Partially linear Bayesian modeling of longitudinal rank and time-to-event data using accelerated failure time model...

Area of Science:

• Biostatistics
• Survival Analysis
• Longitudinal Data Analysis

Background:

• Accelerated Failure Time (AFT) models are crucial for analyzing time-to-event data, estimating covariate effects on survival.
• Parametric AFT models necessitate specifying event time distributions, which can be challenging in real-world applications.
• Existing semiparametric AFT models offer flexibility but may not fully capture complex relationships.

Purpose of the Study:

• To develop a flexible joint modeling framework for longitudinal rank and time-to-event data.
• To extend Accelerated Failure Time (AFT) models to accommodate nonlinear effects and time-dependent covariates.
• To implement a Bayesian approach for robust parameter estimation and uncertainty quantification.

Main Methods:

• A Bayesian approach is employed for joint modeling, incorporating random effects.
• The study proposes a flexible extension of the Accelerated Failure Time (AFT) model, including partially linear models.
• Methods address nonlinear effects of time on longitudinal responses and time-dependent covariate effects on hazard.

Main Results:

• Simulation studies demonstrate the model's capability to accurately estimate parameters.
• The developed joint model was successfully applied to a real-world dataset of brain tumor patients.
• The analysis provided insights into the relationship between longitudinal measures and survival outcomes in the patient cohort.

Conclusions:

• The proposed Bayesian joint modeling approach offers a flexible and robust method for analyzing complex longitudinal and time-to-event data.
• This methodology enhances survival analysis by accounting for nonlinear and time-dependent effects, improving upon traditional AFT models.
• The application to brain tumor data highlights the model's practical utility in clinical research and patient outcome prediction.