Trial Sequential Analysis

Trial Sequential Analysis (TSA) is a methodology that combines an information size calculation (cumulated sample sizes of all included trials) for a meta-analysis with the threshold of statistical significance. TSA is a tool for quantifying the statistical reliability of data in the cumulative meta-analysis adjusting significance levels for sparse data and repetitive testing on accumulating data.

Meta-analysis may result in type I errors due to systematic errors (bias) or random errors (play of chance) due to sparse data and repeated significance testing when updating meta-analysis with new trials. Bias from trials with low methodological quality, outcome measure bias, publication bias, early stopping for benefit, and small trial bias may result in spurious P-values.

In a single trial, interim analyses increase the risk of type I errors. To avoid type I errors, group sequential monitoring boundaries are applied to decide whether a trial could be terminated early because of a sufficiently small P-value, that is if the cumulative Z-curve crosses the monitoring boundaries (1). Sequential monitoring boundaries can be applied to meta-analysis as well, called trial sequential monitoring boundaries. In TSA the addition of each trial in a cumulative meta-analysis is regarded as an interim meta-analysis and TSA controls the risks for type I and type II errors and helps to clarify whether additional trials are needed. Additionally, TSA provides us with important information regarding the required sample size for such trials.

For more detailed information, please refer to the TSA website and the TSA manual in english, chinese and spanish.

The TSA software can be downloaded at the TSA website. You are welcome to use it in your analyses and publications of cumulative meta-analyses with proper reference to the software and some of our articles describing the methodology. Below are some publications where the use of the TSA software is illustrated.

In case you need assistance with the TSA software, please contact us via email: tsa@ctu.dk.

(1) Lan KKG. and DeMets G. Discrete sequential boundaries for clinical trials. Biometrika 1983; 70(3): 659-663. View.

 

Publications which have used TSA and the TSA software:

Nielsen N, Friberg H, Gluud C, Herlitz J, Wetterslev J. Hypothermia after cardiac arrest should be further evaluated - A systematic review of randomised trials with meta-analysis and trial sequential analysis. Int J Cardiol. 2011; 151(3): 333–41. View

Brok J, Thorlund K, Wetterslev J, Gluud C. Apparently conclusive meta-analyses may be inconclusive - Trial sequential analysis adjustment of random error risk due to repetitive testing of accumulating data in apparently conclusive neonatal meta-analyses. Int J Epidemiol. 2009; 38(1): 287-98. View

Thorlund K, Devereaux PJ, Wetterslev J, Guyatt G, Ioannidis JP, Thabane L, Gluud LL, Als-Nielsen B, Gluud C. Can trial sequential monitoring boundaries reduce spurious inferences from meta-analyses? Int J Epidemiol. 2009; 38(1): 276-86. View

Wetterslev J, Thorlund K, Brok J, Gluud C. Estimating required information size by quantifying diversity in random-effects model meta-analyses. BMC Med Res Methodol. 2009; 9(86). View

Afshari A, Wetterslev J, Brok J, Møller AM. Antithrombin III for critically ill patients. Cochrane Database Syst Rev. 2008; (3): CD005370. View

Bangalore S, Wetterslev J, Pranesh S, Sawhney S, Gluud C, Messerli FH. Perioperative beta blockers in patients having non-cardiac surgery: A meta-analysisLancet. 2008; 372(9654): 1962-76. View

Bender R, Bunce C, Clarke M, Gates S, Lange S, Pace NL, Thorlund K. Attention should be given to multiplicity issues in systematic reviewsJ Clin Epidemiol. 2008; 61(9): 857-65. View

Brok J, Thorlund K, Gluud C, Wetterslev J. Trial sequential analysis reveals insufficient information size and potentially false positive results in many meta-analyses. J Clin Epidemiol. 2008; 61(8): 763-9. View

Rambaldi A, Saconato HH, Christensen E, Thorlund K, Wetterslev J, Gluud C. Systematic review: glucocorticosteroids for alcoholic hepatitis - a Cochrane Hepato-Biliary Group systematic review with meta-analyses and trial sequential analyses of randomized clinical trials. Aliment Pharmacol Ther. 2008; 27(12): 1167-78. View

Wetterslev J, Thorlund K, Brok J, Gluud C. Trial sequential analysis may establish when firm evidence is reached in cumulative meta-analysis. J Clin Epidemiol. 2008; 61(1): 64-75. View

Afshari A, Wetterslev J, Brok J, Møller A. Antithrombin III in critically ill patients: Systematic review with meta-analysis and trial sequential analysis. BMJ. 2007; 335(7632): 1248-51. View