×

Measures of single arm outcome in meta-analyses of rare events in the presence of competing risks. (English) Zbl 1329.62031

Summary: When performing single arm meta-analyses of rare events in small populations, if the outcome of interest is incidence, it is not uncommon to have at least one study with zero events, especially in the presence of competing risks. In this paper, we address the problem of how to include studies with zero events in inverse variance meta-analyses when individual patient data are not available, going beyond the naïve approach of not including the study or the use of a continuity correction. The proposed solution is the arcsine transformation of the crude cumulative incidence as its approximate variance, which is inversely proportional to the sample size, can be calculated also for studies with a zero estimate. As an alternative, generalized linear mixed models (GLMM) can be used. Simulations were performed to compare the results from inverse variance method meta-analyses of the arcsine transformed cumulative incidence to those obtained from meta-analyses of the cumulative incidence itself and of the logit transformation of the cumulative incidence. The comparisons have been carried out for different scenarios of heterogeneity, incidence, and censoring and for competing and not competing risks. The arcsine transformation showed the smallest bias and the highest coverage among models assuming within study normality. At the same time, the GLMM model had the best performance at very low incidences. The proposed method was applied to the clinical context that motivated this work, i.e. a meta-analysis of 5-year crude cumulative incidence of central nervous system recurrences in children treated for acute lymphoblastic leukemia.

MSC:

62-07 Data analysis (statistics) (MSC2010)
62P10 Applications of statistics to biology and medical sciences; meta analysis
62J05 Linear regression; mixed models

Software:

R; metafor
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Aalen, Nonparametric estimation of partial transition probabilities in multiple decrement models, The Annals of Statistics 6 pp 534– (1978) · Zbl 0383.62057 · doi:10.1214/aos/1176344198
[2] Aalen, An empirical transition matrix for non-homogeneous markov chains based on censored observations, Scandinavian Journal of Statistics 5 pp 141– (1978) · Zbl 0383.62058
[3] Anscombe, On estimating binomial response relations, Biometrika 43 pp 461– (1956) · Zbl 0074.14703 · doi:10.1093/biomet/43.3-4.461
[4] Barendregt, Meta-analysis of prevalence, Journal of Epidemiology and Community Health 67 pp 974– (2013) · doi:10.1136/jech-2013-203104
[5] Bartlett, Some examples of statistical methods of research in agriculture and applied biology, Supplement to the Journal of the Royal Statistical Society 4 pp 137– (1937) · doi:10.2307/2983644
[6] Bennett, On the variance stabilizing properties of certain transformations-II, Trabajos de Estadistica 8 pp 69– (1957) · Zbl 0080.12403 · doi:10.1007/BF03004004
[7] Cochran, The analysis of variance when experimental errors follow the poisson or binomial laws, The Annals of Mathematical Statistics 11 pp 335– (1940) · Zbl 0023.34104 · doi:10.1214/aoms/1177731871
[8] Cox, The Analysis of Binary Data (1970) · Zbl 0199.53301
[9] Cutler, Maximum utilization of the life table method in analyzing survival, Journal of Chronic Diseases 8 pp 699– (1958) · doi:10.1016/0021-9681(58)90126-7
[10] Einarson, Pharmacoeconomic applications of meta-analysis for single groups using antifungal onychomycosis lacquers as an example, Clinical Therapeutics 19 pp 559– (1997) · doi:10.1016/S0149-2918(97)80140-3
[11] Friedrich, Inclusion of zero total event trials in meta-analyses maintains analytic consistency and incorporates all available data, BMC Medical Research Methodology 7 pp 5– (2007) · doi:10.1186/1471-2288-7-5
[12] Guyot, Enhanced secondary analysis of survival data: reconstructing the data from published Kaplan-Meier survival curves, BMC Medical Research Methodology 12 pp 9– (2012) · doi:10.1186/1471-2288-12-9
[13] Hamza, The binomial distribution of meta-analysis was preferred to model within-study variability, Journal of Clinical Epidemiology 61 pp 41– (2008) · doi:10.1016/j.jclinepi.2007.03.016
[14] Knapp, Improved tests for a random effects meta-regression with a single covariate, Statistics in Medicine 22 pp 2693– (2003) · doi:10.1002/sim.1482
[15] Kuss, An exact test for meta-analysis with binary endpoints, Methods of information in medicine 46 pp 662– (2007)
[16] Laird, Some statistical methods for combining experimental results, International Journal of Technology Assessment in Health Care 6 pp 5– (1990) · doi:10.1017/S0266462300008916
[17] Lipsey, Practical Meta-Analysis (2001)
[18] Mills, Adherence to antiretroviral therapy in sub-saharan africa and north america: a meta-analysis, JAMA: the Journal of the American Medical Association 296 pp 679– (2006) · doi:10.1001/jama.296.6.679
[19] Parmar, Extracting summary statistics to perform meta-analyses of the published literature for survival endpoints, Statistics in Medicine 17 pp 2815– (1998) · doi:10.1002/(SICI)1097-0258(19981230)17:24<2815::AID-SIM110>3.0.CO;2-8
[20] Petretta, Review and metaanalysis of the frequency of familial dilated cardiomyopathy, The American Journal of Cardiology 108 pp 1171– (2011) · doi:10.1016/j.amjcard.2011.06.022
[21] R Core Team, R: A Language and Environment for Statistical Computing (2013)
[22] Rona, The prevalence of food allergy: a meta-analysis, The Journal of Allergy and Clinical Immunology 120 pp 638– (2007) · doi:10.1016/j.jaci.2007.05.026
[23] Rondeau, Investigating trial and treatment heterogeneity in an individual patient data meta-analysis of survival data by means of the penalized maximum likelihood approach, Statistics in Medicine 27 pp 1894– (2008) · doi:10.1002/sim.3161
[24] Rucker, Why add anything to nothing? The arcsine difference as a measure of treatment effect in meta-analysis with zero cells, Statistics in Medicine 28 pp 721– (2009) · doi:10.1002/sim.3511
[25] Stijnen, Random effects meta-analysis of event outcome in the framework of the generalized linear mixed model with applications in sparse data, Statistics in Medicine 29 pp 3046– (2010) · doi:10.1002/sim.4040
[26] Sutton, Meta-analysis of rare and adverse event data, Expert Review of Pharmacoeconomics and Outcomes Research 2 pp 367– (2002) · doi:10.1586/14737167.2.4.367
[27] Sweeting, What to add to nothing? use and avoidance of continuity corrections in meta-analysis of sparse data, Statistics in Medicine 23 pp 1351– (2004) · doi:10.1002/sim.1761
[28] Trikalinos, Simulation-Based Comparison of Methods for Meta-Analysis of Proportions and Rates (2013)
[29] Viechtbauer, Conducting meta-analyses in R with the metafor package, Journal of Statistical Software 36 pp 1– (2010) · doi:10.18637/jss.v036.i03
[30] Zimmerman, Systematic review and meta-analysis of incidence, prevalence and outcomes of atrial fibrillation in patients on dialysis, Nephrology Dialysis Transplantation 27 pp 3816– (2012) · doi:10.1093/ndt/gfs416
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.