Intracluster correlation coefficients and reliability of randomized multicenter stroke trials within VISTA

Benedikt Frank, Rachael L. Fulton, Fraser C. Goldie, Werner Hacke, Christian Weimar, Kennedy R. Lees, Andrei Alexandrov, P. W. Bath, E. Bluhmki, L. Claesson, J. Curram, S. M. Davis, G. Donnan, H. C. Diener, M. Fisher, B. Gregson, J. Grotta, W. Hacke, M. G. Hennerici, M. Hommel & 10 others M. Kaste, P. Lyden, J. Marler, K. Muir, R. Sacco, A. Shuaib, P. Teal, N. G. Wahlgren, S. Warach, C. Weimar

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Background: Reliable estimates of intracluster correlation coefficients (ICCs) for specific outcome measures are crucial for sample size calculations of future cluster randomized trials. ICCs indicate the proportion of data variability that is explained by defined levels of clustering. Aims: In this manuscript, we present potentially valuable and reliable estimates of ICCs for specific baseline and follow-up data. Method: ICCs were estimated from linear and generalized linear mixed models using maximum likelihood estimation for common measures used in stroke research, including modified Rankin Scale (mRS), National Institutes of Health Stroke Scale (NIHSS), and Barthel Index (BI). Results: Data were available for 11841 patients with ischemic stroke from 11 randomized trials. After adjusting for age, thrombolysis, and baseline NIHSS, the median ICC for follow-up data, using center as the level of clustering, ranged from 0·007 to 0·041. The ICCs using trial, continent or year of enrollment as level of clustering were distinctly lower. Less than 1% of the variability of mRS, NIHSS, and BI was explained by any of these three cluster levels. Conclusion: This compendium of relevant ICC estimates should assist trial planning. For example, the sample size for a cluster trial with 150 patients per center using ordinal analysis of mRS should be inflated by 2·0 due to the ICC of 0·007; whereas the ICC of 0·031 using mRS dichotomized above mRS 0-1, requires inflation by 5·6. The low contribution of trials, year or continent of enrollment to overall variation in outcome offers reassurance that analyses using pooled data from multiple trials in VISTA are unlikely to suffer from bias from these sources.

Original languageEnglish (US)
Pages (from-to)602-606
Number of pages5
JournalInternational Journal of Stroke
Volume9
Issue number5
DOIs
StatePublished - Jul 1 2014

Fingerprint

Multicenter Studies
Stroke
National Institutes of Health (U.S.)
Cluster Analysis
Sample Size
Economic Inflation
Linear Models
Outcome Assessment (Health Care)
Research

All Science Journal Classification (ASJC) codes

  • Neurology

Cite this

Frank, B., Fulton, R. L., Goldie, F. C., Hacke, W., Weimar, C., Lees, K. R., ... Weimar, C. (2014). Intracluster correlation coefficients and reliability of randomized multicenter stroke trials within VISTA. International Journal of Stroke, 9(5), 602-606. https://doi.org/10.1111/ijs.12123

Intracluster correlation coefficients and reliability of randomized multicenter stroke trials within VISTA. / Frank, Benedikt; Fulton, Rachael L.; Goldie, Fraser C.; Hacke, Werner; Weimar, Christian; Lees, Kennedy R.; Alexandrov, Andrei; Bath, P. W.; Bluhmki, E.; Claesson, L.; Curram, J.; Davis, S. M.; Donnan, G.; Diener, H. C.; Fisher, M.; Gregson, B.; Grotta, J.; Hacke, W.; Hennerici, M. G.; Hommel, M.; Kaste, M.; Lyden, P.; Marler, J.; Muir, K.; Sacco, R.; Shuaib, A.; Teal, P.; Wahlgren, N. G.; Warach, S.; Weimar, C.

In: International Journal of Stroke, Vol. 9, No. 5, 01.07.2014, p. 602-606.

