|
Activity Number:
|
243
- Operational Considerations in Clinical Trials
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 9, 2022 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #322133
|
|
|
Title:
|
Statistical Comparison of Waterfall Plots in Oncology Drug Development
|
|
Author(s):
|
Mo Huang* and Linda Sun and Cong Chen
|
|
Companies:
|
Merck & Co., Inc. and Merck & Co, Inc. and Merck & Co., Inc.
|
|
Keywords:
|
Waterfall plot;
Oncology;
Clinical trials;
Drug development
|
|
Abstract:
|
Waterfall plots have gained popularity as a visualization tool to present anti-tumor activity of treatments in oncology, especially for Phase I and II trials. The typical waterfall plot in oncology is a bar plot with each bar representing the best percent tumor size reduction from baseline for a subject sorted in descending order along the x-axis. As new therapies are routinely developed in combination with standard of care (SOC) or other investigational treatments, waterfall plot comparison between combination therapy and monotherapy may facilitate development decisions earlier than using ORR or PFS. However, waterfall plots are often assessed heuristically in practice with lack of statistical rigor. In this work, we examine the correspondence between the waterfall plot and the empirical cumulative distribution function (eCDF). Using real examples from published waterfall plots, we demonstrate how to apply and interpret well-established statistical methods for eCDFs (and survival functions in time-to-event analysis) in the analysis and visualization of waterfall plots.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2022 program
|
