Individualized survival predictions using state space model with longitudinal and survival data

J R Soc Interface. 2024 Jul;21(216):20230682. doi: 10.1098/rsif.2023.0682. Epub 2024 Jul 31.

Abstract

Monitoring disease progression often involves tracking biomarker measurements over time. Joint models (JMs) for longitudinal and survival data provide a framework to explore the relationship between time-varying biomarkers and patients' event outcomes, offering the potential for personalized survival predictions. In this article, we introduce the linear state space dynamic survival model for handling longitudinal and survival data. This model enhances the traditional linear Gaussian state space model by including survival data. It differs from the conventional JMs by offering an alternative interpretation via differential or difference equations, eliminating the need for creating a design matrix. To showcase the model's effectiveness, we conduct a simulation case study, emphasizing its performance under conditions of limited observed measurements. We also apply the proposed model to a dataset of pulmonary arterial hypertension patients, demonstrating its potential for enhanced survival predictions when compared with conventional risk scores.

Keywords: expectation maximization algorithm; joint model; longitudinal data; pulmonary arterial hypertension; state space model; survival data.

MeSH terms

  • Humans
  • Longitudinal Studies
  • Models, Statistical*
  • Survival Analysis