

0 Citations
0 Influential
4.5 Altmetric
22.5 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!