Improved Dynamic Predictions from Joint Models of Longitudinal and Survival Data with Time-Varying Effects using P-splines

TL;DR

This paper introduces a Bayesian joint modeling approach with P-splines to allow time-varying effects in predicting survival outcomes based on longitudinal data, specifically applied to valve function monitoring after cardio-thoracic surgery.

Contribution

It develops a novel Bayesian joint model incorporating P-splines for time-varying effects, enhancing dynamic prediction accuracy in medical longitudinal-survival data.

Findings

Improved discrimination and calibration of survival predictions.

Effective modeling of changing biomarker-survival associations over time.

Validated approach in a clinical setting for valve function monitoring.

Abstract

In the field of cardio-thoracic surgery, valve function is monitored over time after surgery. The motivation for our research comes from a study which includes patients who received a human tissue valve in the aortic position. These patients are followed prospectively over time by standardized echocardiographic assessment of valve function. Loss of follow-up could be caused by valve intervention or the death of the patient. One of the main characteristics of the human valve is that its durability is limited. Therefore, it is of interest to obtain a prognostic model in order for the physicians to scan trends in valve function over time and plan their next intervention, accounting for the characteristics of the data. Several authors have focused on deriving predictions under the standard joint modeling of longitudinal and survival data framework that assumes a constant effect for the coefficient that links the longitudinal and survival outcomes. However, in our case this may be a restrictive assumption. Since the valve degenerates, the association between the biomarker with survival may change over time. To improve dynamic predictions we propose a Bayesian joint model that allows a time-varying coefficient to link the longitudinal and the survival processes, using P-splines. We evaluate the performance of the model in terms of discrimination and calibration, while accounting for censoring.