Related Experiment Video
Updated: Sep 9, 2025

A Clinical Trial Assessing the Safety, Efficacy, and Delivery of Olive-Oil-Based Three-Chamber Bags for Parenteral Nutrition
Published on: September 20, 2019
A randomization strategy for a cluster-randomized controlled trial with variable operating room availability
Sheau-Chiann Chen1, Heidi Chen1, Rafael Paez2
1Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA.
Abstract:
A single-center, open-label, pragmatic, non-inferiority, cluster randomized controlled trial was conducted to compare the clinical outcomes of two diagnostic bronchoscopy approaches, Platform A and Platform B. A cluster was defined as an operating room (OR) day. The expected allocation ratio at the cluster level was 1:1 between Platform A and Platform B. The resources available for this trial included one Platform A, one Platform B, two ORs available for two days a week, and one OR available for the other three days. When one platform was randomly assigned to one OR, the other platform was placed in the other OR. Due to limitations in OR and bronchoscopy platform availability precluding individual patient randomization, a stratification strategy was proposed to randomize ORs to a given platform. A simulation with 1000 replicates was performed to assess balance of assignments, using imbalance (defined as the difference/imbalance in the number of patients enrolled between Platform A and Platform B) and its standard deviation as evaluation metrics. At day 150 (210 assignments), a permuted-block randomization method, incorporating stratification by weekdays, reduced both imbalance and variation (mean = 0.044, standard deviation (SD) = 1.110, median = 0, range = (-4, 4)), compared to a permuted-block randomization method (mean = -0.238, SD = 7.064, median = 0, range = (-24, 22)). We further explored an alternative strategy: stratification by OR availability. This evaluation analysis revealed a greater reduction in imbalance, with a range of -2 and 2 (mean = -0.006, SD = 0.690, median = 0). Our innovative study designs, incorporating a permuted-block randomization method stratified by OR availability, effectively reduced the imbalance assignments and optimized allocation of resources. Trial registration ClinicalTrials.gov registration (NCT05705544) for RELIANT on January 30, 2023. ClinicalTrials.gov registration (NCT06654271) for RELIANT 2 on January 12, 2024.
More Related Videos
Related Concept Videos
Randomized Experiments
Simple randomization
Simple...
Group Design
Cluster Sampling Method
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
Blinding
Odds Ratio
Crossover Experiments
Crossover designs are performed even with smaller sample sizes since the samples can act as their controls. These are better than simple randomized trials since patients are exposed to all the treatments.

