Aurélie Chevance1, Tibor Schuster2, Russell Steele3, Nils Ternès4, Robert W Platt5. 1. Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, 1020 Pine Ave W., Montreal, Quebec, Canada H3A 1A2. 2. Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, 1020 Pine Ave W., Montreal, Quebec, Canada H3A 1A2. Electronic address: tibor.schuster@mcgill.ca. 3. Centre for Clinical Epidemiology, Lady Davis Institute for Medical Research, Jewish General Hospital, 3755 Cote Ste-Catherine, H-461, Montreal, Quebec, Canada H3T 1E2; Department of Mathematics and Statistics, McGill University, Burnside Hall, 805 Sherbrooke Street West, Montreal, Quebec, Canada H3A 0B9. 4. Service de biostatistique et d'épidémiologie, Gustave Roussy, 39 rue Camille Desmoulins, Villejuif, France; CESP Centre for Research in Epidemiology and Population Health, INSERM U1018, Paris-Sud University, 12 avenue Paul Vaillant Couturier, Villejuif, France. 5. Department of Epidemiology, Biostatistics, and Occupational Health, McGill University, 1020 Pine Ave W., Montreal, Quebec, Canada H3A 1A2; Department of Pediatrics, McGill University, 1001 Decarie Boulevard, Montreal, Quebec, Canada H4A 3J1.
Abstract
OBJECTIVES: Robustness of an existing meta-analysis can justify decisions on whether to conduct an additional study addressing the same research question. We illustrate the graphical assessment of the potential impact of an additional study on an existing meta-analysis using published data on statin use and the risk of acute kidney injury. STUDY DESIGN AND SETTING: A previously proposed graphical augmentation approach is used to assess the sensitivity of the current test and heterogeneity statistics extracted from existing meta-analysis data. In addition, we extended the graphical augmentation approach to assess potential changes in the pooled effect estimate after updating a current meta-analysis and applied the three graphical contour definitions to data from meta-analyses on statin use and acute kidney injury risk. RESULTS: In the considered example data, the pooled effect estimates and heterogeneity indices demonstrated to be considerably robust to the addition of a future study. Supportingly, for some previously inconclusive meta-analyses, a study update might yield statistically significant kidney injury risk increase associated with higher statin exposure. CONCLUSIONS: The illustrated contour approach should become a standard tool for the assessment of the robustness of meta-analyses. It can guide decisions on whether to conduct additional studies addressing a relevant research question.
OBJECTIVES: Robustness of an existing meta-analysis can justify decisions on whether to conduct an additional study addressing the same research question. We illustrate the graphical assessment of the potential impact of an additional study on an existing meta-analysis using published data on statin use and the risk of acute kidney injury. STUDY DESIGN AND SETTING: A previously proposed graphical augmentation approach is used to assess the sensitivity of the current test and heterogeneity statistics extracted from existing meta-analysis data. In addition, we extended the graphical augmentation approach to assess potential changes in the pooled effect estimate after updating a current meta-analysis and applied the three graphical contour definitions to data from meta-analyses on statin use and acute kidney injury risk. RESULTS: In the considered example data, the pooled effect estimates and heterogeneity indices demonstrated to be considerably robust to the addition of a future study. Supportingly, for some previously inconclusive meta-analyses, a study update might yield statistically significant kidney injury risk increase associated with higher statin exposure. CONCLUSIONS: The illustrated contour approach should become a standard tool for the assessment of the robustness of meta-analyses. It can guide decisions on whether to conduct additional studies addressing a relevant research question.
Authors: Kristian Thorlund; P J Devereaux; Jørn Wetterslev; Gordon Guyatt; John P A Ioannidis; Lehana Thabane; Lise-Lotte Gluud; Bodil Als-Nielsen; Christian Gluud Journal: Int J Epidemiol Date: 2008-09-29 Impact factor: 7.196
Authors: Colin R Dormuth; Brenda R Hemmelgarn; J Michael Paterson; Matthew T James; Gary F Teare; Colette B Raymond; Jean-Philippe Lafrance; Adrian Levy; Amit X Garg; Pierre Ernst Journal: BMJ Date: 2013-03-18
Authors: Alexander J Sutton; Nicola J Cooper; David R Jones; Paul C Lambert; John R Thompson; Keith R Abrams Journal: Stat Med Date: 2007-05-30 Impact factor: 2.373