On Pooling Different Levels of Data in Estimating Parameters of Continuous Meta-Analysis

Authors: N. R. N. Idris, S. Baharom

Abstract:

A meta-analysis may be performed using aggregate data (AD) or an individual patient data (IPD). In practice, studies may be available at both IPD and AD level. In this situation, both the IPD and AD should be utilised in order to maximize the available information. Statistical advantages of combining the studies from different level have not been fully explored. This study aims to quantify the statistical benefits of including available IPD when conducting a conventional summary-level meta-analysis. Simulated meta-analysis were used to assess the influence of the levels of data on overall meta-analysis estimates based on IPD-only, AD-only and the combination of IPD and AD (mixed data, MD), under different study scenario. The percentage relative bias (PRB), root mean-square-error (RMSE) and coverage probability were used to assess the efficiency of the overall estimates. The results demonstrate that available IPD should always be included in a conventional meta-analysis using summary level data as they would significantly increased the accuracy of the estimates.On the other hand, if more than 80% of the available data are at IPD level, including the AD does not provide significant differences in terms of accuracy of the estimates. Additionally, combining the IPD and AD has moderating effects on the biasness of the estimates of the treatment effects as the IPD tends to overestimate the treatment effects, while the AD has the tendency to produce underestimated effect estimates. These results may provide some guide in deciding if significant benefit is gained by pooling the two levels of data when conducting meta-analysis.

Keywords: Aggregate data, combined-level data, Individual patient data, meta analysis.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1094126

References:

[1] Whitehead A (2002). Meta-analysis of controlled clinical trials. London:John Wiley . 215 - 237.
[2] DerSimonian R, Laird N. Meta-analysis in clinical trials. Control Clin Trials 1986, 7, 177-188.
[3] Mantel N, Haenszel W. Statistical aspects of the analysis of data from retrospective studies of disease. J Natl Cancer Inst, 1959, 22, 719-748.
[4] Stewart LA, Tierney JF. To IPD or not to IPD? Advantages and disadvantages of systematic reviews using individual patient data. Eval Health Prof, 2002, 25, 76-97.
[5] Simmonds MC, Higgins JPT, Stewart LA, Tierney JF, Clarke MJ, Thompson SG. Meta-analysis of individual patient data from randomized trials: a review of methods used in practice. Clin Trials 2005, 2, 209-217.
[6] Jones AP, Riley RD, Williamson PR, Whitehead A. Meta-analysis of individual patient data versus aggregate data from longitudinal clinical trials, Clin Trials., 2009, 6(1), 16-27.
[7] Cooper H, Patall EA. The relative benefits of meta-analysis conducted with individual participant data versus aggregated data, Psychol Methods. 2009, Jun, 14(2), 165-76.
[8] Lambert PC, Sutton AJ, Abrams KR, Jones RD. A comparison of summary patient-level covariates in metaregression with individual patient data meta-analysis, Journal of Clinical Epidemiology, 2001, 55, 86–94.
[9] Riley RD,Simmond MC, Look MP. Evidence synthesis combining individual patient data and aggregate data:a systematic review identified current practice and possible methods. Journal of Clinical Epidemiology, 2007, 60, 431-439.
[10] Riley RD, Lambert PC, Staessen JA, Wang J, Gueyffier F, Thijs L and Boutitie F, Meta-analysis of continuous outcomes combining individual patient data and aggregate data, Statist. Med., 2008 27, 1870–1893.
[11] Wang JG, Staessen JA, Franklin SS, Fagard R, Gueyffier F. Systolic and diastolic blood pressure lowering as determinants of cardiovascular Hypertension, 2005, 45, 907–913.
[12] Idris, NRN., Robertson C, (2009). The effects of imputing the missing standard deviations on the standarderror of the meta analysis estimates. Comm in stats – Sim and Comp ; 38:513-526.