Investigating the temporal pattern of neuroimaging-based brain age estimation as a biomarker for Alzheimer's Disease related neurodegeneration

• DOI: 10.1016/j.neuroimage.2022.119621
• Publication Date: 2022-09-09T07:16:22Z
• Authors: Alexei Taylor; Fengqing Zhang; Xin Niu; Ashley Heywood; Jane Stocks; Gangyi Feng; Karteek Popuri; Mirza Faisal Beg; Lei Wang
• Keywords: Cognitive Decline; Apolipoprotein E; Neurophysiology

Neuroimaging-based brain-age estimation via machine learning has emerged as an important new approach for studying brain aging. The difference between one's estimated age and chronological age, the gap (BAG), been proposed Alzheimer's Disease (AD) biomarker. However, most past studies on BAG have cross-sectional. Quantifying longitudinal changes in individual's temporal pattern would likely improve prediction of AD progression clinical outcome based neurophysiological changes. To fill this gap, our study conducted predictive modeling using a large neuroimaging dataset with up to 8 years follow-up examine patterns BAG's trajectory how it varies by subject-level characteristics (sex, APOEɛ4 carriership) disease status. Specifically, we explored rate change over time individuals who remain stable normal cognition or mild cognitive impairment (MCI), well progress AD. Combining multimodal imaging data support vector regression model estimate yielded improved performance single modality. Multilevel results showed followed linear increasing significantly faster MCI progressed compared cognitively did not progress. dynamic during were further moderated sex carriership. Our findings demonstrate potential biomarker understanding individual specific related progression.