Centralized statistical monitoring of clinical trial enrollment performance. Issue 4 (1st October 2020)

• Record Type: Journal Article
• Authors: Anisimov, Vladimir; Austin, Matthew
• Is Part Of: Communication in statistics. Volume 6:Issue 4(2020)
• Page Start: 392
• Page End: 410
• Publication Date: 2020-10-01
• Subjects: Clinical trial -- modeling enrollment -- statistical monitoring -- Poisson-gamma model -- interim performance; Mathematical statistics -- Data processing -- Periodicals; 519.505
• DOI: 10.1080/23737484.2020.1758240
• Languages: English
• ISSNs: 2373-7484

Abstract

Abstract: A novel analytic methodology for centralized statistical monitoring of the clinical trial interim enrollment performance is developed. The underlying technique uses a Poisson-gamma (PG) enrollment model developed by Anisimov and Fedorov in the previous publications. This technique is extended to modeling clinical centers performance and detecting outliers (low and high enrolling centers) using interim enrollment data and different approaches ( P -values, 2D-classification). To analyze country/region performance, a new technique based on the approximation of the enrollment process in country/region by a PG process with aggregated parameters is developed. The developed methodology is applied to the analysis of the interim enrollment performance of a real clinical trial. The results support the efficiency of using this methodology in monitoring of various enrollment characteristics.