Please use this identifier to cite or link to this item:
Title: A statistical approach to central monitoring of data quality in clinical trials
Authors: Venet, David
Doffagne, Erik
Burzykowski, Tomasz 
Beckers, Francois
Tellier, Yves
Genevois-Marlin, Eric
Becker, Ursula
Bee, Valerie
Wilson, Veronique
Legrand, Catherine 
Buyse, Marc 
Issue Date: 2012
Source: CLINICAL TRIALS, 9 (6), p. 705-713
Abstract: Background Classical monitoring approaches rely on extensive on-site visits and source data verification. These activities are associated with high cost and a limited contribution to data quality. Central statistical monitoring is of particular interest to address these shortcomings. Purpose This article outlines the principles of central statistical monitoring and the challenges of implementing it in actual trials. Methods A statistical approach to central monitoring is based on a large number of statistical tests performed on all variables collected in the database, in order to identify centers that differ from the others. The tests generate a high-dimensional matrix of p-values, which can be analyzed by statistical methods and bioinformatic tools to identify extreme centers. Results Results from actual trials are provided to illustrate typical findings that can be expected from a central statistical monitoring approach, which detects abnormal patterns that were not (or could not have been) detected by on-site monitoring. Limitations Central statistical monitoring can only address problems present in the data. Important aspects of trial conduct such as a lack of informed consent documentation, for instance, require other approaches. The results provided here are empirical examples from a limited number of studies. Conclusion Central statistical monitoring can both optimize on-site monitoring and improve data quality and as such provides a cost-effective way of meeting regulatory requirements for clinical trials. Clinical Trials 2012; 9: 705-713.
Notes: [Buyse, Marc] IDDI Inc, Houston, TX 77060 USA. [Venet, David; Doffagne, Erik; Burzykowski, Tomasz] IDDI, Louvain, Belgium. [Venet, David] Univ Libre Brussels, IRIDIA, Brussels, Belgium. [Burzykowski, Tomasz; Buyse, Marc] Hasselt Univ, Interuniv Inst Biostat & Stat Bioinformat I BioSt, Diepenbeek, Belgium. [Beckers, Francois; Tellier, Yves] GlaxoSmithKline Biol, Wavre, Belgium. [Genevois-Marlin, Eric] Sanofi Aventis R&D Biostat & Programming, Bridgewater, NJ USA. [Becker, Ursula] F Hoffmann LaRoche Ltd, Basel, Switzerland. [Bee, Valerie; Wilson, Veronique] Translat Res Oncol TRIO, Paris, France. [Legrand, Catherine] Catholic Univ Louvain, Inst Stat Biostat & Actuarial Sci ISBA, B-1348 Louvain, Belgium.
Keywords: Medicine, Research & Experimental
Document URI:
ISSN: 1740-7745
e-ISSN: 1740-7753
DOI: 10.1177/1740774512447898
ISI #: 000312452600006
Category: A1
Type: Journal Contribution
Validations: ecoom 2014
Appears in Collections:Research publications

Files in This Item:
File Description SizeFormat 
Clinical Trials - A statistical approach to central monitoring of data quality in clinical trials.pdf
  Restricted Access
909.2 kBAdobe PDFView/Open    Request a copy
Show full item record


checked on Sep 5, 2020


checked on May 14, 2022

Page view(s)

checked on May 18, 2022


checked on May 18, 2022

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.