This is automation package for generating the Line of Therapy table using the Line of Therapy Algorithm, as described in the paper "Temporal phenotyping by mining healthcare data to derive lines of therapy for cancer" accepted in the Journal of Biomedical Informatics. https://www.ncbi.nlm.nih.gov/pubmed/31689549
The purpose of having line of therapy rules is to determine the start date, end date, line number and treatment regimen of a patient's journey toward treating cancer. Typically, this information is not available in an EHR or claims database, but is rather derived from medication history information via business rules. EHR databases most commonly have rules deriving line of therapy due to their availability of medical chart reviews. Claims do not have this information, and therefore special rules and considerations need to be applied when deriving line of therapy information.
Merck has internally developed business rules to take patient drug claims administrations and convert them into line of therapy treatment patterns for the purpose of performing downstream analysis such as oncology time on treatment analysis. At this moment the Line of Therapy Algorithm is supported for NSCLC, Melanoma and HNSCC indications Oncology indications.
As of now, the R codes for LoT algorithm has already been developed. These consists of primarily four R script files as well as six reference CSV files. The four script files either run the main execution of the line of therapy calculation, or contain supporting functions that the main execution calls on. https://github.com/Merck/Line-of-Therapy-Algorithm.git
We developed the R package version of the LoT algorithm for :
Simple workflow and execution
Easy installation and setup
User guide and documentation
Shareability
Version control
You can install the current version of rwLoT package from source file or clone from bitbucket source folder.
install.packages(rwLoT)
install.packages(path_to_file, repos = NULL, type="source")
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.