Saved in:
Bibliographic Details
Main Authors: Zhang, Yuming, Duan, Congyuan, Xia, Dong, Zhou, Doudou, Cai, Tianxi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.08637
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917475439869952
author Zhang, Yuming
Duan, Congyuan
Xia, Dong
Zhou, Doudou
Cai, Tianxi
author_facet Zhang, Yuming
Duan, Congyuan
Xia, Dong
Zhou, Doudou
Cai, Tianxi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_08637
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spherical Mixture Integration for Latent Embedding Alignment across Multi-Source Feature Spaces
Zhang, Yuming
Duan, Congyuan
Xia, Dong
Zhou, Doudou
Cai, Tianxi
Methodology
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.
title Spherical Mixture Integration for Latent Embedding Alignment across Multi-Source Feature Spaces
topic Methodology
url https://arxiv.org/abs/2605.08637