Novel Approaches for Dynamic Visualization of Adverse Event Data in Oncology Clinical Trials: A Case Study Using Immunotherapy Trial S1400-I (SWOG)

Abstract

PURPOSE Clinical trial adverse event (AE) data are increasingly complex and high-dimensional, especially for trials evaluating novel targeted agents and immunotherapies. Standard approaches to summarize and analyze AEs remain generally tabular, failing to describe the nature of AEs. Novel dynamic and data visualization methods are needed to enable a more comprehensive assessment of the overall toxicity profile of treatments. METHODS We developed methods for visualizing the numerous categorizations and types of AEs along with a dynamic approach to better reflect its highly dimensional nature without sacrificing the reporting of rare events. Circular plots displaying the proportion of maximal-grade AEs by system organ classes (SOCs) and butterfly plots displaying the proportion of AEs by severity for each AE term were developed to enable comparisons of AE patterns by treatment arm. These approaches were applied to a randomized phase III trial (S1400I; ClinicalTrials.gov identifier: NCT02785952 ) comparing nivolumab with nivolumab plus ipilimumab in patients with stage IV squamous non–small-cell lung cancer. RESULTS Our visualizations revealed that patients randomly assigned to nivolumab and ipilimumab had higher rates of grade 3 or higher AEs compared with nivolumab alone for several SOCs, including musculoskeletal (5.6% v 0.8%), skin (5.6% v 0.8%), vascular (5.6% v 1.6%), and cardiac (4% v 1.6%) toxicities. They also suggested a pattern of higher prevalence of moderate GI and endocrine toxicities and showed that although the rates of cardiac and neurologic toxicities were similar, the types of events were discordant. CONCLUSION The graphical approaches we proposed enable a more comprehensive and intuitive evaluation of toxicity types by treatment groups, which is not apparent in tabular and descriptive reporting methods.