An R package for clustering cohort patients by medical history or creating data-driven medical topics (clusters of concept_ids corresponding to the same medical topic).
There is also a javascript D3 interactive visulisation available for viewing the results.
patientCluster is an R package, with some functions implemented using h2o (http://h2o-release.s3.amazonaws.com/h2o/rel-lambert/5/docs-website/Ruser/Rinstall.html).
Requires R (version ? or higher). Installation on Windows requires RTools. Libraries used in patientCluster require Java.
```r install.packages("devtools") library(devtools) install_github("ohdsi/SqlRender") install_github("ohdsi/DatabaseConnector") install_github("ohdsi/patientCluster")
library("patientCluster") library("h2o") h2o.init(nthreads = -1, max_mem_size = '16g') ```
patientCluster is licensed under Apache License 2.0
patientCluster is being developed in R Studio.
Beta
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.