Statistical Frameworks for Oncology Dose-Finding Designs with Late-Onset Toxicities: A Review

TL;DR

This review discusses statistical frameworks for dose-finding in oncology trials with late-onset toxicities, focusing on time-to-event models, design classes, theoretical properties, and practical implementation.

Contribution

It categorizes existing designs into TITE and POD classes, introduces computational algorithms, and compares their performance through simulations.

Findings

TITE and POD design classes encompass existing and new methods.

Theoretical properties such as convergence and coherence are analyzed.

Simulation studies compare design operating characteristics.

Abstract

In oncology dose-finding trials, due to staggered enrollment, it might be desirable to make dose-assignment decisions in real-time in the presence of pending toxicity outcomes, for example, when the dose-limiting toxicity is late-onset. Patients' time-to-event information may be utilized to facilitate such decisions. We review statistical frameworks for time-to-event modeling in dose-finding trials and summarize existing designs into two classes: TITE designs and POD designs. TITE designs are based on inference on toxicity probabilities, while POD designs are based on inference on dose-finding decisions. These two classes of designs contain existing individual designs as special cases and also give rise to new designs. We discuss and study the theoretical properties of these designs, including large-sample convergence properties, coherence principles, and the underlying decision rules. To facilitate the use of these designs in practice, we introduce efficient computational algorithms and review common practical considerations, such as safety rules and suspension rules. Finally, the operating characteristics of several designs are evaluated and compared through computer simulations.