A prognostic model of Alzheimer's disease relying on multiple longitudinal measures and time-to-event data.


INTRODUCTION:Characterizing progression in Alzheimer's disease is critically important for early detection and targeted treatment. The objective was to develop a prognostic model, based on multivariate longitudinal markers, for predicting progression-free survival in patients with mild cognitive impairment. METHODS:The information contained in multiple longitudinal markers was extracted using multivariate functional principal components analysis and used as predictors in the Cox regression models. Cross-validation was used for selecting the best model based on Alzheimer's Disease Neuroimaging Initiative-1. External validation was conducted on Alzheimer's Disease Neuroimaging Initiative-2. RESULTS:Model comparison yielded a prognostic index computed as the weighted combination of historical information of five neurocognitive longitudinal markers that are routinely collected in observational studies. The comprehensive validity analysis provided solid evidence of the usefulness of the model for predicting Alzheimer's disease progression. DISCUSSION:The prognostic model was improved by incorporating multiple longitudinal markers. It is useful for monitoring disease and identifying patients for clinical trial recruitment.





Published Version (Please cite this version)


Publication Info

Li, Kan, Richard O'Brien, Michael Lutz, Sheng Luo and undefined Alzheimer's Disease Neuroimaging Initiative (2018). A prognostic model of Alzheimer's disease relying on multiple longitudinal measures and time-to-event data. Alzheimer's & dementia : the journal of the Alzheimer's Association, 14(5). pp. 644–651. 10.1016/j.jalz.2017.11.004 Retrieved from https://hdl.handle.net/10161/19150.

This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.



Richard J O'Brien

Disque D. Deane University Distinguished Professor of Neurology

Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.