Multiview Incomplete Knowledge Graph Integration with application to cross-institutional EHR data harmonization

Doudou Zhou, Ziming Gan, Xu Shi, Alina Patwari, Everett Rush, Clara Lea Bonzel, Vidul A. Panickan, Chuan Hong, Yuk Lam Ho, Tianrun Cai, Lauren Costa, Xiaoou Li, Victor M. Castro, Shawn N. Murphy, Gabriel Brat, Griffin Weber, Paul Avillach, J. Michael Gaziano, Kelly Cho, Katherine P. LiaoJunwei Lu, Tianxi Cai

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

Objective: The growing availability of electronic health records (EHR) data opens opportunities for integrative analysis of multi-institutional EHR to produce generalizable knowledge. A key barrier to such integrative analyses is the lack of semantic interoperability across different institutions due to coding differences. We propose a Multiview Incomplete Knowledge Graph Integration (MIKGI) algorithm to integrate information from multiple sources with partially overlapping EHR concept codes to enable translations between healthcare systems. Methods: The MIKGI algorithm combines knowledge graph information from (i) embeddings trained from the co-occurrence patterns of medical codes within each EHR system and (ii) semantic embeddings of the textual strings of all medical codes obtained from the Self-Aligning Pretrained BERT (SAPBERT) algorithm. Due to the heterogeneity in the coding across healthcare systems, each EHR source provides partial coverage of the available codes. MIKGI synthesizes the incomplete knowledge graphs derived from these multi-source embeddings by minimizing a spherical loss function that combines the pairwise directional similarities of embeddings computed from all available sources. MIKGI outputs harmonized semantic embedding vectors for all EHR codes, which improves the quality of the embeddings and enables direct assessment of both similarity and relatedness between any pair of codes from multiple healthcare systems. Results: With EHR co-occurrence data from Veteran Affairs (VA) healthcare and Mass General Brigham (MGB), MIKGI algorithm produces high quality embeddings for a variety of downstream tasks including detecting known similar or related entity pairs and mapping VA local codes to the relevant EHR codes used at MGB. Based on the cosine similarity of the MIKGI trained embeddings, the AUC was 0.918 for detecting similar entity pairs and 0.809 for detecting related pairs. For cross-institutional medical code mapping, the top 1 and top 5 accuracy were 91.0% and 97.5% when mapping medication codes at VA to RxNorm medication codes at MGB; 59.1% and 75.8% when mapping VA local laboratory codes to LOINC hierarchy. When trained with 500 labels, the lab code mapping attained top 1 and 5 accuracy at 77.7% and 87.9%. MIKGI also attained best performance in selecting VA local lab codes for desired laboratory tests and COVID-19 related features for COVID EHR studies. Compared to existing methods, MIKGI attained the most robust performance with accuracy the highest or near the highest across all tasks. Conclusions: The proposed MIKGI algorithm can effectively integrate incomplete summary data from biomedical text and EHR data to generate harmonized embeddings for EHR codes for knowledge graph modeling and cross-institutional translation of EHR codes.

Original languageEnglish (US)
Article number104147
JournalJournal of Biomedical Informatics
Volume133
DOIs
StatePublished - Sep 2022

Bibliographical note

Funding Information:
This project was supported by the NIH 1OT2OD032581 grant (Biomedical Informatics and AI/ML Pipelines to Advance Health Equity and Research Diversity - Infrastructure core) and the Million Veteran Program, Department of Veteran Affairs, Office of Research and Development, Veterans Health Administration, supported by award (#MVP000). This research used resources of the Knowledge Discovery Infrastructure at Oak Ridge National Laboratory, which is supported by the Office of Science of the US Department of Energy under Contract No. DE-AC05-00OR22725. This publication does not represent the views of the Department of Veterans Affairs or the U.S. government.

Funding Information:
This project was supported by the NIH 1OT2OD032581 grant (Biomedical Informatics and AI/ML Pipelines to Advance Health Equity and Research Diversity - Infrastructure core) and the Million Veteran Program, Department of Veteran Affairs, Office of Research and Development, Veterans Health Administration, supported by award (#MVP000). This research used resources of the Knowledge Discovery Infrastructure at Oak Ridge National Laboratory, which is supported by the Office of Science of the US Department of Energy under Contract No. DE-AC05-00OR22725 . This publication does not represent the views of the Department of Veterans Affairs or the U.S. government.

Publisher Copyright:
© 2022

Keywords

  • Code mapping
  • Knowledge graph
  • PMI matrix
  • Transfer learning
  • Word embedding

Fingerprint

Dive into the research topics of 'Multiview Incomplete Knowledge Graph Integration with application to cross-institutional EHR data harmonization'. Together they form a unique fingerprint.

Cite this