B0309
Title: Dynamic survival prediction with sparse longitudinal images via multi-dimensional FPCA
Authors: Haolun Shi - Simon Fraser University (Canada) [presenting]
Abstract: The motivation is to predict the progression of Alzheimer's disease (AD) based on a series of longitudinally observed brain scan images. Existing works on dynamic prediction for AD focus primarily on extracting predictive information from multivariate longitudinal biomarker values or brain imaging data at the baseline; whereas in practice, the subject's brain scan image represented by a multi-dimensional data matrix is collected at each follow-up visit. It is of great interest to predict the progression of AD directly from a series of longitudinally observed images. A novel multi-dimensional functional principal component analysis is proposed based on alternating regression on tensor-product B-spline, which circumvents the computational difficulty of doing eigendecomposition and offers the flexibility of accommodating sparsely and irregularly observed image series. The functional principal component scores are then used as features in the Cox proportional hazards model. A dynamic prediction framework is further developed to provide a personalized prediction that can be updated as new images are collected. The method extracts visibly interpretable images of the functional principal components and offers an accurate prediction of the conversion to AD. The effectiveness of the method is examined via simulation studies and its application is illustrated on the Alzheimer's disease neuroimaging initiative data.
