In UMCSTaR/medicareAnalytics: Analytic Tools for Medicare Data Research Projects

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

medicareAnalytics

The goal of medicareAnalytics is to simplify the data processing and modeling for medicare research projects. This project is based on the medicare analytic file data structures, and used a lot variable names specifically only for the medicare analytic file.

Since most of the medicare projects are using the same cohort filters and models, this package can help the analysts and reseach fellows to conduct analyses.

Installation

You can install the development version of medicareAnalytics from GitHub with:

# install.packages("devtools")
devtools::install_github("UMCSTaR/medicareAnalytics")

Example

Create multi-procedure frequency table

library(medicareAnalytics)
library(tidyverse)
## basic example code

# load medicare dt
medicare = data.table::fread("/Volumes/George_Surgeon_Projects/standardized_medicare_data_using_R/analysis_ready_data/ecs_primary_surgeon_medicare2018.csv", nrows = 5000)


multiple_procedures_table(medicare, project_sepcific_procedure_tax = "e_proc_grp_lbl")

Only keep US medschool graduates

# load medicare dt
medicare = data.table::fread("/Volumes/George_Surgeon_Projects/standardized_medicare_data_using_R/analysis_ready_data/ecs_primary_surgeon_medicare2018.csv", nrows = 5000)


remove_nonUS_trained(medicare) %>% 
  select(-contains("id"), -contains("dt")) %>%  # remove sensitive data
  head()

apply all filters

medicare %>% 
  apply_all_filters(add_variables = "val_yr_practice") %>%
  select(-contains("id"), -contains("dt")) %>%  # remove sensitive data
  glimpse()