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

Living systematic reviews: 3. Statistical methods for updating meta-analyses. Simmonds, M., Salanti, G., McKenzie, J., Elliott, J., Agoritsas, T., Hilton, J., Perron, C., Akl, E., Hodder, R., Pestridge, C., Albrecht, L., Horsley, T., Platt, J., Armstrong, R., Nguyen, P. H., Plovnick, R., Arno, A., Ivers, N., Quinn, G., Au, A., Johnston, R., Rada, G., Bagg, M., Jones, A., Ravaud, P., Boden, C., Kahale, L., Richter, B., Boisvert, I., Keshavarz, H., Ryan, R., Brandt, L., Kolakowsky-Hayner, S. A., Salama, D., Brazinova, A., Nagraj, S. K., Buchbinder, R., Lasserson, T., Santaguida, L., Champion, C., Lawrence, R., Santesso, N., Chandler, J., Les, Z., Schünemann, H. J., Charidimou, A., Leucht, S., Shemilt, I., Chou, R., Low, N., Sherifali, D., Churchill, R., Maas, A., Siemieniuk, R., Cnossen, M. C., MacLehose, H., Cossi, M., Macleod, M., Skoetz, N., Counotte, M., Marshall, I., Soares-Weiser, K., Craigie, S., Marshall, R., Srikanth, V., Dahm, P., Martin, N., Sullivan, K., Danilkewich, A., García, L. M., Synnot, A., Danko, K., Mavergames, C., Taylor, M., Donoghue, E., Maxwell, L. J., Thayer, K., Dressler, C., McAuley, J., Thomas, J., Egan, C., McDonald, S., Tritton, R., Tsafnat, G., Elliott, S. A., Meerpohl, J., Tugwell, P., Etxeandia, I., Merner, B., Turgeon, A., Featherstone, R., Mondello, S., Turner, T., Foxlee, R., Morley, R., van Valkenhoef, G., Garner, P., Munafo, M., Vandvik, P., Gerrity, M., Munn, Z., Wallace, B., Glasziou, P., Murano, M., Wallace, S. A., Green, S., Newman, K., Watts, C., Grimshaw, J., Nieuwlaat, R., Weeks, L., Gurusamy, K., Nikolakopoulou, A., Weigl, A., Haddaway, N., Noel-Storr, A., Wells, G., Hartling, L., O'Connor, A., Wiercioch, W., Hayden, J., Page, M., Wolfenden, L., Helfand, M., Pahwa, M., Nuñez, J. J. Y., Higgins, J., Pardo, J. P., Yost, J., Hill, S., & Pearson, L. Journal of Clinical Epidemiology, 91:38-46, Elsevier, 2017.

Paper doi abstract bibtex

Abstract

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.

@article{simmonds2017living,
  abstract = {<h2>Abstract</h2><p>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.</p>},
  added-at = {2021-02-24T15:54:29.000+0100},
  author = {Simmonds, Mark and Salanti, Georgia and McKenzie, Joanne and Elliott, Julian and Agoritsas, Thomas and Hilton, John and Perron, Caroline and Akl, Elie and Hodder, Rebecca and Pestridge, Charlotte and Albrecht, Lauren and Horsley, Tanya and Platt, Joanne and Armstrong, Rebecca and Nguyen, Phi Hung and Plovnick, Robert and Arno, Anneliese and Ivers, Noah and Quinn, Gail and Au, Agnes and Johnston, Renea and Rada, Gabriel and Bagg, Matthew and Jones, Arwel and Ravaud, Philippe and Boden, Catherine and Kahale, Lara and Richter, Bernt and Boisvert, Isabelle and Keshavarz, Homa and Ryan, Rebecca and Brandt, Linn and Kolakowsky-Hayner, Stephanie A. and Salama, Dina and Brazinova, Alexandra and Nagraj, Sumanth Kumbargere and Buchbinder, Rachelle and Lasserson, Toby and Santaguida, Lina and Champion, Chris and Lawrence, Rebecca and Santesso, Nancy and Chandler, Jackie and Les, Zbigniew and Schünemann, Holger J. and Charidimou, Andreas and Leucht, Stefan and Shemilt, Ian and Chou, Roger and Low, Nicola and Sherifali, Diana and Churchill, Rachel and Maas, Andrew and Siemieniuk, Reed and Cnossen, Maryse C. and MacLehose, Harriet and Cossi, Marie-Joelle and Macleod, Malcolm and Skoetz, Nicole and Counotte, Michel and Marshall, Iain and Soares-Weiser, Karla and Craigie, Samantha and Marshall, Rachel and Srikanth, Velandai and Dahm, Philipp and Martin, Nicole and Sullivan, Katrina and Danilkewich, Alanna and García, Laura Martínez and Synnot, Anneliese and Danko, Kristen and Mavergames, Chris and Taylor, Mark and Donoghue, Emma and Maxwell, Lara J. and Thayer, Kris and Dressler, Corinna and McAuley, James and Thomas, James and Egan, Cathy and McDonald, Steve and Tritton, Roger and Tsafnat, Guy and Elliott, Sarah A. and Meerpohl, Joerg and Tugwell, Peter and Etxeandia, Itziar and Merner, Bronwen and Turgeon, Alexis and Featherstone, Robin and Mondello, Stefania and Turner, Tari and Foxlee, Ruth and Morley, Richard and van Valkenhoef, Gert and Garner, Paul and Munafo, Marcus and Vandvik, Per and Gerrity, Martha and Munn, Zachary and Wallace, Byron and Glasziou, Paul and Murano, Melissa and Wallace, Sheila A. and Green, Sally and Newman, Kristine and Watts, Chris and Grimshaw, Jeremy and Nieuwlaat, Robby and Weeks, Laura and Gurusamy, Kurinchi and Nikolakopoulou, Adriani and Weigl, Aaron and Haddaway, Neal and Noel-Storr, Anna and Wells, George and Hartling, Lisa and O'Connor, Annette and Wiercioch, Wojtek and Hayden, Jill and Page, Matthew and Wolfenden, Luke and Helfand, Mark and Pahwa, Manisha and Nuñez, Juan José Yepes and Higgins, Julian and Pardo, Jordi Pardo and Yost, Jennifer and Hill, Sophie and Pearson, Leslea},
  biburl = {https://www.bibsonomy.org/bibtex/24074c664eb3bd7cd659219ff5ce9e145/fordham1},
  description = {Living systematic reviews: 3. Statistical methods for updating meta-analyses - Journal of Clinical Epidemiology},
  doi = {10.1016/j.jclinepi.2017.08.008},
  interhash = {cb639b960b073e9a2100297526000d62},
  intrahash = {4074c664eb3bd7cd659219ff5ce9e145},
  issn = {0895-4356, 1878-5921},
  journal = {Journal of Clinical Epidemiology},
  keywords = {meta_analysis},
  pages = {38-46},
  publisher = {Elsevier},
  timestamp = {2021-02-24T15:54:29.000+0100},
  title = {Living systematic reviews: 3. Statistical methods for updating meta-analyses},
  type = {Article},
  url = {https://www.jclinepi.com/article/S0895-4356(17)30601-7/fulltext#articleInformation},
  volume = 91,
  year = 2017
}

Downloads: 0