AUTHOR=Gautherot Morgan , Kuchcinski Grégory , Bordier Cécile , Sillaire Adeline Rollin , Delbeuck Xavier , Leroy Mélanie , Leclerc Xavier , Pruvo Jean-Pierre , Pasquier Florence , Lopes Renaud 

TITLE=Longitudinal Analysis of Brain-Predicted Age in Amnestic and Non-amnestic Sporadic Early-Onset Alzheimer's Disease

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 13 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2021.729635

DOI=10.3389/fnagi.2021.729635

ISSN=1663-4365

ABSTRACT=Objective: Predicted age difference (PAD) is a score computed by subtracting chronological age from ‘brain’ age, which is estimated using neuroimaging data. The goal of this study was to evaluate the PAD as a marker of phenotypic heterogeneity and severity within early-onset Alzheimer disease (EOAD) patients. 
Methods: We first used 3D T1-weighted (3DT1) magnetic resonance images (MRI) of 3227 healthy subjects aged from 18 to 85 years to train, optimize and evaluate the brain age model. 123 participants meeting criteria for early-onset (< 65 years) sporadic form of probable Alzheimer’s disease and presenting with two distinctive clinical presentation (an amnestic (n=74) and a non-amnestic forms (n=49)) were included at baseline and followed-up for a maximum of 4 years. All of the participants underwent a work-up at baseline and every year during the follow-up period, which includes: clinical examination, neuropsychological testing, genotyping and structural MRI and cerebrospinal fluid biomarker assays only at baseline. PAD score was calculated by applying brain age model to 3DT1 images of the EOAD patients and healthy controls matched for age and sex. At baseline, between-group differences for neuropsychological and PAD scores were assessed using linear models. Regarding longitudinal analysis of neuropsychological and PAD scores, differences between amnestic and non-amnestic participants were analyzed using linear mixed-effects modeling. 
Results: PAD score was significantly higher for non-amnestic patients (2.35±0.91) than amnestic patients (2.09±0.74) and controls (0.00 ± 1). Regardless of the clinical presentation, PAD scores were positively correlated with cognition. They were correlated with the Mini Mental State Examination (MMSE) and the Clinical Dementia Rating sum of boxes (CDR-SB). Longitudinal analyses showed that the gradual development of the patient’s disease was accompanied by a significant increase in PAD score over time for both amnestic and non-amnestic patients. 
Conclusion: PAD score was able to separate amnestic and non-amnestic sporadic forms. Regardless of the clinical presentation, as PAD score was a way of quantifying an early brain age acceleration, it was an appropriate method to detect the development of AD and follow the evolution of the disease as a marker of severity as MMSE and CDR-SB.