Progression along data-driven disease timelines is predictive of Alzheimer's disease in a population-based cohort
NeuroImage , Volume 238
Data-driven disease progression models have provided important insight into the timeline of brain changes in<br/>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<br/>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<br/>derived from structural MRI were considered. We estimated APOE-specific disease timelines of changes in these<br/>biomarkers using a recently proposed method called co-initialized discriminative event-based modeling (co-init<br/>DEBM). This method can also estimate a disease stage for new subjects by calculating their position along the<br/>disease timelines. The model was trained and cross-validated on the Alzheimer’s Disease Neuroimaging Initiative<br/>(ADNI) dataset, and tested on the population-based Rotterdam Study (RS) cohort. We compared the diagnostic<br/>and prognostic value of the disease stage in the two cohorts. Furthermore, we investigated if the rate of change of<br/>disease stage in RS participants with longitudinal MRI data was predictive of AD. In ADNI, the estimated disease<br/>timeslines for 𝜖4 non-carriers and carriers were found to be significantly different from one another (𝑝 < 0.001).<br/>The estimate disease stage along the respective timelines distinguished AD subjects from controls with an AUC<br/>of 0.83 in both APOE 𝜖4 non-carriers and carriers. In the RS cohort, we obtained an AUC of 0.83 and 0.85 in 𝜖4<br/>non-carriers and carriers, respectively. Progression along the disease timelines as estimated by the rate of change<br/>of disease stage showed a significant difference (𝑝 < 0.005) for subjects with pre-symptomatic AD as compared to<br/>the general aging population in RS. It distinguished pre-symptomatic AD subjects with an AUC of 0.81 in APOE<br/>𝜖4 non-carriers and 0.88 in carriers, which was better than any individual volumetric biomarker, or its rate of<br/>change, could achieve. Our results suggest that co-init DEBM trained on case-controlled data is generalizable to a<br/>population-based cohort setting and that progression along the disease timelines is predictive of the development<br/>of AD in the general population. We expect that this approach can help to identify at-risk individuals from the<br/>general population for targeted clinical trials as well as to provide biomarker based objective assessment in such<br/>trials.