The hunt for efficient, incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measures
Abstract Background We consider the design of stepped wedge trials with continuous recruitment and continuous outcome measures. Suppose we recruit from a fixed number of clusters where eligible participants present continuously, and suppose we have fine control over when each cluster crosses to the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-11-01
|
| Series: | BMC Medical Research Methodology |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12874-020-01155-z |
| _version_ | 1818529795305111552 |
|---|---|
| author | Richard Hooper Jessica Kasza Andrew Forbes |
| author_facet | Richard Hooper Jessica Kasza Andrew Forbes |
| author_sort | Richard Hooper |
| collection | DOAJ |
| description | Abstract Background We consider the design of stepped wedge trials with continuous recruitment and continuous outcome measures. Suppose we recruit from a fixed number of clusters where eligible participants present continuously, and suppose we have fine control over when each cluster crosses to the intervention. Suppose also that we want to minimise the number of participants, leading us to consider “incomplete” designs (i.e. without full recruitment). How can we schedule recruitment and cross-over at different clusters to recruit efficiently while achieving good precision? Methods The large number of possible designs can make exhaustive searches impractical. Instead we consider an algorithm using iterative improvements to hunt for an efficient design. At each iteration (starting from a complete design) a single participant – the one with the smallest impact on precision – is removed, and small changes preserving total sample size are made until no further improvement in precision can be found. Results Striking patterns emerge. Solutions typically focus recruitment and cross-over on the leading diagonal of the cluster-by-time diagram, but in some scenarios clusters form distinct phases resembling before-and-after designs. Conclusions There is much to be learned about optimal design for incomplete stepped wedge trials. Algorithmic searches could offer a practical approach to trial design in complex settings generally. |
| first_indexed | 2024-12-11T17:11:31Z |
| format | Article |
| id | doaj.art-2280a24f605940c5afb0536fc1c8ac42 |
| institution | Directory Open Access Journal |
| issn | 1471-2288 |
| language | English |
| last_indexed | 2024-12-11T17:11:31Z |
| publishDate | 2020-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj.art-2280a24f605940c5afb0536fc1c8ac422022-12-22T00:57:30ZengBMCBMC Medical Research Methodology1471-22882020-11-012011910.1186/s12874-020-01155-zThe hunt for efficient, incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measuresRichard Hooper0Jessica Kasza1Andrew Forbes2Queen Mary University of LondonMonash UniversityMonash UniversityAbstract Background We consider the design of stepped wedge trials with continuous recruitment and continuous outcome measures. Suppose we recruit from a fixed number of clusters where eligible participants present continuously, and suppose we have fine control over when each cluster crosses to the intervention. Suppose also that we want to minimise the number of participants, leading us to consider “incomplete” designs (i.e. without full recruitment). How can we schedule recruitment and cross-over at different clusters to recruit efficiently while achieving good precision? Methods The large number of possible designs can make exhaustive searches impractical. Instead we consider an algorithm using iterative improvements to hunt for an efficient design. At each iteration (starting from a complete design) a single participant – the one with the smallest impact on precision – is removed, and small changes preserving total sample size are made until no further improvement in precision can be found. Results Striking patterns emerge. Solutions typically focus recruitment and cross-over on the leading diagonal of the cluster-by-time diagram, but in some scenarios clusters form distinct phases resembling before-and-after designs. Conclusions There is much to be learned about optimal design for incomplete stepped wedge trials. Algorithmic searches could offer a practical approach to trial design in complex settings generally.http://link.springer.com/article/10.1186/s12874-020-01155-zAlgorithmsCluster randomised trialsContinuous recruitmentEfficient designStepped wedge trials |
| spellingShingle | Richard Hooper Jessica Kasza Andrew Forbes The hunt for efficient, incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measures BMC Medical Research Methodology Algorithms Cluster randomised trials Continuous recruitment Efficient design Stepped wedge trials |
| title | The hunt for efficient, incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measures |
| title_full | The hunt for efficient, incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measures |
| title_fullStr | The hunt for efficient, incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measures |
| title_full_unstemmed | The hunt for efficient, incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measures |
| title_short | The hunt for efficient, incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measures |
| title_sort | hunt for efficient incomplete designs for stepped wedge trials with continuous recruitment and continuous outcome measures |
| topic | Algorithms Cluster randomised trials Continuous recruitment Efficient design Stepped wedge trials |
| url | http://link.springer.com/article/10.1186/s12874-020-01155-z |
| work_keys_str_mv | AT richardhooper thehuntforefficientincompletedesignsforsteppedwedgetrialswithcontinuousrecruitmentandcontinuousoutcomemeasures AT jessicakasza thehuntforefficientincompletedesignsforsteppedwedgetrialswithcontinuousrecruitmentandcontinuousoutcomemeasures AT andrewforbes thehuntforefficientincompletedesignsforsteppedwedgetrialswithcontinuousrecruitmentandcontinuousoutcomemeasures AT richardhooper huntforefficientincompletedesignsforsteppedwedgetrialswithcontinuousrecruitmentandcontinuousoutcomemeasures AT jessicakasza huntforefficientincompletedesignsforsteppedwedgetrialswithcontinuousrecruitmentandcontinuousoutcomemeasures AT andrewforbes huntforefficientincompletedesignsforsteppedwedgetrialswithcontinuousrecruitmentandcontinuousoutcomemeasures |