The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
The PheNorm R package provides an unsupervised phenotyping algorithm, for electronic health record (EHR) data. A human-annotated training set with gold-standard disease status labels is usually required to build an algorithm for phenotyping based on a set of predictive features. PheNorm, however, does not require expert-labeled samples for training.
The algorithm combines the most predictive variables, such as the counts of the main International Classification of Diseases (ICD) codes, with other EHR features. Those include for example health utilization and processed clinical note data. PheNorm aims to obtain a score for accurate risk prediction and disease classification. In particular, it normalizes the surrogate to resemble gaussian mixture and leverages the remaining features through random corruption denoising. PheNorm automatically generates phenotyping algorithms and demonstrates the capacity for EHR-driven annotations to scale to the next level phenotypic big data.
The data consists of ICD codes and additional features.
The output is:
the predicted probability of the risk of having the phenotype
the coefficient beta corresponding to all the features additional to the ICD codes.
The main steps of the algorithm are presented in the following flowchart:
The PheNorm package can be installed using the remotes package. The following code executed in R will get you started:
install.packages("remotes",repos = "http://cran.us.r-project.org")
remotes::install_github("celehs/PheNorm")
library(PheNorm)Yu S, Ma Y, Gronsbell J, Cai T, Ananthakrishnan AN, Gainer VS, Churchill SE, Szolovits P, Murphy SN, Kohane IS, Liao KP, Cai T. Enabling phenotypic big data with PheNorm. J Am Med Inform Assoc. 2018 Jan 1;25(1):54-60. doi: 10.1093/jamia/ocx111. PMID: 29126253; PMCID: PMC6251688. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6251688/
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.