Beanz: An R package for Bayesian analysis of heterogeneous treatment effects with a graphical user interface

Research output: Contribution to journalArticle

Abstract

In patient-centered outcomes research, it is essential to assess the heterogeneity of treatment effects (HTE) when making health care decisions for an individual patient or a group of patients. Nevertheless, it remains challenging to evaluate HTE based on information collected from clinical studies that are often designed and conducted to evaluate the efficacy of a treatment for the overall population. The Bayesian framework offers a principled and flexible approach to estimate and compare treatment effects across subgroups of patients defined by their characteristics. In this paper, we describe the package beanz which facilitates the conduct of Bayesian analysis of HTE by allowing users to explore a wide range of Bayesian HTE analysis models and produce posterior inferences about HTE. The package beanz also provides a web-based graphical user interface (GUI) for users to conduct the Bayesian analysis of HTE in an interactive and user-friendly manner. With the GUI feature, package beanz can also be used by analysts not familiar with the R environment. We demonstrate package beanz using data from a randomized controlled trial on angiotensin converting enzyme inhibitor for treating congestive heart failure (N = 2569).

Original languageEnglish (US)
JournalJournal of Statistical Software
Volume85
DOIs
StatePublished - Jan 1 2018

Fingerprint

Graphical User Interface
Treatment Effects
Bayesian Analysis
Graphical user interfaces
Health care
Enzymes
Angiotensin
Congestive Heart Failure
Randomized Controlled Trial
Evaluate
Model Analysis
Heterogeneous treatment effects
Bayesian analysis
Graphical user interface
Treatment effects
Web-based
Healthcare
Inhibitor
Efficacy
Subgroup

Keywords

  • Bayesian analysis
  • GUI
  • HTE
  • Patient-centered outcomes research
  • R
  • Shiny
  • Stan
  • Subgroup analysis
  • Web-based Bayesian analysis

ASJC Scopus subject areas

  • Software
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

@article{1d3076db29a74b67a69561808715bf4f,
title = "Beanz: An R package for Bayesian analysis of heterogeneous treatment effects with a graphical user interface",
abstract = "In patient-centered outcomes research, it is essential to assess the heterogeneity of treatment effects (HTE) when making health care decisions for an individual patient or a group of patients. Nevertheless, it remains challenging to evaluate HTE based on information collected from clinical studies that are often designed and conducted to evaluate the efficacy of a treatment for the overall population. The Bayesian framework offers a principled and flexible approach to estimate and compare treatment effects across subgroups of patients defined by their characteristics. In this paper, we describe the package beanz which facilitates the conduct of Bayesian analysis of HTE by allowing users to explore a wide range of Bayesian HTE analysis models and produce posterior inferences about HTE. The package beanz also provides a web-based graphical user interface (GUI) for users to conduct the Bayesian analysis of HTE in an interactive and user-friendly manner. With the GUI feature, package beanz can also be used by analysts not familiar with the R environment. We demonstrate package beanz using data from a randomized controlled trial on angiotensin converting enzyme inhibitor for treating congestive heart failure (N = 2569).",
keywords = "Bayesian analysis, GUI, HTE, Patient-centered outcomes research, R, Shiny, Stan, Subgroup analysis, Web-based Bayesian analysis",
author = "Chenguang Wang and Louis, {Thomas A.} and Henderson, {Nicholas C.} and Weiss, {Carlos O.} and Ravi Varadhan",
year = "2018",
month = "1",
day = "1",
doi = "10.18637/jss.v085.i07",
language = "English (US)",
volume = "85",
journal = "Journal of Statistical Software",
issn = "1548-7660",
publisher = "University of California at Los Angeles",

}

TY - JOUR

T1 - Beanz

T2 - An R package for Bayesian analysis of heterogeneous treatment effects with a graphical user interface

AU - Wang, Chenguang

AU - Louis, Thomas A.

AU - Henderson, Nicholas C.

AU - Weiss, Carlos O.

AU - Varadhan, Ravi

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In patient-centered outcomes research, it is essential to assess the heterogeneity of treatment effects (HTE) when making health care decisions for an individual patient or a group of patients. Nevertheless, it remains challenging to evaluate HTE based on information collected from clinical studies that are often designed and conducted to evaluate the efficacy of a treatment for the overall population. The Bayesian framework offers a principled and flexible approach to estimate and compare treatment effects across subgroups of patients defined by their characteristics. In this paper, we describe the package beanz which facilitates the conduct of Bayesian analysis of HTE by allowing users to explore a wide range of Bayesian HTE analysis models and produce posterior inferences about HTE. The package beanz also provides a web-based graphical user interface (GUI) for users to conduct the Bayesian analysis of HTE in an interactive and user-friendly manner. With the GUI feature, package beanz can also be used by analysts not familiar with the R environment. We demonstrate package beanz using data from a randomized controlled trial on angiotensin converting enzyme inhibitor for treating congestive heart failure (N = 2569).

AB - In patient-centered outcomes research, it is essential to assess the heterogeneity of treatment effects (HTE) when making health care decisions for an individual patient or a group of patients. Nevertheless, it remains challenging to evaluate HTE based on information collected from clinical studies that are often designed and conducted to evaluate the efficacy of a treatment for the overall population. The Bayesian framework offers a principled and flexible approach to estimate and compare treatment effects across subgroups of patients defined by their characteristics. In this paper, we describe the package beanz which facilitates the conduct of Bayesian analysis of HTE by allowing users to explore a wide range of Bayesian HTE analysis models and produce posterior inferences about HTE. The package beanz also provides a web-based graphical user interface (GUI) for users to conduct the Bayesian analysis of HTE in an interactive and user-friendly manner. With the GUI feature, package beanz can also be used by analysts not familiar with the R environment. We demonstrate package beanz using data from a randomized controlled trial on angiotensin converting enzyme inhibitor for treating congestive heart failure (N = 2569).

KW - Bayesian analysis

KW - GUI

KW - HTE

KW - Patient-centered outcomes research

KW - R

KW - Shiny

KW - Stan

KW - Subgroup analysis

KW - Web-based Bayesian analysis

UR - http://www.scopus.com/inward/record.url?scp=85049527835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049527835&partnerID=8YFLogxK

U2 - 10.18637/jss.v085.i07

DO - 10.18637/jss.v085.i07

M3 - Article

AN - SCOPUS:85049527835

VL - 85

JO - Journal of Statistical Software

JF - Journal of Statistical Software

SN - 1548-7660

ER -