Portal de Periódicos da CAPES

Living systematic reviews: 3. Statistical methods for updating meta-analyses

2017; Elsevier BV; Volume: 91; Linguagem: Inglês

10.1016/j.jclinepi.2017.08.008

1878-5921

Mark Simmonds, Georgia Salanti, Joanne E. McKenzie, Julian Elliott, Thomas Agoritsas, John Hilton, Caroline Perron, Elie A. Akl, Rebecca K Hodder, Charlotte Pestridge, Lauren Albrecht, Tanya Horsley, Joanne Platt, Rebecca Armstrong, Phi Hùng Nguyễn, Robert M. Plovnick, Anneliese Arno, Noah Ivers, Gail Quinn, Agnes Au, Renea V Johnston, Gabriel Rada, Matthew K. Bagg, Arwel W. Jones, Philippe Ravaud, Catherine Boden, Lara A Kahale, Bernt Richter, Isabelle Boisvert, Homa Keshavarz, Rebecca Ryan, Linn Brandt, Stephanie A. Kolakowsky‐Hayner, Dina H. Salama, Alexandra Bražinová, Sumanth Kumbargere Nagraj, Georgia Salanti, Rachelle Buchbinder, Toby J Lasserson, Lina Santaguida, Chris Champion, Rebecca Lawrence, Nancy Santesso, Jackie Chandler, Zbigniew Leś, Holger J. Schünemann, Andreas Charidimou, Stefan Leucht, Ian Shemilt, Roger Chou, Nicola Low, Diana Sherifali, Rachel Churchill, Andrew I.R. Maas, Reed Siemieniuk, Maryse C. Cnossen, Harriet MacLehose, Mark Simmonds, Marie-Joëlle Cossi, Malcolm Macleod, Nicole Skoetz, Michel Jacques Counotte, Iain Marshall, Karla Soares‐Weiser, Samantha Craigie, Iain Marshall, Velandai Srikanth, Philipp Dahm, Nicole Martin, Katrina Sullivan, Alanna Danilkewich, Laura Martínez García, Anneliese Synnot, Kristen Danko, Chris Mavergames, Mark J. Taylor, Emma Donoghue, Lara Maxwell, Kris Thayer, Corinna Dressler, James H. McAuley, James Thomas, Cathy Egan, Steve McDonald, Roger Tritton, Julian Elliott, Joanne E. McKenzie, Guy Tsafnat, Sarah A. Elliott, Joerg J Meerpohl, Peter Tugwell, Itziar Etxeandia‐Ikobaltzeta, Bronwen Merner, Alexis F. Turgeon, Robin Featherstone, Stefania Mondello, Tari Turner, Ruth Foxlee, Richard Morley, Gert van Valkenhoef, Paul Garner, Marcus R. Munafò, Per Olav Vandvik, Martha Gerrity, Zachary Munn, Byron Wallace, Paul Glasziou, Melissa Murano, S Wallace, Sally Green, Kristine Newman, Chris Watts, Jeremy Grimshaw, Robby Nieuwlaat, Laura Weeks, Kurinchi Selvan Gurusamy, Adriani Nikolakopoulou, Aaron Weigl, Neal Haddaway, Anna H Noel-Storr, George A. Wells, Lisa Hartling, Annette M. O’Connor, Wojtek Wiercioch, Jill A. Hayden, Matthew J. Page, Luke Wolfenden, Mark Helfand, Manisha Pahwa, Juan José Yepes‐Nuñez, Julian P. T. Higgins, Jordi Pardo Pardo, Jennifer Yost, Sophie Hill, Leslea Pearson,

Statistical Methods in Clinical Trials

A living systematic review (LSR) should keep the review current as new research evidence emerges. Any meta-analyses included in the review will also need updating as new material is identified. If the aim of the review is solely to present the best current evidence standard meta-analysis may be sufficient, provided reviewers are aware that results may change at later updates. If the review is used in a decision-making context, more caution may be needed. When using standard meta-analysis methods, the chance of incorrectly concluding that any updated meta-analysis is statistically significant when there is no effect (the type I error) increases rapidly as more updates are performed. Inaccurate estimation of any heterogeneity across studies may also lead to inappropriate conclusions. This paper considers four methods to avoid some of these statistical problems when updating meta-analyses: two methods, that is, law of the iterated logarithm and the Shuster method control primarily for inflation of type I error and two other methods, that is, trial sequential analysis and sequential meta-analysis control for type I and II errors (failing to detect a genuine effect) and take account of heterogeneity. This paper compares the methods and considers how they could be applied to LSRs.