Research output: Contribution to journalArticle

Frank, B, Fulton, RL, Goldie, FC, Hacke, W, Weimar, C, Lees, KR, Alexandrov, A, Bath, PW, Bluhmki, E, Claesson, L, Curram, J, Davis, SM, Donnan, G, Diener, HC, Fisher, M, Gregson, B, Grotta, J, Hacke, W, Hennerici, MG, Hommel, M, Kaste, M, Lyden, P, Marler, J, Muir, K, Sacco, R, Shuaib, A, Teal, P, Wahlgren, NG, Warach, S & Weimar, C 2014, 'Intracluster correlation coefficients and reliability of randomized multicenter stroke trials within VISTA', International Journal of Stroke, vol. 9, no. 5, pp. 602-606. https://doi.org/10.1111/ijs.12123
Frank, Benedikt ; Fulton, Rachael L. ; Goldie, Fraser C. ; Hacke, Werner ; Weimar, Christian ; Lees, Kennedy R. ; Alexandrov, Andrei ; Bath, P. W. ; Bluhmki, E. ; Claesson, L. ; Curram, J. ; Davis, S. M. ; Donnan, G. ; Diener, H. C. ; Fisher, M. ; Gregson, B. ; Grotta, J. ; Hacke, W. ; Hennerici, M. G. ; Hommel, M. ; Kaste, M. ; Lyden, P. ; Marler, J. ; Muir, K. ; Sacco, R. ; Shuaib, A. ; Teal, P. ; Wahlgren, N. G. ; Warach, S. ; Weimar, C. / Intracluster correlation coefficients and reliability of randomized multicenter stroke trials within VISTA. In: International Journal of Stroke. 2014 ; Vol. 9, No. 5. pp. 602-606.
@article{9640442af80b4b20a91ee466eec5234d,
title = "Intracluster correlation coefficients and reliability of randomized multicenter stroke trials within VISTA",
abstract = "Background: Reliable estimates of intracluster correlation coefficients (ICCs) for specific outcome measures are crucial for sample size calculations of future cluster randomized trials. ICCs indicate the proportion of data variability that is explained by defined levels of clustering. Aims: In this manuscript, we present potentially valuable and reliable estimates of ICCs for specific baseline and follow-up data. Method: ICCs were estimated from linear and generalized linear mixed models using maximum likelihood estimation for common measures used in stroke research, including modified Rankin Scale (mRS), National Institutes of Health Stroke Scale (NIHSS), and Barthel Index (BI). Results: Data were available for 11841 patients with ischemic stroke from 11 randomized trials. After adjusting for age, thrombolysis, and baseline NIHSS, the median ICC for follow-up data, using center as the level of clustering, ranged from 0·007 to 0·041. The ICCs using trial, continent or year of enrollment as level of clustering were distinctly lower. Less than 1{\%} of the variability of mRS, NIHSS, and BI was explained by any of these three cluster levels. Conclusion: This compendium of relevant ICC estimates should assist trial planning. For example, the sample size for a cluster trial with 150 patients per center using ordinal analysis of mRS should be inflated by 2·0 due to the ICC of 0·007; whereas the ICC of 0·031 using mRS dichotomized above mRS 0-1, requires inflation by 5·6. The low contribution of trials, year or continent of enrollment to overall variation in outcome offers reassurance that analyses using pooled data from multiple trials in VISTA are unlikely to suffer from bias from these sources.",
author = "Benedikt Frank and Fulton, {Rachael L.} and Goldie, {Fraser C.} and Werner Hacke and Christian Weimar and Lees, {Kennedy R.} and Andrei Alexandrov and Bath, {P. W.} and E. Bluhmki and L. Claesson and J. Curram and Davis, {S. M.} and G. Donnan and Diener, {H. C.} and M. Fisher and B. Gregson and J. Grotta and W. Hacke and Hennerici, {M. G.} and M. Hommel and M. Kaste and P. Lyden and J. Marler and K. Muir and R. Sacco and A. Shuaib and P. Teal and Wahlgren, {N. G.} and S. Warach and C. Weimar",
year = "2014",
month = "7",
day = "1",
doi = "10.1111/ijs.12123",
language = "English (US)",
volume = "9",
pages = "602--606",
journal = "International Journal of Stroke",
issn = "1747-4930",
publisher = "Wiley-Blackwell",
number = "5",

}

TY - JOUR

T1 - Intracluster correlation coefficients and reliability of randomized multicenter stroke trials within VISTA

AU - Frank, Benedikt

AU - Fulton, Rachael L.

AU - Goldie, Fraser C.

