MRI-Based Alzheimer’s Disease-Resemblance Atrophy Index in the Detection of Preclinical and Prodromal Alzheimer’s Disease

Abstract Background: We aimed to validate the performance of an MRI-based machine learning derived Alzheimer’s Disease-resemblance atrophy index (AD-RAI) in detecting preclinical and prodromal AD. Methods: A total of 62 subjects (mild cognitive impairment [MCI]=25, cognitively unimpaired [CU]=37) underwent MRI, 11C- PIB, and 18F-T807 PET. We investigated the performance of AD-RAI at the pre-specified cutoff of ≥ 0.5 in detecting preclinical and prodromal AD and compared its performance with that of visual and volumetric hippocampal measures. Results: AD-RAI achieved the best metrics among all subjects (sensitivity 0.73, specificity 0.91, accuracy 87.10%) and among MCI subgroup (sensitivity 0.91, specificity 0.79, accuracy 84.00%) in detecting A+T+ subjects over other measures. Among CU subgroup, hippocampal volume (sensitivity 0.75, specificity 0.88, accuracy 86.49%) achieved a higher sensitivity than AD-RAI (sensitivity 0.25, specificity 0.97, accuracy 89.19%) in detecting preclinical AD.Conclusions: AD-RAI aids the detection of early AD, in particular at the prodromal stage.