R IN HEALTH DECISION SCIENCES: A SCOPING REVIEW
Purpose: R is an open-source software that has gained increased popularity among statisticians and recently among health decision scientists. R's popularity stems from a large number of user-written functions that support a wide array of analyses and data visualization. The purpose of this paper is to provide an overview of existing R functionalities as they apply to various stages of decision analysis, including model development, parameter estimation and output analyses.
Methods: To determine R's use in health decision science's literature, we sued Google Scholar to search within the full text of articles describing decision models and cost-effectiveness analyses that used a number of software packages, including excel, SAS, Stata, TreeAge and R. Next, we reviewed nearly sixty R-packages relevant to various stages of decision analysis. The packages were divided into three major categories: (1) Model design and development, (2) input parameter estimation and calibration, and (3) Analysis of model outputs and result visualization.
Results: The figure shows the increased popularity of R in health decision sciences. R's diffusion into the health decision sciences literature was measured through the proportion of studies per year that were conducted using R versus any other software. R is increasing in popularity, with the proportion of studies using R increasing nearly by nearly 50% over the past 5 years. In fact, R was the only software that showed a consistent increase in use over time. In contrast, the other software showed either negative or semi-stationary trends. In addition, Many of the R packages can be applied to decision analysis with minimal or no modifications.
Conclusion: R has rapidly become one of the most widely used tools in statistical analyses. Thus, the purpose of this overview is to provide a baseline reference point for users interested in navigating the large number of R packages relevant to decision analyses. In subsequent tutorials, we will detail how to conduct specific tasks that are commonly used in decision analysis and simulation modeling, for example model building, calibration and value of information analysis among others.