A New Method to Model and Predict Progression Free Survival Based on Tumor Growth Dynamics

Abstract

Progression‐free survival (PFS) has been increasingly used as a primary endpoint for early clinical development. The aim of the present work was to develop a model where target lesion dynamics and risk for nontarget progression are jointly modeled for predicting PFS. The model was developed based on a pooled platinum‐resistant ovarian cancer dataset comprising four different treatments and a wide range of dose levels. The target lesion progression was derived from tumor growth dynamics based on the Response Evaluation Criteria in Solid Tumors (RECIST) criteria. The nontarget progression hazard was correlated to the first derivative of target lesion tumor size with respect to time. The PFS time was determined by the first occurring event, target lesion progression, or nontarget progression. The final joint model not only captured target lesion tumor growth dynamics but also predicted PFS well. A similar approach can potentially be used to predict PFS in future oncology studies.

Modelling the association between biomarkers and clinical outcome: An introduction to nonlinear joint models

“…Joint model predictions can identify most-at-risk individuals, 2,15,53 in a perspective of personalized medicine, or for early decision making based on observation of the biomarker kinetics. 54,55 Let us assume that the biomarker is observed until a given landmark time s at which the patient is alive, and the aim is to predict patient biomarker kinetics and the risk of death at the horizon time s þ t, i.e. formally, to calculate:…”

“…Joint model predictions can identify most‐at‐risk individuals, 2,15,53 in a perspective of personalized medicine, or for early decision making based on observation of the biomarker kinetics 54,55 …”

Opportunities for Quantitative Translational Modeling in Oncology

“…Promising efforts are under way to combine qualitative longitudinal data on nontarget lesions and new lesions with target lesion data to improve outcome predictions. 59 Moreover, incorporating biomarker responses in tumor kinetic modeling has the potential to resolve the pharmacological variability of different response types in order to better predict the duration of response. 60 Despite some progress, longitudinal tumor size models tend to be agnostic of mechanism of action (MoA).…”

Model‐based prediction of progression‐free survival for combination therapies in oncology

“…Such models have previously been investigated and tested with several different monotherapies. 20,21 In recent decades, large amounts of data have been gathered in oncology, where advances in, for example, single-cell technologies, and decreased sequencing costs have enabled the generation of large amounts of molecular data. 22,23 Machine learning (ML) is a popular approach for analyzing such high-dimensional data, 24 and has been used in oncology to for example, estimate the correlation between covariates and individual parameters, or PFS time, using methods such as RandomForest and LASSO.…”

“…25,26 In this paper, we have three aims. First, to extend the model-based PFS prediction described by Yu et al 21 to combination therapies. This is accomplished by joining a tumor growth inhibition (TGI) model to a time-to-event (TTE) model for non-target progression (NTP).…”