Dynamic Changes in Quantitative MRI-based Biomarkers of Alzheimer’s Disease and Its Association with Cognitive Decline – A Longitudinal Study

Alzheimer's disease (AD) resemblance atrophy index (AD-RAI) is a novel MRI-based machine-learning derived imaging biomarker for AD that is valid in detection of early AD. We selected 318 CU and MCI subjects in ADNI with four-year follow-up with 1471 serial MRI scans to assess longitudinal changes of the MRI biomarkers (i.e., AD-RAI, HV, HF, BPV, BPF) in correlation with the change in time and conversion status. We used generalized linear mixed-effects models to compute and show the predictive value. AD-RAI over time showed the highest classification accuracy for predicting converters when compared with other imaging biomarkers.