Search

Dynamic prediction methods incorporate longitudinal biomarker information to produce updated, more accurate predictions of conditional survival probability. There are two approaches for obtaining dynamic predictions: (1) a joint model of the longitudinal marker and survival process, and (2) an approximate approach that specifies a model for a specific component of the joint distribution. In the case of a binary marker, an illness‐death model is an example of a joint modeling approach that is unified and produces consistent predictions. However, previous literature has shown that approximate approaches, such as landmarking, with additional flexibility can have good predictive performance. One such approach proposes using a Gaussian copula to model the joint distribution of conditional continuous marker and survival distributions. It has the advantage of specifying established, flexible models for the marginals for which goodness‐of‐fit can be assessed, and has easy estimation that can be implemented in standard software. In this article, we provide a Gaussian copula approach for dynamic prediction to accommodate a binary marker using a continuous latent variable formulation. We compare the predictive performance of this approach to joint modeling and landmarking using simulations and demonstrate its use for obtaining dynamic predictions in an application to a prostate cancer study. [ABSTRACT FROM AUTHOR]

Biomarkers are often measured over time in epidemiological studies and clinical trials for better understanding of the mechanism of diseases. In large cohort studies, case-cohort sampling provides a cost effective method to collect expensive biomarker data for revealing the relationship between biomarker trajectories and time to event. However, biomarker measurements are often limited by the sensitivity and precision of a given assay, resulting in data that are censored at detection limits and prone to measurement errors. Additionally, the occurrence of an event of interest may preclude biomarkers from being further evaluated. Inappropriate handling of these types of data can lead to biased conclusions. Under a classical case cohort design, we propose a modified likelihood-based approach to accommodate these special features of longitudinal biomarker measurements in the accelerated failure time models. The maximum likelihood estimators based on the full likelihood function are obtained by Gaussian quadrature method. We evaluate the performance of our case-cohort estimator and compare its relative efficiency to the full cohort estimator through simulation studies. The proposed method is further illustrated using the data from a biomarker study of sepsis among patients with community acquired pneumonia. [ABSTRACT FROM AUTHOR]