# Improving phase II oncology trials using best observed RECIST response as an endpoint by modelling continuous tumour measurements

## TL;DR

This paper introduces an extension of the augmented binary method to improve the analysis of best observed RECIST responses in phase II oncology trials, significantly increasing statistical power by modeling continuous tumor measurements.

## Contribution

The paper develops a novel statistical approach that extends existing methods to better utilize best observed responses, enhancing power in phase II cancer trial analyses.

## Key findings

- Method improves power by approximately 35% over traditional analysis.
- Simulation and real data demonstrate increased efficiency in single-arm and randomized trials.
- Modified version reduces computational effort while maintaining efficiency.

## Abstract

In many phase II trials in solid tumours, patients are assessed using endpoints based on the Response Evaluation Criteria in Solid Tumours (RECIST) scale. Often, analyses are based on the response rate. This is the proportion of patients who have an observed tumour shrinkage above a pre-defined level and no new tumour lesions. The augmented binary method has been proposed to improve the precision of the estimator of the response rate. The method involves modelling the tumour shrinkage to avoid dichotomising it. However, in many trials the best observed response is used as the primary outcome. In such trials, patients are followed until progression, and their best observed RECIST outcome is used as the primary endpoint. In this paper, we propose a method that extends the augmented binary method so that it can be used when the outcome is best observed response. We show through simulated data and data from a real phase II cancer trial that this method improves power in both single-arm and randomised trials. The average gain in power compared to the traditional analysis is equivalent to approximately a 35% increase in sample size. A modified version of the method is proposed to reduce the computational effort required. We show this modified method maintains much of the efficiency advantages.