The optimal design of clinical trials with potential biomarker effects: A novel computational approach

Abstract

As a future trend of healthcare, personalized medicine tailors medical treatments to individual patients. It requires to identify a subset of patients with the best response to treatment. The subset can be defined by a biomarker (eg, expression of a gene) and its cutoff value. Topics on subset identification have received massive attention. There are over two million hits by keyword searches on Google Scholar. However, designing clinical trials that utilize the discovered uncertain subsets/biomarkers is not trivial and rarely discussed in the literature. This leads to a gap between research results and real-world drug development. To fill in this gap, we formulate the problem of clinical trial design into an optimization problem involving high-dimensional integration, and propose a novel computational solution based on Monte Carlo and smoothing methods. Our method utilizes the modern techniques of general purpose computing on graphics processing units for large-scale parallel computing. Compared to a published method in three-dimensional problems, our approach is more accurate and 133 times faster. This advantage increases when dimensionality increases. Our method is scalable to higher dimensional problems since the precision bound of our estimated study power is a finite number not affected by dimensionality. To design clinical trials incorporating the potential biomarkers, users can use our software "DesignCTPB". This software can be found on Github and will be available as an R package on CRAN. Although our research is motivated by the design of clinical trials, the method can be used widely to solve other optimization problems involving high-dimensional integration.

A Vector Theory of Assessing Clinical Trials: An Application to Bioequivalence

“…Similar efforts by scientists in the field have also appeared in the literature. For example, in a recent study, the problem of clinical trial design is reformulated as an optimization challenge, integrating high-dimensional aspects [66]. In that study, the authors introduced a computational approach using Monte Carlo and smoothing techniques to address it.…”

“…In that study, the authors introduced a computational approach using Monte Carlo and smoothing techniques to address it. Their method uses modern techniques of general-purpose computing on graphics processing units for large-scale parallel computing [66]. In another quite recent study, the endpoints of Phase 2 and Phase 3 trials are examined within a combined 2-in-1 design [67].…”

Machine Learning Models for the Identification of Prognostic and Predictive Cancer Biomarkers: A Systematic Review

“…The strategies for utilizing an individual's distinct clinical, genomic, genetic, and environmental data to guide decisions about disease prevention, diagnosis, and treatment are evolving at an exponential rate [1]. Personalized medicine allows for therapies to be administered to the subsets of patients with the best responses based upon on their individual features, and furthermore, the use of personalized biomarkers can enable pharmaceutical firms to improve the likelihood of success in their clinical studies [2]. To identify the subset of patients who would benefit from a treatment, biomarkers are becoming more important in personalized medicine, whether for prognosis, prediction, or dosage selection.…”

A New Model Selection Metric for Biomarker Detection Algorithms and Tools

“…Existing solutions focus on optimizing design for the biomarker-based drug clinical trial. Placing two hypotheses on the entire population and biomarker-positive groups can diversify risk [13]. 2 in 1 adaptive design can determine whether to conduct a phase 2/3 seamless clinical trial based on the phase 2 result [14,15].…”