Browsing by Subject "functional data analysis"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item Open Access Deep learning for the dynamic prediction of multivariate longitudinal and survival data.(Statistics in medicine, 2022-03-28) Lin, Jeffrey; Luo, ShengThe 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.Item Open Access Dynamic prediction of Alzheimer's disease progression using features of multiple longitudinal outcomes and time-to-event data.(Statistics in medicine, 2019-10) Li, Kan; Luo, ShengThis paper is motivated by combining serial neurocognitive assessments and other clinical variables for monitoring the progression of Alzheimer's disease (AD). We propose a novel framework for the use of multiple longitudinal neurocognitive markers to predict the progression of AD. The conventional joint modeling longitudinal and survival data approach is not applicable when there is a large number of longitudinal outcomes. We introduce various approaches based on functional principal component for dimension reduction and feature extraction from multiple longitudinal outcomes. We use these features to extrapolate the health outcome trajectories and use scores on these features as predictors in a Cox proportional hazards model to conduct predictions over time. We propose a personalized dynamic prediction framework that can be updated as new observations collected to reflect the patient's latest prognosis, and thus intervention could be initiated in a timely manner. Simulation studies and application to the Alzheimer's Disease Neuroimaging Initiative dataset demonstrate the robustness of the method for the prediction of future health outcomes and risks of target events under various scenarios.Item Open Access Prognostic Modeling of Parkinson's Disease Progression Using Early Longitudinal Patterns of Change.(Movement disorders : official journal of the Movement Disorder Society, 2021-07-30) Ren, Xuehan; Lin, Jeffrey; Stebbins, Glenn T; Goetz, Christopher G; Luo, ShengBackground
Predicting Parkinson's disease (PD) progression may enable better adaptive and targeted treatment planning.Objective
Develop a prognostic model using multiple, easily acquired longitudinal measures to predict temporal clinical progression from Hoehn and Yahr (H&Y) stage 1 or 2 to stage 3 in early PD.Methods
Predictive longitudinal measures of PD progression were identified by the joint modeling method. Measures were extracted by multivariate functional principal component analysis methods and used as covariates in Cox proportional hazards models. The optimal model was developed from the Parkinson's Progression Marker Initiative (PPMI) data set and confirmed with external validation from the Longitudinal and Biomarker Study in PD (LABS-PD) study.Results
The proposed prognostic model with longitudinal information of selected clinical measures showed significant advantages in predicting PD temporal progression in comparison to a model with only baseline information (iAUC = 0.812 vs. 0.743). The modeling results allowed the development of a prognostic index for categorizing PD patients into low, mid, and high risk of progression to HY 3 that is offered to facilitate physician-patient discussion on prognosis.Conclusion
Incorporating longitudinal information of multiple clinical measures significantly enhances predictive performance of prognostic models. Furthermore, the proposed prognostic index enables clinicians to classify patients into different risk groups, which could be adaptively updated as new longitudinal information becomes available. Modeling of this type allows clinicians to utilize observational data sets that inform on disease natural history and specifically, for precision medicine, allows the insertion of a patient's clinical data to calculate prognostic estimates at the individual case level. © 2021 International Parkinson and Movement Disorder Society.