AU - Hacke, Werner

AU - Weimar, Christian

AU - Lees, Kennedy R.

AU - Alexandrov, Andrei

AU - Bath, P. W.

AU - Bluhmki, E.

AU - Claesson, L.

AU - Curram, J.

AU - Davis, S. M.

AU - Donnan, G.

AU - Diener, H. C.

AU - Fisher, M.

AU - Gregson, B.

AU - Grotta, J.

AU - Hacke, W.

AU - Hennerici, M. G.

AU - Hommel, M.

AU - Kaste, M.

AU - Lyden, P.

AU - Marler, J.

AU - Muir, K.

AU - Sacco, R.

AU - Shuaib, A.

AU - Teal, P.

AU - Wahlgren, N. G.

AU - Warach, S.

AU - Weimar, C.

PY - 2014/7/1

Y1 - 2014/7/1

N2 - Background: Reliable estimates of intracluster correlation coefficients (ICCs) for specific outcome measures are crucial for sample size calculations of future cluster randomized trials. ICCs indicate the proportion of data variability that is explained by defined levels of clustering. Aims: In this manuscript, we present potentially valuable and reliable estimates of ICCs for specific baseline and follow-up data. Method: ICCs were estimated from linear and generalized linear mixed models using maximum likelihood estimation for common measures used in stroke research, including modified Rankin Scale (mRS), National Institutes of Health Stroke Scale (NIHSS), and Barthel Index (BI). Results: Data were available for 11841 patients with ischemic stroke from 11 randomized trials. After adjusting for age, thrombolysis, and baseline NIHSS, the median ICC for follow-up data, using center as the level of clustering, ranged from 0·007 to 0·041. The ICCs using trial, continent or year of enrollment as level of clustering were distinctly lower. Less than 1% of the variability of mRS, NIHSS, and BI was explained by any of these three cluster levels. Conclusion: This compendium of relevant ICC estimates should assist trial planning. For example, the sample size for a cluster trial with 150 patients per center using ordinal analysis of mRS should be inflated by 2·0 due to the ICC of 0·007; whereas the ICC of 0·031 using mRS dichotomized above mRS 0-1, requires inflation by 5·6. The low contribution of trials, year or continent of enrollment to overall variation in outcome offers reassurance that analyses using pooled data from multiple trials in VISTA are unlikely to suffer from bias from these sources.

AB - Background: Reliable estimates of intracluster correlation coefficients (ICCs) for specific outcome measures are crucial for sample size calculations of future cluster randomized trials. ICCs indicate the proportion of data variability that is explained by defined levels of clustering. Aims: In this manuscript, we present potentially valuable and reliable estimates of ICCs for specific baseline and follow-up data. Method: ICCs were estimated from linear and generalized linear mixed models using maximum likelihood estimation for common measures used in stroke research, including modified Rankin Scale (mRS), National Institutes of Health Stroke Scale (NIHSS), and Barthel Index (BI). Results: Data were available for 11841 patients with ischemic stroke from 11 randomized trials. After adjusting for age, thrombolysis, and baseline NIHSS, the median ICC for follow-up data, using center as the level of clustering, ranged from 0·007 to 0·041. The ICCs using trial, continent or year of enrollment as level of clustering were distinctly lower. Less than 1% of the variability of mRS, NIHSS, and BI was explained by any of these three cluster levels. Conclusion: This compendium of relevant ICC estimates should assist trial planning. For example, the sample size for a cluster trial with 150 patients per center using ordinal analysis of mRS should be inflated by 2·0 due to the ICC of 0·007; whereas the ICC of 0·031 using mRS dichotomized above mRS 0-1, requires inflation by 5·6. The low contribution of trials, year or continent of enrollment to overall variation in outcome offers reassurance that analyses using pooled data from multiple trials in VISTA are unlikely to suffer from bias from these sources.

UR - http://www.scopus.com/inward/record.url?scp=84902075136&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902075136&partnerID=8YFLogxK

U2 - 10.1111/ijs.12123

DO - 10.1111/ijs.12123

M3 - Article

VL - 9

SP - 602

EP - 606

JO - International Journal of Stroke

JF - International Journal of Stroke

SN - 1747-4930

IS - 5

ER -