Clinical knowledge extraction via sparse embedding regression (KESER) with multi-center large scale electronic health record data.

Autor:	Hong C; Harvard Medical School, Boston, MA, USA.; VA Boston Healthcare System, Boston, MA, USA., Rush E; Department of Energy, Oak Ridge National Lab, Oak Ridge, TN, USA., Liu M; Harvard T.H. Chan School of Public Health, Boston, MA, USA., Zhou D; University of California, Davis, CA, USA., Sun J; University of Illinois at Chicago, Chicago, IL, USA., Sonabend A; Harvard T.H. Chan School of Public Health, Boston, MA, USA., Castro VM; Mass General Brigham, Boston, MA, USA., Schubert P; VA Boston Healthcare System, Boston, MA, USA., Panickan VA; Harvard Medical School, Boston, MA, USA., Cai T; VA Boston Healthcare System, Boston, MA, USA.; Mass General Brigham, Boston, MA, USA., Costa L; VA Boston Healthcare System, Boston, MA, USA., He Z; Mass General Brigham, Boston, MA, USA., Link N; VA Boston Healthcare System, Boston, MA, USA., Hauser R; West Haven VA Medical Center, West Haven, CT, USA., Gaziano JM; Harvard Medical School, Boston, MA, USA.; VA Boston Healthcare System, Boston, MA, USA.; Brigham and Women's Hospital, Boston, MA, USA., Murphy SN; Mass General Brigham, Boston, MA, USA., Ostrouchov G; Department of Energy, Oak Ridge National Lab, Oak Ridge, TN, USA., Ho YL; VA Boston Healthcare System, Boston, MA, USA., Begoli E; Department of Energy, Oak Ridge National Lab, Oak Ridge, TN, USA., Lu J; VA Boston Healthcare System, Boston, MA, USA.; Harvard T.H. Chan School of Public Health, Boston, MA, USA., Cho K; Harvard Medical School, Boston, MA, USA.; VA Boston Healthcare System, Boston, MA, USA.; Brigham and Women's Hospital, Boston, MA, USA., Liao KP; Harvard Medical School, Boston, MA, USA.; VA Boston Healthcare System, Boston, MA, USA.; Brigham and Women's Hospital, Boston, MA, USA., Cai T; Harvard Medical School, Boston, MA, USA. tcai@hsph.harvard.edu.; VA Boston Healthcare System, Boston, MA, USA. tcai@hsph.harvard.edu.; Harvard T.H. Chan School of Public Health, Boston, MA, USA. tcai@hsph.harvard.edu.
Jazyk:	angličtina
Zdroj:	NPJ digital medicine [NPJ Digit Med] 2021 Oct 27; Vol. 4 (1), pp. 151. Date of Electronic Publication: 2021 Oct 27.
DOI:	10.1038/s41746-021-00519-z
Abstrakt:	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. (© 2021. The Author(s).)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu