Three handy tips and a practical guide to improve your propensity score models

Sytske Anne Bergstra, Alexandre Sepriano, Sofia Ramiro, Robert Landewé

Research output: Contribution to journalReview article

1 Downloads (Pure)

Abstract

Real-world data are increasingly available to investigate real-world' safety and efficacy. However, since treatment in observational studies is not randomly allocated, confounding by indication may occur, in which differences in patient characteristics may influence both treatment choices and treatment responses. A popular method to adjust for this type of bias is the use of propensity scores (PS). The PS is a score between 0 and 1 that reflects the likelihood per patient of receiving one of the treatment categories of interest conditional on a set of variables. At least in theory, in patients with similar PS, the treatment prescribed will be independent of these variables (pseudorandomisation). But researchers using PS sometimes fail to recognise important methodological flaws which can lead to spurious conclusions. These include perfect prediction of treatment allocation, untied observations and lack of generalisability due to oversimplification of complex clinical scenarios. In this viewpoint we will discuss the most commonly encountered flaws and provide a stepwise description on the estimation and use of PS, such that in future publications these flaws can be avoided.

Original languageEnglish
Article numbere000953
JournalRMD Open
Volume5
Issue number1
DOIs
Publication statusPublished - 1 Apr 2019

Fingerprint

Propensity Score
Therapeutics
Observational Studies
Research Personnel
Safety

Keywords

  • bias
  • observational studies
  • propensity scores
  • treatment effects

Cite this

@article{5257812851bc4cabb30e75d63140b91b,
title = "Three handy tips and a practical guide to improve your propensity score models",
abstract = "Real-world data are increasingly available to investigate real-world' safety and efficacy. However, since treatment in observational studies is not randomly allocated, confounding by indication may occur, in which differences in patient characteristics may influence both treatment choices and treatment responses. A popular method to adjust for this type of bias is the use of propensity scores (PS). The PS is a score between 0 and 1 that reflects the likelihood per patient of receiving one of the treatment categories of interest conditional on a set of variables. At least in theory, in patients with similar PS, the treatment prescribed will be independent of these variables (pseudorandomisation). But researchers using PS sometimes fail to recognise important methodological flaws which can lead to spurious conclusions. These include perfect prediction of treatment allocation, untied observations and lack of generalisability due to oversimplification of complex clinical scenarios. In this viewpoint we will discuss the most commonly encountered flaws and provide a stepwise description on the estimation and use of PS, such that in future publications these flaws can be avoided.",
keywords = "bias, observational studies, propensity scores, treatment effects",
author = "Bergstra, {Sytske Anne} and Alexandre Sepriano and Sofia Ramiro and Robert Landew{\'e}",
year = "2019",
month = "4",
day = "1",
doi = "10.1136/rmdopen-2019-000953",
language = "English",
volume = "5",
journal = "RMD Open",
issn = "2044-6055",
publisher = "BMJ Publishing Group: BMJ",
number = "1",

}

Three handy tips and a practical guide to improve your propensity score models. / Bergstra, Sytske Anne; Sepriano, Alexandre; Ramiro, Sofia; Landewé, Robert.

In: RMD Open, Vol. 5, No. 1, e000953, 01.04.2019.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Three handy tips and a practical guide to improve your propensity score models

AU - Bergstra, Sytske Anne

AU - Sepriano, Alexandre

AU - Ramiro, Sofia

AU - Landewé, Robert

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Real-world data are increasingly available to investigate real-world' safety and efficacy. However, since treatment in observational studies is not randomly allocated, confounding by indication may occur, in which differences in patient characteristics may influence both treatment choices and treatment responses. A popular method to adjust for this type of bias is the use of propensity scores (PS). The PS is a score between 0 and 1 that reflects the likelihood per patient of receiving one of the treatment categories of interest conditional on a set of variables. At least in theory, in patients with similar PS, the treatment prescribed will be independent of these variables (pseudorandomisation). But researchers using PS sometimes fail to recognise important methodological flaws which can lead to spurious conclusions. These include perfect prediction of treatment allocation, untied observations and lack of generalisability due to oversimplification of complex clinical scenarios. In this viewpoint we will discuss the most commonly encountered flaws and provide a stepwise description on the estimation and use of PS, such that in future publications these flaws can be avoided.

AB - Real-world data are increasingly available to investigate real-world' safety and efficacy. However, since treatment in observational studies is not randomly allocated, confounding by indication may occur, in which differences in patient characteristics may influence both treatment choices and treatment responses. A popular method to adjust for this type of bias is the use of propensity scores (PS). The PS is a score between 0 and 1 that reflects the likelihood per patient of receiving one of the treatment categories of interest conditional on a set of variables. At least in theory, in patients with similar PS, the treatment prescribed will be independent of these variables (pseudorandomisation). But researchers using PS sometimes fail to recognise important methodological flaws which can lead to spurious conclusions. These include perfect prediction of treatment allocation, untied observations and lack of generalisability due to oversimplification of complex clinical scenarios. In this viewpoint we will discuss the most commonly encountered flaws and provide a stepwise description on the estimation and use of PS, such that in future publications these flaws can be avoided.

KW - bias

KW - observational studies

KW - propensity scores

KW - treatment effects

UR - http://www.scopus.com/inward/record.url?scp=85065299275&partnerID=8YFLogxK

U2 - 10.1136/rmdopen-2019-000953

DO - 10.1136/rmdopen-2019-000953

M3 - Review article

VL - 5

JO - RMD Open

JF - RMD Open

SN - 2044-6055

IS - 1

M1 - e000953

ER -