A Bayesian group sequential schema for ordinal endpoints

TL;DR

This paper introduces a Bayesian group sequential framework for ordinal endpoints in clinical trials, addressing a gap in design methods for such data with flexible models and supporting software.

Contribution

It proposes a novel Bayesian group sequential design for ordinal endpoints, including PO, NPO, and switch models, with extensive simulations and an R package.

Findings

Demonstrates desirable performance through simulations

Provides a flexible framework for various ordinal endpoint scenarios

Includes an R package for practical implementation

Abstract

The ordinal endpoint is prevalent in clinical studies. For example, for the COVID-19, the most common endpoint used was 7-point ordinal scales. Another example is in phase II cancer studies, efficacy is often assessed as an ordinal variable based on a level of response of solid tumors with four categories: complete response, partial response, stable disease, and progression, though often a dichotomized approach is used in practices. However, there lack of designs for the ordinal endpoint despite Whitehead et al. (1993, 2017), Jaki et al. (2003) to list a few. In this paper, we propose a generic group sequential schema based on Bayesian methods for ordinal endpoints, including three methods, the proportional-odds-model (PO)-based, non-proportional-odds-model (NPO)-based, and PO/NPO switch-model-based designs, which makes our proposed methods generic to be able to deal with various scenarios. We conducted extensive simulations to demonstrate the desirable performances of the proposed method and an R package BayesOrdDesign has also been developed.