Article Text

Download PDFPDF
Implementing hierarchical network meta-analysis incorporating exchangeable dose effects compared to standard hierarchical network meta-analysis
  1. Jennifer Watt1,2,3,
  2. Mark Hofmeister4,
  3. Cinzia Del Giovane5,6,
  4. Rebecca Turner7,
  5. Andrea C Tricco1,3,
  6. Dimitris Mavridis8,
  7. Sharon Straus1,2,3,
  8. Areti Angeliki Veroniki1,3
  1. 1 Knowledge Translation Program, St. Michael's Hospital, Toronto, Ontario, Canada
  2. 2 Geriatric Medicine, University of Toronto, Toronto, Ontario, Canada
  3. 3 Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada
  4. 4 O’Brien Institute of Public Health, University of Calgary, Calgary, Alberta, Canada
  5. 5 Institute of Primary Health Care (BIHAM), University of Bern, Bern, Switzerland
  6. 6 Department of Medical and Surgical Sciences for Children and Adults, University-Hospital of Modena and Reggio Emilia, Modena, Italy
  7. 7 MRC Clinical Trials Unit, University College London, London, UK
  8. 8 Department of Primary Education, University of Ioannina, Ioannina, Greece
  1. Correspondence to Dr Jennifer Watt, Unity Health Toronto, Toronto, ON M5B 1W8, Canada; jennifer.watt{at}

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.


Network meta-analysis (NMA) compares the efficacy or safety of more than two treatments or treatment doses that are directly or indirectly compared through a common comparator.1 2 Treatment doses are not routinely incorporated into NMAs, which potentially limits the applicability and validity of results.3 4 In this paper, we will introduce readers to NMA incorporating dose effects, specifically, how they can implement a hierarchical random effects NMA incorporating exchangeable dose effects. In particular, we share a motivating clinical example describing the comparative risk of vomiting associated with different cholinesterase inhibitor doses (ie, donepezil, galantamine and rivastigmine) and use this example to illustrate (1) key similarities and differences between the standard NMA and NMA incorporating exchangeable dose effects; (2) why incorporating dose effects in NMA is important; (3) steps to follow when completing a systematic review with NMA incorporating dose effects; (4) results derived from a hierarchical random effects NMA incorporating exchangeable dose effects and how they will facilitate clinical decision-making and (5) how to consider potential dose effects when evaluating NMA relevance and credibility. Please refer to our companion publication for a more in depth theoretical discussion of hierarchical NMA models incorporating dose effects and alternative NMA models incorporating dose effects.5

Motivating clinical example

Clinicians prescribe cholinesterase inhibitors (ie, donepezil, galantamine and rivastigmine) to slow cognitive decline in people with dementia.4 Cholinesterase inhibitors are associated with potential side effects, including headaches, nausea and vomiting.4 5 Understanding if certain cholinesterase inhibitor doses are associated with a higher risk of side effects than others could inform, or even change, clinical decision-making. To describe potential dose effects, we used a subset of data from a published systematic review with NMA describing treatment level risk of vomiting associated with cholinesterase inhibitor use (see online supplemental table 1 for dataset).4 We implemented …

View Full Text


  • Twitter @JennAnnWatt

  • Contributors JW, MH, SS and AAV conceptualised the study. JW, CDG, RT, DM and AAV contributed to model creation. JW performed all analyses. JW, ACT, SS and AAV supported data duration. JW drafted the first version of the manuscript and is the guarantor of this article. All authors reviewed and edited the manuscript.

  • Funding ACT is funded by a Tier 2 Canada Research Chair in Knowledge Synthesis. SES is funded by a Tier 1 Canada Research Chair in Knowledge Translation. RMT is supported by the UK Medical Research Council (grant No MC_UU_00004/06).

  • Competing interests All authors have completed the ICMJE uniform disclosure form and declare: no support from any organisation for the submitted work; no financial relationships with any organisations that might have an interest in the submitted work in the previous 3 years and no other relationships or activities that could appear to have influenced the submitted work. AAV is on the editorial board of BMJ Evidence Based Medicine but was not involved with the peer review process or decision to publish.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.