Statistical modeling and prediction of clinical trial recruitment

Yu Lan, Gong Tang, Daniel F Heitjan

Research output: Contribution to journalArticle

Abstract

Real-time prediction of clinical trial accrual can support logistical planning, ensuring that studies meet but do not exceed sample size targets. We describe a novel, simulation-based prediction method that is founded on a realistic model for the underlying processes of recruitment. The model reflects key features of enrollment such as the staggered initiation of new centers, heterogeneity in enrollment capacity, and declining accrual within centers. The model's first stage assumes that centers join the trial (ie, initiate accrual) according to an inhomogeneous Poisson process in discrete time. The second part assumes that each center's enrollment pattern reflects an early plateau followed by a slow decline, with a burst at the end of the trial following the announcement of an imminent closing date. By summing up achieved and projected enrollment, one can predict accrual as a function of time and, thereby, the time when the trial will achieve a planned enrollment target. We applied our method retrospectively to two real-world trials: NSABP B-38 and REMATCH (Randomized Evaluation of Mechanical Assistance for the Treatment of Congestive Heart Failure). In both studies, the proposed method produced prediction intervals for time to completion that were more accurate than those from conventional predictions that assume a constant rate of enrollment, estimated either from the entire trial to date or over a recent time window. The advantage is substantial in the early stages of NSABP B-38. We conclude that a method based on a realistic accrual model offers improved accuracy in the prediction of enrollment landmarks, especially at the early stages of large trials that involve many centers.

Original languageEnglish (US)
JournalStatistics in Medicine
DOIs
Publication statusAccepted/In press - Jan 1 2018

    Fingerprint

Keywords

  • Bayesian
  • center initiation
  • enrollment
  • marginal likelihood

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this