Dataset Information

A new randomization procedure based on multiple covariates and applicable to parallel studies with simultaneous enrollment of all subjects prior to intervention.

ABSTRACT:

Background

Parallel intervention studies involving volunteers usually require a procedure to allocate the subjects to study-arms. Statistical models to evaluate the different outcomes of the study-arms will include study-arm as a factor along with any covariate that might affect the results. To ensure that the effects of the covariates are confounded to the least possible extent with the effects of the arms, stratified randomization can be applied. However, there is at present no clear-cut procedure when there are multiple covariates.

Methods

For parallel study designs with simultaneous enrollment of all subjects prior to intervention, we propose a D-optimal blocking procedure to allocate subjects with known values of the covariates to the study arms. We prove that the procedure minimizes the variances of the baseline differences between the arms corrected for the covariates. The procedure uses standard statistical software.

Results

We demonstrate the potential of the method by an application to a human parallel nutritional intervention trial with three arms and 162 healthy volunteers. The covariates were gender, age, body mass index, an initial composite health score, and a categorical indicator called first-visit group, defining groups of volunteers who visit the clinical centre on the same day (17 groups). Volunteers were allocated equally to the study-arms by the D-optimal blocking procedure. The D-efficiency of the model connecting an outcome with the study-arms and correcting for the covariates equals 99.2%. We simulated 10,000 random allocations of subjects to arms either unstratified or stratified by first-visit group. Intervals covering the middle 95% of the D-efficiencies for these allocations were [82.0, 92.0] and [93.2, 98.4], respectively.

Conclusions

Allocation of volunteers to study-arms with a D-optimal blocking procedure with the values of the covariates as inputs substantially improves the efficiency of the statistical model that connects the response with the study arms and corrects for the covariates.

Trial registration

Dutch Trial Register NL7054 ( NTR7259 ). Registered May 15, 2018.

SUBMITTER: Schoen ED

PROVIDER: S-EPMC7469365 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A new randomization procedure based on multiple covariates and applicable to parallel studies with simultaneous enrollment of all subjects prior to intervention.

Schoen Eric D ED Wopereis Suzan S

BMC medical research methodology 20200903 1

<h4>Background</h4>Parallel intervention studies involving volunteers usually require a procedure to allocate the subjects to study-arms. Statistical models to evaluate the different outcomes of the study-arms will include study-arm as a factor along with any covariate that might affect the results. To ensure that the effects of the covariates are confounded to the least possible extent with the effects of the arms, stratified randomization can be applied. However, there is at present no clear-c ...[more]

PMID: 32883212

Similar Datasets

Project description:BACKGROUND:Outcomes of surgical trials hinge on surgeon selection and their underlying expertise. Assessment of expertise is paramount. We investigated whether surgeons' performance measured by the fundamentals of laparoscopic surgery (FLS) assessment program could predict their performance in a surgical trial. METHODS:As part of a prospective multi-institutional study of minimally invasive inguinal lymphadenectomy (MILND) for melanoma, surgical oncologists with no prior MILND experience underwent pre-trial FLS assessment. Surgeons completed MILND training, began enrolling patients, and submitted videos of each MILND case performed. Videos were scored with the global operative assessment of laparoscopic skills (GOALS) tool. Associations between baseline FLS scores and participant's trial performance metrics were assessed. RESULTS:Twelve surgeons enrolled patients; their median total baseline FLS score was 332 (range 275-380, max possible 500, passing >270). Participants enrolled 87 patients in the study (median 6 per surgeon, range 1-24), of which 72 (83%) videos were adequate for scoring. Baseline GOALS score was 17.1 (range 9.6-21.2, max possible score 30). Inter-rater reliability was excellent (ICC = 0.85). FLS scores correlated with improved GOALS scores (r = 0.57, p = 0.05) and with decreased operative time (r = -0.6, p = 0.02). No associations were found with the degree of patient recruitment (r = 0.02, p = 0.7), lymph node count (r = 0.01, p = 0.07), conversion rate (r = -0.06, p = 0.38) or major complications(r = -0.14, p = 0.6). CONCLUSIONS:FLS skill assessment of surgeons prior to their enrollment in a surgical trial is feasible. Although better FLS scores predicted improved operative performance and operative time, other trial outcome measures showed no difference. Our findings have implications for the documentation of laparoscopic expertise of surgeons in practice and may allow more appropriate selection of surgeons to participate in clinical trials.

Dataset Information

A new randomization procedure based on multiple covariates and applicable to parallel studies with simultaneous enrollment of all subjects prior to intervention.

Background

Methods

Results

Conclusions

Trial registration

Publications

A new randomization procedure based on multiple covariates and applicable to parallel studies with simultaneous enrollment of all subjects prior to intervention.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets