Spherical Mixture Integration for Latent Embedding Alignment across Multi-Source Feature Spaces

TL;DR

This paper introduces SMILE, a method for aligning and harmonizing multi-source clinical data embeddings to improve multi-institutional EHR analysis.

Contribution

It proposes a novel spherical mixture model with weak supervision for embedding alignment and provides theoretical guarantees for its effectiveness.

Findings

Enhanced alignment of heterogeneous EHR data sources.

Theoretical error bounds for latent embedding recovery.

Improved synonym clustering demonstrated in simulations and real data.

Abstract

Multi-institutional electronic health record (Multi-EHR) data have emerged as a powerful resource for developing predictive models to support clinical decisions and for generating reliable real-world evidence. By aggregating information from diverse patient populations and institutions, they enhance the robustness and generalizability of models and findings. However, analyzing multi-EHR remains challenging because disparate institutions rarely map all data elements to common ontology, and raw EHR codes are often overly granular and institution-specific, fragmenting representations of the same clinical concept. Hence, integrative analysis must overcome two key hurdles: harmonizing codes with the same clinical meaning (synonymy), and aligning institutional feature spaces. To address these challenges, we propose SMILE, a Spherical Mixture Integration for Latent Embedding alignment across multi-source feature spaces, where embeddings from heterogeneous sources serve as privacy-preserving summaries of clinical concepts and sparse auxiliary relationship pairs provide weak supervision on the latent geometry. Synonymy is modeled via a mixture of von Mises-Fisher distributions, yielding unified representations that consolidate semantically equivalent raw codes. We develop a composite quasi-likelihood estimation procedure and establish non-asymptotic error bounds for latent representations and mixture mean directions, together with consistent recovery of synonym clusters. The theory quantifies statistical gains from integrating multiple sources and auxiliary knowledge graph information. Simulations and a multi-institutional EHR application demonstrate improved alignment and synonym clustering.