Personalized Longitudinal Medical Report Generation via Temporally-Aware Federated Adaptation

TL;DR

This paper introduces FedTAR, a federated learning framework that models temporal disease progression for personalized medical report generation, improving accuracy and coherence while preserving patient privacy.

Contribution

It proposes FedTAR, a novel federated approach that incorporates temporal dynamics and demographic personalization for longitudinal medical data modeling.

Findings

Improves linguistic accuracy of reports.

Enhances temporal coherence across visits.

Demonstrates strong generalization across sites.

Abstract

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.