Browsing by Subject "joint model"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ItemOpen Access
    Deep learning for the dynamic prediction of multivariate longitudinal and survival data.
    (Statistics in medicine, 2022-03-28) Lin, Jeffrey; Luo, Sheng
    The joint model for longitudinal and survival data improves time-to-event predictions by including longitudinal outcome variables in addition to baseline covariates. However, in practice, joint models may be limited by parametric assumptions in both the longitudinal and survival submodels. In addition, computational difficulties arise when considering multiple longitudinal outcomes due to the large number of random effects to be integrated out in the full likelihood. In this article, we discuss several recent machine learning methods for incorporating multivariate longitudinal data for time-to-event prediction. The presented methods use functional data analysis or convolutional neural networks to model the longitudinal data, both of which scale well to multiple longitudinal outcomes. In addition, we propose a novel architecture based on the transformer neural network, named TransformerJM, which jointly models longitudinal and time-to-event data. The prognostic abilities of each model are assessed and compared through both simulation and real data analysis on Alzheimer's disease datasets. Specifically, the models were evaluated based on their ability to dynamically update predictions as new longitudinal data becomes available. We showed that TransformerJM improves upon the predictive performance of existing methods across different scenarios.
  • Thumbnail Image
    ItemOpen Access
    Functional survival forests for multivariate longitudinal outcomes: Dynamic prediction of Alzheimer's disease progression.
    (Statistical methods in medical research, 2020-07-29) Lin, Jeffrey; Li, Kan; Luo, Sheng
    The random survival forest (RSF) is a non-parametric alternative to the Cox proportional hazards model in modeling time-to-event data. In this article, we developed a modeling framework to incorporate multivariate longitudinal data in the model building process to enhance the predictive performance of RSF. To extract the essential features of the multivariate longitudinal outcomes, two methods were adopted and compared: multivariate functional principal component analysis and multivariate fast covariance estimation for sparse functional data. These resulting features, which capture the trajectories of the multiple longitudinal outcomes, are then included as time-independent predictors in the subsequent RSF model. This non-parametric modeling framework, denoted as functional survival forests, is better at capturing the various trends in both the longitudinal outcomes and the survival model which may be difficult to model using only parametric approaches. These advantages are demonstrated through simulations and applications to the Alzheimer's Disease Neuroimaging Initiative.
  • Thumbnail Image
    ItemOpen Access
    Joint Analyses of Longitudinal and Time-to-Event Data in Research on Aging: Implications for Predicting Health and Survival.
    (Front Public Health, 2014) Arbeev, Konstantin G; Akushevich, Igor; Kulminski, Alexander M; Ukraintseva, Svetlana V; Yashin, Anatoliy I
    Longitudinal data on aging, health, and longevity provide a wealth of information to investigate different aspects of the processes of aging and development of diseases leading to death. Statistical methods aimed at analyses of time-to-event data jointly with longitudinal measurements became known as the "joint models" (JM). An important point to consider in analyses of such data in the context of studies on aging, health, and longevity is how to incorporate knowledge and theories about mechanisms and regularities of aging-related changes that accumulate in the research field into respective analytic approaches. In the absence of specific observations of longitudinal dynamics of relevant biomarkers manifesting such mechanisms and regularities, traditional approaches have a rather limited utility to estimate respective parameters that can be meaningfully interpreted from the biological point of view. A conceptual analytic framework for these purposes, the stochastic process model of aging (SPM), has been recently developed in the biodemographic literature. It incorporates available knowledge about mechanisms of aging-related changes, which may be hidden in the individual longitudinal trajectories of physiological variables and this allows for analyzing their indirect impact on risks of diseases and death. Despite, essentially, serving similar purposes, JM and SPM developed in parallel in different disciplines with very limited cross-referencing. Although there were several publications separately reviewing these two approaches, there were no publications presenting both these approaches in some detail. Here, we overview both approaches jointly and provide some new modifications of SPM. We discuss the use of stochastic processes to capture biological variation and heterogeneity in longitudinal patterns and important and promising (but still largely underused) applications of JM and SPM to predictions of individual and population mortality and health-related outcomes.