解决医疗报告生成中的隐私与时间演化难题，实现跨机构个性化长期病程建模。
Personalized Longitudinal Medical Report Generation via Temporally-Aware Federated Adaptation
- 基于时间感知联邦学习框架，融合患者人口统计信息与时间动态调整。
- 在J-MID和MIMIC-CXR上提升语言准确率、时间连贯性及跨站点泛化能力。
- 适合医疗AI研发、跨机构协作建模的隐私保护场景。
纵向医疗报告生成对临床至关重要，但受限于严格隐私约束及疾病进展的动态性。尽管联邦学习（FL）可在不共享数据的前提下协同训练，现有方法普遍忽略纵向动态，假设客户端分布静态，难以建模就诊间的时间变化或患者特异性差异，导致优化不稳定与报告质量下降。本文提出联邦时间适应（FTA）框架，显式考虑客户端数据的时间演化。在此基础上，设计FedTAR，融合人口统计驱动的个性化与时间感知全局聚合：从人口统计嵌入生成轻量级LoRA适配器，并通过元学习时间策略进行时间残差聚合，使用一阶MAML优化。在包含100万次检查的J-MID和MIMIC-CXR数据集上，实验显示语言准确性、时间一致性及跨站点泛化性能均持续提升，验证了FedTAR作为鲁棒且隐私保护的联邦纵向建模范式。
原文摘要 · Abstract (English)
Longitudinal medical report generation is clinically important yet remains challenging due to strict privacy constraints and the evolving nature of disease progression. Although federated learning (FL) enables collaborative training without data sharing, existing FL methods largely overlook longitudinal dynamics by assuming stationary client distributions, making them unable to model temporal shifts across visits or patient-specific heterogeneity-ultimately leading to unstable optimization and suboptimal report generation. We introduce Federated Temporal Adaptation (FTA), a federated setting that explicitly accounts for the temporal evolution of client data. Building upon this setting, we propose FedTAR, a framework that integrates demographic-driven personalization with time-aware global aggregation. FedTAR generates lightweight LoRA adapters from demographic embeddings and performs temporal residual aggregation, where updates from different visits are weighted by a meta-learned temporal policy optimized via first-order MAML. Experiments on J-MID (1M exams) and MIMIC-CXR demonstrate consistent improvements in linguistic accuracy, temporal coherence, and cross-site generalization, establishing FedTAR as a robust and privacy-preserving paradigm for federated longitudinal modeling.
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。