AI 中文总结
本研究提出LUNG-KGMM知识引导多模态框架，整合多类数据与临床知识开展1-6年肺癌发病预测，经MIMIC及厦门队列验证，其性能优于现有方法且具备跨队列可迁移性。
AI 中文摘要
早期识别肺癌风险对于及时干预至关重要，但现有预测模型受限于仅依赖单一数据模态，且无法利用结构化临床知识。我们提出LUNG-KGMM，这是一种知识引导的多模态框架，整合纵向电子健康记录、放射学报告、胸部X光片表征以及指南衍生知识，用于1至6年的肺癌发病预测。为解决模态异质性和潜在数据泄露问题，我们开发了经泄露净化的报告处理流程，以及处理不完整随访的 horizon-masked 累积训练目标。我们进一步引入临床指南的知识图谱表征，将报告触发的发现-属性-行动关系编码为可审计的知识流。我们从公开可用的MIMIC数据库构建了多模态开发队列，并从厦门医疗大数据平台构建了真实世界验证队列。在MIMIC队列上开展的大量实验表明，LUNG-KGMM的性能优于现有最先进的方法，而在厦门队列上的验证进一步体现了其跨队列可迁移性及本地适配的必要性。MIMIC开发队列可公开获取；厦门队列受当地数据隐私法规监管。
英文摘要
Early identification of lung cancer risk is critical for timely intervention, yet existing prediction models are limited by their reliance on single data modalities and their inability to leverage structured clinical knowledge. We propose LUNG-KGMM, a knowledge-guided multimodal framework that integrates longitudinal electronic health records, radiology reports, chest radiograph representations, and guideline-derived knowledge for 1-to-6-year incident lung cancer prediction. To address modality heterogeneity and potential data leakage, we develop a leakage-sanitized report processing pipeline and a horizon-masked cumulative training objective that handles incomplete follow-up. We further introduce a knowledge-graph representation of clinical guidance that encodes report-triggered finding-attribute-action relations as an auditable knowledge stream. We build a multimodal development cohort from the publicly available MIMIC databases and construct a real-world validation cohort from the Xiamen Medical Big Data Platform. Extensive experiments on the MIMIC cohort demonstrate that LUNG-KGMM achieves superior performance over state-of-the-art methods, and validation on the Xiamen cohort further characterizes its cross-cohort portability and the need for local adaptation. The MIMIC development cohort is publicly accessible; the Xiamen cohort is governed by local data privacy regulations.
Comments22 pages, 4 figures, 7 tables, accepted by PRCV Oral
Journal refThe 9th Chinese Conference on Pattern Recognition and Computer Vision, PRCV2026
