Bayesian adaptive design of early-phase clinical trials for precision medicine based on cancer biomarkers.

Shinjo Yada

doi:10.1515/ijb-2021-0009

Abstract

Cancer tissue samples obtained via biopsy or surgery were examined for specific gene mutations by genetic testing to inform treatment. Precision medicine, which considers not only the cancer type and location, but also the genetic information, environment, and lifestyle of each patient, can be applied for disease prevention and treatment in individual patients. The number of patient-specific characteristics, including biomarkers, has been increasing with time; these characteristics are highly correlated with outcomes. The number of patients at the beginning of early-phase clinical trials is often limited. Moreover, it is challenging to estimate parameters of models that include baseline characteristics as covariates such as biomarkers. To overcome these issues and promote personalized medicine, we propose a dose-finding method that considers patient background characteristics, including biomarkers, using a model for phase I/II oncology trials. We built a Bayesian neural network with input variables of dose, biomarkers, and interactions between dose and biomarkers and output variables of efficacy outcomes for each patient. We trained the neural network to select the optimal dose based on all background characteristics of a patient. Simulation analysis showed that the probability of selecting the desirable dose was higher using the proposed method than that using the naïve method.

Highlights

Cancer is treated according to its type and location in the body, such as lung, breast, gastric, and colorectal cancers
Cancer tissue samples obtained via biopsy or surgery were examined for specific gene mutations by genetic testing to inform treatment
Cancer tissue samples obtained via biopsy or surgery are normally examined for the presence of specific gene mutations by genetic testing

Summary

Introduction

Cancer is treated according to its type and location in the body, such as lung, breast, gastric, and colorectal cancers. For the trial design and method to personalize dose finding, Chen et al [10] proposed an outcome weighted learning approach for a nonconvex loss function to estimate the optimal individualized dose (IDR) They claimed that the proposed method could be applied to infer the IDR, including accounting for drug toxicity, and that it could reveal potential biomarkers influencing the IDR. Kakurai et al [13] proposed a dose-finding method that considers multiple genes and selects the individualized optimal dose for each patient by simultaneously performing variable selection and parameter estimation using Bayesian least absolute shrinkage and selection operator (Bayesian LASSO) They supposed that the responses were efficacy and toxicity expression. The Bayesian neural network model learned from the patient data and selected the most probable optimal dose level for each patient based on the predicted results obtained using the learned network model

Network model

Trial design

Simulation settings

Simulation results

Discussion