Repository files navigation

The kesernetwork builds a shiny app to visualize the knowledge networksfor the code concepts. Using co-occurrence matrices of EHR codes fromVeterans Affairs (VA) and Massachusetts General Brigham (MGB), theknowledge extraction via sparse embedding regression (KESER) algorithmwas used to construct knowledge networks for the code concepts.

Install the released version of kesernetwork from CRAN:

install.packages("kesernetwork")

Or install the development version from GitHub with:

install.packages("remotes")remotes::install_github("celehs/kesernetwork")

This is a basic example which shows you how to run thekesernetworkapp. Remember you need to get access to the data and save it to yourlocal computer. In order to guarantee some dependencies are loaded, youmust uselibrary(kesernetwork) beforehand, instead of directly runningkesernetwork::run_app().

library(kesernetwork)run_app(Rdata_path="path/to/kesernetwork.RData")

See thegetting startedguide tolearn how to use kesernetwork.

• Hong, C., Rush, E., Liu, M. et al. Clinical knowledge extraction viasparse embedding regression (KESER) with multi-center large scaleelectronic health record data. npj Digit. Med. 4, 151 (2021).https://doi.org/10.1038/s41746-021-00519-z