Abstract
The increasing availability of electronic health record (EHR) systems has created enormous potential for translational research. However, it is difficult to know all the relevant codes related to a phenotype due to the large number of codes available. Traditional data mining approaches often require the use of patient-level data, which hinders the ability to share data across institutions. In this project, we demonstrate that multi-center large-scale code embeddings can be used to efficiently identify relevant features related to a disease of interest. We constructed large-scale code embeddings for a wide range of codified concepts from EHRs from two large medical centers. We developed knowledge extraction via sparse embedding regression (KESER) for feature selection and integrative network analysis. We evaluated the quality of the code embeddings and assessed the performance of KESER in feature selection for eight diseases. Besides, we developed an integrated clinical knowledge map combining embedding data from both institutions. The features selected by KESER were comprehensive compared to lists of codified data generated by domain experts. Features identified via KESER resulted in comparable performance to those built upon features selected manually or with patient-level data. The knowledge map created using an integrative analysis identified disease-disease and disease-drug pairs more accurately compared to those identified using single institution data. Analysis of code embeddings via KESER can effectively reveal clinical knowledge and infer relatedness among codified concepts. KESER bypasses the need for patient-level data in individual analyses providing a significant advance in enabling multi-center studies using EHR data.
| Original language | English |
|---|---|
| Article number | 151 |
| Journal | npj Digital Medicine |
| Volume | 4 |
| Issue number | 1 |
| DOIs | |
| State | Published - Dec 2021 |
Funding
We would like to acknowledge that this work would not have been possible without the collaboration between VA and the Department of Energy which provided the computing infrastructure necessary to develop and test these approaches at scale using nationwide VA EHR data. We would also like to thank Ms. Hope Cook, SQL Database Administrator, and Mr. Ian Goethert, Data Engineer, for their assistance with optimizing the computing environment required for this study. This manuscript has been in part co-authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725, and under a joint program with the Department of Veterans Affairs under the Million Veteran Project Computational Health Analytics for Medical Precision to Improve Outcomes Now. Part of this research is based on data from the Million Veteran Program, Office of Research and Development, Veterans Health Administration, and was supported by award #MVP000. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a nonexclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy. gov/downloads/doe-public-access-plan). This research used resources of the Knowledge Discovery Infrastructure at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725. The study protocol was approved by the MGB Human Research Committee (IRB00010756). No patient contact occurred in this study which relied on secondary use of data allowing for waiver of informed consent as detailed by 45 CFR 46.116. These activities were approved through the VA Central IRB. They were supported by Million Veteran Program, VA Central IRB 10-02, and approved under VA Central IRB protocol 18–38.