用知识图谱指导生成罕见病患者病历，既真实又保护隐私。
RareGraph-Synth: Knowledge-Guided Diffusion Models for Generating Privacy-Preserving Synthetic Patient Trajectories in Ultra-Rare Diseases
- 将5个医学知识库融合成800万条关系的异质图，指导扩散模型生成过程。
- 生成数据与真实数据相似度提升40%，对隐私攻击的防御能力显著增强。
- 适合罕见病研究、医疗数据共享等需要高保真且高隐私保护的场景。
我们提出RareGraph-Synth，一种基于知识引导的连续时间扩散框架，用于生成超罕见疾病的真实但隐私保护的电子健康记录（EHR）轨迹。该方法整合了五个公开资源：Orphanet/Orphadata、人类表型本体（HPO）、GARD罕见病知识图谱（KG）、PrimeKG和美国食品药品监督管理局不良事件报告系统（FAERS），构建了一个包含约800万条类型化边的异质知识图谱。从该图谱中提取的元路径得分用于调节前向随机微分方程中的每标记噪声调度，引导生成过程实现生物上合理的实验室检查-药物-不良事件共现，同时保持基于分数的扩散模型稳定性。反向去噪器生成带有时间戳的实验室代码、药物代码和不良事件标志三元组序列，不含任何受保护的健康信息。在模拟的超罕见病队列上，RareGraph-Synth相较于无引导扩散基线降低类别最大均值差异40%，相对于GAN模型降低超过60%，且不损害下游预测性能。使用DOMIAS攻击者进行黑盒成员推断评估，获得的AUROC约为0.53，低于0.55的安全释放阈值，显著优于非知识图谱基线的约0.61±0.03，表明其具备强抗重识别能力。结果表明，将生物医学知识图谱直接嵌入扩散噪声调度中，可同时提升生成质量与隐私保护水平，为罕见病研究的数据安全共享提供新途径。
原文摘要 · Abstract (English)
We propose RareGraph-Synth, a knowledge-guided, continuous-time diffusion framework that generates realistic yet privacy-preserving synthetic electronic-health-record (EHR) trajectories for ultra-rare diseases. RareGraph-Synth unifies five public resources: Orphanet/Orphadata, the Human Phenotype Ontology (HPO), the GARD rare-disease KG, PrimeKG, and the FDA Adverse Event Reporting System (FAERS) into a heterogeneous knowledge graph comprising approximately 8 M typed edges. Meta-path scores extracted from this 8-million-edge KG modulate the per-token noise schedule in the forward stochastic differential equation, steering generation toward biologically plausible lab-medication-adverse-event co-occurrences while retaining score-based diffusion model stability. The reverse denoiser then produces timestamped sequences of lab-code, medication-code, and adverse-event-flag triples that contain no protected health information. On simulated ultra-rare-disease cohorts, RareGraph-Synth lowers categorical Maximum Mean Discrepancy by 40 percent relative to an unguided diffusion baseline and by greater than 60 percent versus GAN counterparts, without sacrificing downstream predictive utility. A black-box membership-inference evaluation using the DOMIAS attacker yields AUROC approximately 0.53, well below the 0.55 safe-release threshold and substantially better than the approximately 0.61 plus or minus 0.03 observed for non-KG baselines, demonstrating strong resistance to re-identification. These results suggest that integrating biomedical knowledge graphs directly into diffusion noise schedules can simultaneously enhance fidelity and privacy, enabling safer data sharing for rare-disease research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。