Related Experiment Video
Updated: Sep 8, 2025

An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Multi-stage dose expansion cohort (MSDEC) design with Bayesian stopping rule
1Department of Biostatistics, Bioinformatics and Biomathematics, Georgetown University, Washington, DC, United States.
This study introduces a novel hybrid frequentist-Bayesian design for Phase I trials, enhancing safety by reducing patient exposure to toxic doses. The multi-stage dose-expansion cohort (MSDEC) design improves maximum tolerated dose (MTD) determination.
Area of Science:
- Clinical Trial Design
- Biostatistics
- Pharmacology
Background:
- Phase I trials commonly use algorithm-based (e.g., 3+3) or model-based (e.g., CRM) designs to find the maximum tolerated dose (MTD).
- The traditional 3+3 design is widely used for its simplicity, but it may lack accuracy in MTD determination, especially with limited patient numbers.
- Dose-expansion cohorts (DEC) are increasingly employed to better define toxicity profiles of novel agents.
Purpose of the Study:
- To propose a novel multi-stage dose-expansion cohort (MSDEC) hybrid frequentist-Bayesian design for Phase I clinical trials.
- To enhance the safety and accuracy of MTD determination in early-phase drug development.
- To integrate historical data effectively using a power prior within a Bayesian framework.
Main Methods:
- The MSDEC design combines a power prior for modeling historical dose-escalation data with a sequential conditional probability ratio test for safety monitoring.
- A Bayesian stopping rule is developed for safety monitoring.
- Maximum sample size is determined using a fixed-sample-size test with exact binomial computation.
Main Results:
- Simulation studies indicate that the MSDEC design effectively reduces the probability of patients receiving toxic doses.
- The power prior allows objective weighting of historical data, reducing reliance on subjective expert opinion for Bayesian model parameterization.
- The hybrid approach balances the strengths of frequentist and Bayesian methodologies for robust dose-finding.
Conclusions:
- The proposed MSDEC design offers a safer and potentially more accurate approach to MTD determination in Phase I trials compared to traditional methods.
- The use of power prior in a Bayesian context provides a data-driven and flexible way to incorporate historical information.
- This hybrid design represents a significant advancement in optimizing early-phase clinical trial methodology for novel therapeutics.
Related Concept Videos
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.
Dosage Regimen: Fixed Dose
Fixed-dose regimens can be used for various routes of administration, including intravenous (IV) injections and oral medications. For IV administration, a predetermined amount of the drug is...
Dose-Response Relationship: Overview
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Study Design in Statistics
Does aspirin reduce the risk of heart attacks? Is one brand of fertilizer more effective at growing roses than another? Is fatigue as dangerous to a driver as the influence of alcohol? Questions like these are answered using randomized experiments with proper...
Dose-Response Relationship: Selectivity and Specificity

