Federated Learning for Heterogeneous Electronic Health Record Systems with Cost Effective Participant Selection

TL;DR

This paper introduces EHRFL, a federated learning framework that enhances compatibility across heterogeneous EHR systems and reduces costs through a privacy-preserving participant selection strategy, enabling efficient, institution-specific clinical prediction models.

Contribution

The paper presents a novel federated learning approach combining text-based EHR modeling and a differentially private participant selection method for cost-effective, compatible, and privacy-preserving healthcare modeling.

Findings

Effective cross-institution compatibility without costly standardization

Cost reduction in federated learning via participant selection

Maintained model performance with fewer participants

Abstract

The increasing volume of electronic health records (EHRs) presents the opportunity to improve the accuracy and robustness of models in clinical prediction tasks. Unlike traditional centralized approaches, federated learning enables training on data from multiple institutions while preserving patient privacy and complying with regulatory constraints. In practice, healthcare institutions (i.e., hosts) often need to build predictive models tailored to their specific needs (e.g., creatinine-level prediction, N-day readmission prediction) using federated learning. When building a federated learning model for a single healthcare institution, two key challenges arise: (1) ensuring compatibility across heterogeneous EHR systems, and (2) managing federated learning costs within budget constraints. Specifically, heterogeneity in EHR systems across institutions hinders compatible modeling, while the computational costs of federated learning can exceed practical budget limits for healthcare institutions. To address these challenges, we propose EHRFL, a federated learning framework designed for building a cost-effective, host-specific predictive model using patient EHR data. EHRFL consists of two components: (1) text-based EHR modeling, which facilitates cross-institution compatibility without costly data standardization, and (2) a participant selection strategy based on averaged patient embedding similarity to reduce the number of participants without degrading performance. Our participant selection strategy sharing averaged patient embeddings is differentially private, ensuring patient privacy. Experiments on multiple open-source EHR datasets demonstrate the effectiveness of both components. With our framework, healthcare institutions can build institution-specific predictive models under budgetary constraints with reduced costs and time.