Representation Learning to Advance Multi-institutional Studies with Electronic Health Record Data

2025-02-12

AI Summary

Collaborative analysis of multi-institutional electronic health records (EHRs) is hindered by clinical concept encoding heterogeneity and stringent privacy constraints. Method: We propose GAME, a novel algorithm enabling cross-institutional, cross-lingual clinical concept alignment and representation learning without sharing patient-level data. GAME introduces a three-tier alignment framework integrating knowledge graph construction, large language model–based semantic mapping, and graph attention networks (GATs), jointly leveraging transfer learning and federated learning to produce generalizable embeddings. Results: Evaluated across seven healthcare institutions in bilingual (Chinese–English) settings, GAME significantly improves feature quality for disease modeling—e.g., heart failure and rheumatoid arthritis—and successfully supports multicenter studies on Alzheimer’s disease prognosis prediction and suicide risk assessment in psychiatric patients. By reconciling semantic heterogeneity while preserving data privacy, GAME establishes a new paradigm for privacy-preserving, cross-domain EHR analytics.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Game Theory and Economic Paradigms: Coordination and Collaboration

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

The adoption of EHRs has expanded opportunities to leverage data-driven algorithms in clinical care and research. A major bottleneck in effectively conducting multi-institutional EHR studies is the data heterogeneity across systems with numerous codes that either do not exist or represent different clinical concepts across institutions. The need for data privacy further limits the feasibility of including multi-institutional patient-level data required to study similarities and differences across patient subgroups. To address these challenges, we developed the GAME algorithm. Tested and validated across 7 institutions and 2 languages, GAME integrates data in several levels: (1) at the institutional level with knowledge graphs to establish relationships between codes and existing knowledge sources, providing the medical context for standard codes and their relationship to each other; (2) between institutions, leveraging language models to determine the relationships between institution-specific codes with established standard codes; and (3) quantifying the strength of the relationships between codes using a graph attention network. Jointly trained embeddings are created using transfer and federated learning to preserve data privacy. In this study, we demonstrate the applicability of GAME in selecting relevant features as inputs for AI-driven algorithms in a range of conditions, e.g., heart failure, rheumatoid arthritis. We then highlight the application of GAME harmonized multi-institutional EHR data in a study of Alzheimer's disease outcomes and suicide risk among patients with mental health disorders, without sharing patient-level data outside individual institutions.

Problem

• Addressing EHR data heterogeneity across institutions
• Ensuring data privacy in multi-institutional studies
• Developing GAME algorithm for harmonized EHR data analysis

Innovation

• GAME algorithm
• knowledge graphs
• federated learning