Issues relating to study design and risk of bias when including non-randomized studies in systematic reviews on the effects of interventions

J P T Higgins, Craig Robert Ramsay, B C Reeves, J J Deeks, B Shea, J C Valentine, P Tugwell, G Wells

Research output: Contribution to journalArticle

Abstract

Non-randomized studies may provide valuable evidence on the effects of interventions. They are the main
source of evidence on the intended effects of some types of interventions and often provide the only
evidence about the effects of interventions on long-term outcomes, rare events or adverse effects.
Therefore, systematic reviews on the effects of interventions may include various types of non-randomized
studies. In this second paper in a series, we address how review authors might articulate the particular
non-randomized study designs they will include and how they might evaluate, in general terms, the extent
to which a particular non-randomized study is at risk of important biases. We offer guidance for describing
and classifying different non-randomized designs based on speci¿c features of the studies in place of using
non-informative study design labels. We also suggest criteria to consider when deciding whether to
include non-randomized studies. We conclude that a taxonomy of study designs based on study design
features is needed. Review authors need new tools speci¿cally to assess the risk of bias for some
non-randomized designs that involve a different inferential logic compared with parallel group trials.
Copyright © 2012 John Wiley & Sons, Ltd.
Original languageEnglish
Pages (from-to)12-25
Number of pages14
JournalResearch Synthesis Methods
Volume4
Issue number1
Early online date25 Sep 2012
DOIs
Publication statusPublished - Mar 2013

Fingerprint

trend
General Terms
taxonomy
evidence
event
Group

Keywords

  • non randomized studies
  • study design
  • bias
  • systematic reviews

Cite this

Issues relating to study design and risk of bias when including non-randomized studies in systematic reviews on the effects of interventions. / Higgins, J P T; Ramsay, Craig Robert; Reeves, B C; Deeks, J J ; Shea, B; Valentine, J C; Tugwell, P; Wells, G.

In: Research Synthesis Methods, Vol. 4, No. 1, 03.2013, p. 12-25.

Research output: Contribution to journalArticle

Higgins, J P T ; Ramsay, Craig Robert ; Reeves, B C ; Deeks, J J ; Shea, B ; Valentine, J C ; Tugwell, P ; Wells, G. / Issues relating to study design and risk of bias when including non-randomized studies in systematic reviews on the effects of interventions. In: Research Synthesis Methods. 2013 ; Vol. 4, No. 1. pp. 12-25.
@article{3ad721b26d8b45728c391a570e3aa2e1,
title = "Issues relating to study design and risk of bias when including non-randomized studies in systematic reviews on the effects of interventions",
abstract = "Non-randomized studies may provide valuable evidence on the effects of interventions. They are the mainsource of evidence on the intended effects of some types of interventions and often provide the onlyevidence about the effects of interventions on long-term outcomes, rare events or adverse effects.Therefore, systematic reviews on the effects of interventions may include various types of non-randomizedstudies. In this second paper in a series, we address how review authors might articulate the particularnon-randomized study designs they will include and how they might evaluate, in general terms, the extentto which a particular non-randomized study is at risk of important biases. We offer guidance for describingand classifying different non-randomized designs based on speci¿c features of the studies in place of usingnon-informative study design labels. We also suggest criteria to consider when deciding whether toinclude non-randomized studies. We conclude that a taxonomy of study designs based on study designfeatures is needed. Review authors need new tools speci¿cally to assess the risk of bias for somenon-randomized designs that involve a different inferential logic compared with parallel group trials.Copyright {\circledC} 2012 John Wiley & Sons, Ltd.",
keywords = "non randomized studies, study design, bias, systematic reviews",
author = "Higgins, {J P T} and Ramsay, {Craig Robert} and Reeves, {B C} and Deeks, {J J} and B Shea and Valentine, {J C} and P Tugwell and G Wells",
year = "2013",
month = "3",
doi = "10.1002/jrsm.1056",
language = "English",
volume = "4",
pages = "12--25",
journal = "Research Synthesis Methods",
issn = "1759-2887",
publisher = "John Wiley and Sons Ltd",
number = "1",

}

TY - JOUR

T1 - Issues relating to study design and risk of bias when including non-randomized studies in systematic reviews on the effects of interventions

AU - Higgins, J P T

AU - Ramsay, Craig Robert

AU - Reeves, B C

AU - Deeks, J J

AU - Shea, B

AU - Valentine, J C

AU - Tugwell, P

AU - Wells, G

PY - 2013/3

Y1 - 2013/3

N2 - Non-randomized studies may provide valuable evidence on the effects of interventions. They are the mainsource of evidence on the intended effects of some types of interventions and often provide the onlyevidence about the effects of interventions on long-term outcomes, rare events or adverse effects.Therefore, systematic reviews on the effects of interventions may include various types of non-randomizedstudies. In this second paper in a series, we address how review authors might articulate the particularnon-randomized study designs they will include and how they might evaluate, in general terms, the extentto which a particular non-randomized study is at risk of important biases. We offer guidance for describingand classifying different non-randomized designs based on speci¿c features of the studies in place of usingnon-informative study design labels. We also suggest criteria to consider when deciding whether toinclude non-randomized studies. We conclude that a taxonomy of study designs based on study designfeatures is needed. Review authors need new tools speci¿cally to assess the risk of bias for somenon-randomized designs that involve a different inferential logic compared with parallel group trials.Copyright © 2012 John Wiley & Sons, Ltd.

AB - Non-randomized studies may provide valuable evidence on the effects of interventions. They are the mainsource of evidence on the intended effects of some types of interventions and often provide the onlyevidence about the effects of interventions on long-term outcomes, rare events or adverse effects.Therefore, systematic reviews on the effects of interventions may include various types of non-randomizedstudies. In this second paper in a series, we address how review authors might articulate the particularnon-randomized study designs they will include and how they might evaluate, in general terms, the extentto which a particular non-randomized study is at risk of important biases. We offer guidance for describingand classifying different non-randomized designs based on speci¿c features of the studies in place of usingnon-informative study design labels. We also suggest criteria to consider when deciding whether toinclude non-randomized studies. We conclude that a taxonomy of study designs based on study designfeatures is needed. Review authors need new tools speci¿cally to assess the risk of bias for somenon-randomized designs that involve a different inferential logic compared with parallel group trials.Copyright © 2012 John Wiley & Sons, Ltd.

KW - non randomized studies

KW - study design

KW - bias

KW - systematic reviews

U2 - 10.1002/jrsm.1056

DO - 10.1002/jrsm.1056

M3 - Article

VL - 4

SP - 12

EP - 25

JO - Research Synthesis Methods

JF - Research Synthesis Methods

SN - 1759-2887

IS - 1

ER -