Progression along data-driven disease timelines is predictive of Alzheimer's disease in a population-based cohort

Aug 28, 2026

Data-driven disease progression models have clarified timelines of brain changes across Alzheimer’s disease (AD) phenotypes, yet their ability to predict progression of pre-symptomatic AD in population-based cohorts remains unclear. This study tested whether APOE-stratified disease timelines trained in a case-controlled setting generalize to the Rotterdam Study, using structural MRI biomarkers and co-initialized discriminative event-based modeling. Disease stage estimates and stage change rates were evaluated for diagnostic and prognostic value against clinical outcomes.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Abstract

Introduction

Methods and Modeling

Results and Evaluation

Conclusions

Delft University of Technology Progression along data-driven disease timelines is predictive of Alzheimer's disease in a population-based cohort Venkatraghavan, Vikram; Vinke, Elisabeth J. ; Bron, Esther E. ; Niessen, Wiro J. ; Arfan Ikram, M. ; Klein, Stefan; Vernooij, Meike W. DOI 10.1016/j.neuroimage.2021.118233 Publication date 2021 Document Version Final published version Published in NeuroImage Citation (APA) Venkatraghavan, V. , Vinke, E. J. , Bron, E. E. , Niessen, W. J. , Arfan Ikram, M. , Klein, S. , & Vernooij, M. W.(2021) . Progression along data-driven disease timelines is predictive of Alzheimer's disease in a populationbased cohort. NeuroImage, 238, Article 118233. [https://doi.org/10.1016/j.neuroimage.2021.118233](https://doi.org/10.1016/j.neuroimage.2021.118233) Important note To cite this publication, please use the final published version (if applicable) . Please check the document version above. Copyright Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons. Takedown policy Please contact us and provide details if you believe this document breaches copyrights. We will remove access to the work immediately and investigate your claim. This work is downloaded from Delft University of Technology. For technical reasons the number of authors shown on this cover page is limited to a maximum of 10. NeuroImage 238 (2021) 118233 Contents lists available at ScienceDirect NeuroImage journal [homepage:](homepage: www.elsevier.com/locate/neuroimage)[ www.elsevier.com/locate/neuroimage](homepage: www.elsevier.com/locate/neuroimage) | Progression along data-driven disease timelines is predictive of Alzheimer’s disease in a population-based cohort
Vikram Venkatraghavana,1, Elisabeth J. Vinkea,c,1, Esther E. Brona, Wiro J. Niessen a,b, M. Arfan Ikram c, Stefan Klein a,2, Meike W. Vernooija,c,2,∗ , for the Alzheimer’s Disease Neuroimaging Initiative\#
a Department of Radiology & Nuclear Medicine, Erasmus MC, University Medical Center Rotterdam, The Netherlands
b Quantitative Imaging Group, Dept. of Imaging Physics, Faculty of Applied Sciences, Delft University of Technology, Delft, The Netherlands c Department of Epidemiology, Erasmus MC, University Medical Center Rotterdam, The Netherlands | | | | | --- | --- | --- | --- | | a r t i c l e i n f o | | a b s t r a c t | | | Keywords:
Disease progression modeling Event-based model Alzheimer’s disease
APOE
Population study | | Data-driven disease progression models have provided important insight into the timeline of brain changes in AD phenotypes. However, their utility in predicting the progression of pre-symptomatic AD in a populationbased setting has not yet been investigated. In this study, we investigated if the disease timelines constructed in a case-controlled setting, with subjects stratiﬁed according to APOE status, are generalizable to a populationbased cohort, and if progression along these disease timelines is predictive of AD. Seven volumetric biomarkers derived from structural MRI were considered. We estimated APOE-speciﬁc disease timelines of changes in these biomarkers using a recently proposed method called co-initialized discriminative event-based modeling (co-init DEBM). This method can also estimate a disease stage for new subjects by calculating their position along the disease timelines. The model was trained and cross-validated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, and tested on the population-based Rotterdam Study (RS) cohort. We compared the diagnostic and prognostic value of the disease stage in the two cohorts. Furthermore, we investigated if the rate of change of disease stage in RS participants with longitudinal MRI data was predictive of AD. In

FAQs

What question does the study address about disease timelines in Alzheimer’s disease?

It evaluates whether data-driven disease timelines constructed in a case-controlled setting, stratified by APOE status, can be generalized to a population-based cohort and whether progression along these timelines predicts AD development.

What biomarkers and modeling approach are used?

Seven volumetric biomarkers derived from structural MRI are used, and APOE-specific disease timelines are estimated with co-initialized discriminative event-based modeling (co-init DEBM), which can also infer disease stage for new subjects.

How is predictive performance assessed across cohorts?

The diagnostic and prognostic value of estimated disease stage is compared between the ADNI dataset (training and cross-validation) and the Rotterdam Study cohort (testing), including whether the rate of change in disease stage predicts pre-symptomatic AD.

Aug 28, 2026

Upload by 8796093062539