Evaluating brain age as a marker of autosomal dominant Alzheimer disease progression

Abstract

AbstractBackgroundEstimates of “brain‐predicted age” quantify apparent brain age compared to normative trajectories of neuroimaging features. Brain‐predicted age is elevated in sporadic Alzheimer disease (AD), but is underexplored in autosomal dominant AD (ADAD). We used a previously‐trained model (DeepBrainNet [DBN], Bashyam et al., 2020), which requires minimal MRI pre‐processing, to predict brain age in the Dominantly Inherited Alzheimer Network (DIAN) and evaluated brain age as a marker of ADAD progression.MethodWe used DBN to predict brain age from minimally‐processed, whole‐brain T1 structural MRI scans in 265 ADAD mutation‐carriers (MCs) and 183 non‐carrier controls (NCs). We then tested whether the brain age gap (BAG; difference between predicted and true age) differed as a function of mutation and cognitive status, or estimated years until symptom onset (EYO), and whether it was associated with established markers of amyloid (PiB PET, CSF amyloid‐ß‐42/40), phosphorylated tau (CSF and plasma pTau‐181), neurodegeneration (CSF and plasma neurofilament light [NFL]), and cognition (global neuropsychological composite and CDR‐sum of boxes). Finally, we compared BAG to other MRI measures, and examined heterogeneity in BAG as a function of mutation variants (APP vs. PSEN1 before or after codon 200), APOE E4 carrier status, sex, and education.ResultDBN accurately predicted age in DIAN (Figure 1A). BAG was elevated in symptomatic and asymptomatic MCs, compared to NCs, beginning around ‐10 EYO (Figure 1B,C). BAG, hippocampal volume, and a cortical thickness summary followed similar trajectories across EYO (Figure 1D). BAG was positively associated with PiB PET, CSF and plasma pTau, and CSF and plasma NFL, and was associated with worse cognitive scores, especially in symptomatic MCs (Figure 2). BAG was most elevated in MCs with a PSEN1 mutation before codon 200, but did not differ as a function of APOE, sex, or education (Figure 3).ConclusionWe extend prior work using BAG from sporadic AD to ADAD, noting consistent results. BAG tracks well with markers of pTau, neurodegeneration, and cognition, but to a lesser extent, amyloid, in ADAD. BAG may capture similar signal to established MRI measures. However, DBN‐based BAG offers unique benefits in simplicity of data processing and interpretation.