Estimation of Patient Recruitment Using Summary Data Aggregated Across Trials

Accurate modeling of patient recruitment is critical for helping ensure operational efficiency of clinical trials. However, current methods to estimate key model parameters typically require granular center-level data, which can be challenging to obtain. We propose using summary-level data aggregated from publicly available historical trials to help ameliorate these problems. Specifically, we introduce an estimation framework that estimates Poisson-Gamma model parameters of phase III trials by leveraging data from multiple public trials using a maximum likelihood approach. Our framework has desirable theoretical properties in the objective function, which facilitate solution development. Finally, we demonstrate that our approach can accurately estimate model parameters in both simulations and real data case studies of hypertension and type 2 diabetes trials from ClinicalTrials.gov.

History: Accepted by Paul Brooks, Area Editor for Applications in Biology, Medicine, & Healthcare.

Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information (https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2024.0780) as well as from the IJOC GitHub software repository (https://github.com/INFORMSJoC/2024.0780). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/.