Enrollment Forecast for Clinical Trials at the Portfolio Planning Phase Based on Site-Level Historical Data

TL;DR

This paper introduces a Bayesian generalized linear mixed-effects model for more accurate clinical trial enrollment forecasting, capturing nonlinear patterns and providing detailed predictive insights to improve planning and execution.

Contribution

The paper presents a novel Bayesian GLMM approach using non-homogeneous Poisson processes for improved enrollment prediction accuracy over traditional methods.

Findings

Significant improvement in prediction accuracy compared to traditional models

Proper calibration of data variability and coverage rates

Effective generation of enrollment curves with confidence bands

Abstract

Accurate forecast of a clinical trial enrollment timeline at the planning phase is of great importance to both corporate strategic planning and trial operational excellence. While predictions of key milestones such as last subject first dose date can inform strategic decision-making, detailed predictive insights (e.g., median number of enrolled subjects by month for a country) can facilitate the planning of clinical trial operation activities and promote execution excellence. The naive approach often calculates an average enrollment rate from historical data and generates an inaccurate prediction based on a linear trend with the average rate. The traditional statistical approach utilizes the simple Poisson-Gamma model that assumes time-invariant site activation rates and it can fail to capture the underlying nonlinear patterns (e.g., up and down site activation pattern). We present a novel statistical approach based on generalized linear mixed-effects models and the use of non-homogeneous Poisson processes through Bayesian framework to model the country initiation, site activation and subject enrollment sequentially in a systematic fashion. We validate the performance of our proposed enrollment modeling framework based on a set of preselected 25 studies from four therapeutic areas. Our modeling framework shows a substantial improvement in prediction accuracy in comparison to the traditional statistical approach. Furthermore, we show that our modeling and simulation approach calibrates the data variability appropriately and gives correct coverage rates for prediction intervals of various nominal levels. Finally, we demonstrate the use of our approach to generate the predicted enrollment curves through time with confidence bands overlaid.