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.
Highlights
The adoption of electronic health record (EHR) systems has simultaneously changed clinical practice and expanded the breadth of biomedical research
The knowledge extraction via sparse embedding regression (KESER) approach enables the assessment of conditional dependency between EHR features by performing sparse regression of embedding vectors without requiring additional patient-level data
We demonstrate the advantage of integrative analyses across sites in detecting known associations
Summary
The adoption of electronic health record (EHR) systems has simultaneously changed clinical practice and expanded the breadth of biomedical research. EHR clinical data typically includes diagnostic billing codes, laboratory orders and results, procedure codes, and medication prescriptions. These comprehensive longitudinal data allow for studies to examine a broad range of hypotheses. This wealth of data raises challenges in selecting and creating EHR features among thousands of options relevant to the study or condition of interest. Most current studies manually select individual EHR features and map specific EHR codes to represent each feature, requiring input from clinical and informatics experts. In addition to being susceptible to subjective bias, this manual, time-consuming process cannot be scaled for projects requiring multiple phenotypes
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
