The number needed to treat in pairwise and network meta-analysis and its graphical representation

Areti Angeliki Veroniki, Ralf Bender, Paul Glasziou, Sharon E. Straus, Andrea C. Tricco

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Objective: The objective of this study was to present ways to graphically represent a number needed to treat (NNT) in (network) meta-analysis (NMA). Study Design and Setting: A barrier to using NNT in NMA when an odds ratio (OR) or risk ratio (RR) is used is the determination of a single control event rate (CER). We discuss approaches to calculate a CER, and illustrate six graphical methods for NNT from NMA. We illustrate the graphical approaches using an NMA of cognitive enhancers for Alzheimer's dementia. Results: The NNT calculation using a relative effect measure, such as OR and RR, requires a CER value, but different CERs, including mean CER across studies, pooled CER in meta-analysis, and expert opinion-based CER may result in different NNTs. An NNT from NMA can be presented in a bar plot, Cates plot, or forest plot for a single outcome, and a bubble plot, scatterplot, or rank-heat plot for ≥2 outcomes. Each plot is associated with different properties and can serve different needs. Conclusion: Caution is needed in NNT interpretation, as considerations such as selection of effect size and CER, and CER assumption across multiple comparisons, may impact NNT and decision-making. The proposed graphs are helpful to interpret NNTs calculated from (network) meta-analyses.

Original languageEnglish
Pages (from-to)11-22
Number of pages12
JournalJournal of Clinical Epidemiology
Volume111
Early online date21 Mar 2019
DOIs
Publication statusPublished - 1 Jul 2019

Fingerprint

Numbers Needed To Treat
Odds Ratio
Nootropic Agents
Expert Testimony
Network Meta-Analysis
Meta-Analysis
Decision Making
Alzheimer Disease
Hot Temperature

Cite this

Veroniki, Areti Angeliki ; Bender, Ralf ; Glasziou, Paul ; Straus, Sharon E. ; Tricco, Andrea C. / The number needed to treat in pairwise and network meta-analysis and its graphical representation. In: Journal of Clinical Epidemiology. 2019 ; Vol. 111. pp. 11-22.
@article{c9709afd4e314af29d10e9328764b86d,
title = "The number needed to treat in pairwise and network meta-analysis and its graphical representation",
abstract = "Objective: The objective of this study was to present ways to graphically represent a number needed to treat (NNT) in (network) meta-analysis (NMA). Study Design and Setting: A barrier to using NNT in NMA when an odds ratio (OR) or risk ratio (RR) is used is the determination of a single control event rate (CER). We discuss approaches to calculate a CER, and illustrate six graphical methods for NNT from NMA. We illustrate the graphical approaches using an NMA of cognitive enhancers for Alzheimer's dementia. Results: The NNT calculation using a relative effect measure, such as OR and RR, requires a CER value, but different CERs, including mean CER across studies, pooled CER in meta-analysis, and expert opinion-based CER may result in different NNTs. An NNT from NMA can be presented in a bar plot, Cates plot, or forest plot for a single outcome, and a bubble plot, scatterplot, or rank-heat plot for ≥2 outcomes. Each plot is associated with different properties and can serve different needs. Conclusion: Caution is needed in NNT interpretation, as considerations such as selection of effect size and CER, and CER assumption across multiple comparisons, may impact NNT and decision-making. The proposed graphs are helpful to interpret NNTs calculated from (network) meta-analyses.",
author = "Veroniki, {Areti Angeliki} and Ralf Bender and Paul Glasziou and Straus, {Sharon E.} and Tricco, {Andrea C.}",
year = "2019",
month = "7",
day = "1",
doi = "10.1016/j.jclinepi.2019.03.007",
language = "English",
volume = "111",
pages = "11--22",
journal = "Journal of Chronic Diseases",
issn = "0895-4356",
publisher = "Elsevier",

}

The number needed to treat in pairwise and network meta-analysis and its graphical representation. / Veroniki, Areti Angeliki; Bender, Ralf; Glasziou, Paul; Straus, Sharon E.; Tricco, Andrea C.

In: Journal of Clinical Epidemiology, Vol. 111, 01.07.2019, p. 11-22.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - The number needed to treat in pairwise and network meta-analysis and its graphical representation

AU - Veroniki, Areti Angeliki

AU - Bender, Ralf

AU - Glasziou, Paul

AU - Straus, Sharon E.

AU - Tricco, Andrea C.

PY - 2019/7/1

Y1 - 2019/7/1

N2 - Objective: The objective of this study was to present ways to graphically represent a number needed to treat (NNT) in (network) meta-analysis (NMA). Study Design and Setting: A barrier to using NNT in NMA when an odds ratio (OR) or risk ratio (RR) is used is the determination of a single control event rate (CER). We discuss approaches to calculate a CER, and illustrate six graphical methods for NNT from NMA. We illustrate the graphical approaches using an NMA of cognitive enhancers for Alzheimer's dementia. Results: The NNT calculation using a relative effect measure, such as OR and RR, requires a CER value, but different CERs, including mean CER across studies, pooled CER in meta-analysis, and expert opinion-based CER may result in different NNTs. An NNT from NMA can be presented in a bar plot, Cates plot, or forest plot for a single outcome, and a bubble plot, scatterplot, or rank-heat plot for ≥2 outcomes. Each plot is associated with different properties and can serve different needs. Conclusion: Caution is needed in NNT interpretation, as considerations such as selection of effect size and CER, and CER assumption across multiple comparisons, may impact NNT and decision-making. The proposed graphs are helpful to interpret NNTs calculated from (network) meta-analyses.

AB - Objective: The objective of this study was to present ways to graphically represent a number needed to treat (NNT) in (network) meta-analysis (NMA). Study Design and Setting: A barrier to using NNT in NMA when an odds ratio (OR) or risk ratio (RR) is used is the determination of a single control event rate (CER). We discuss approaches to calculate a CER, and illustrate six graphical methods for NNT from NMA. We illustrate the graphical approaches using an NMA of cognitive enhancers for Alzheimer's dementia. Results: The NNT calculation using a relative effect measure, such as OR and RR, requires a CER value, but different CERs, including mean CER across studies, pooled CER in meta-analysis, and expert opinion-based CER may result in different NNTs. An NNT from NMA can be presented in a bar plot, Cates plot, or forest plot for a single outcome, and a bubble plot, scatterplot, or rank-heat plot for ≥2 outcomes. Each plot is associated with different properties and can serve different needs. Conclusion: Caution is needed in NNT interpretation, as considerations such as selection of effect size and CER, and CER assumption across multiple comparisons, may impact NNT and decision-making. The proposed graphs are helpful to interpret NNTs calculated from (network) meta-analyses.

UR - http://www.scopus.com/inward/record.url?scp=85064198314&partnerID=8YFLogxK

U2 - 10.1016/j.jclinepi.2019.03.007

DO - 10.1016/j.jclinepi.2019.03.007

M3 - Article

VL - 111

SP - 11

EP - 22

JO - Journal of Chronic Diseases

JF - Journal of Chronic Diseases

SN - 0895-4356

ER -