Skip to content
Preprint · OA via OpenAlex

Disentangling Alzheimer's disease neurodegeneration from typical brain aging using machine learning

Gyujoon Hwang, Ahmed Abdulkadir, Güray Erus, Mohamad Habes, Raymond Pomponio, Haochang Shou, Jimit J. Doshi, Elizabeth Mamourian, Tanweer Rashid, Murat Bilgel, Yong Fan A, Aristeidis Sotiras, Dhivya Srinivasan, John C. Morris, Daniel S. Marcus

arXiv (Cornell University) · 2021

Abstract

Neuroimaging biomarkers that distinguish between typical brain aging and Alzheimer's disease (AD) are valuable for determining how much each contributes to cognitive decline. Machine learning models can derive multi-variate brain change patterns related to the two processes, including the SPARE-AD (Spatial Patterns of Atrophy for Recognition of Alzheimer's Disease) and SPARE-BA (of Brain Aging) investigated herein. However, substantial overlap between brain regions affected in the two processes confounds measuring them independently. We present a methodology toward disentangling the two. T1-weighted MRI images of 4,054 participants (48-95 years) with AD, mild cognitive impairment (MCI), or cognitively normal (CN) diagnoses from the iSTAGING (Imaging-based coordinate SysTem for AGIng and NeurodeGenerative diseases) consortium were analyzed. First, a subset of AD patients and CN adults were selected based purely on clinical diagnoses to train SPARE-BA1 (regression of age using CN individuals) and SPARE-AD1 (classification of CN versus AD). Second, analogous groups were selected based on clinical and molecular markers to train SPARE-BA2 and SPARE-AD2: amyloid-positive (A+) AD continuum group (consisting of A+AD, A+MCI, and A+ and tau-positive CN individuals) and amyloid-negative (A-) CN group. Finally, the combined group of the AD continuum and A-/CN individuals was used to train SPARE-BA3, with the intention to estimate brain age regardless of AD-related brain changes. Disentangled SPARE models derived brain patterns that were more specific to the two types of the brain changes. Correlation between the SPARE-BA and SPARE-AD was significantly reduced. Correlation of disentangled SPARE-AD was non-inferior to the molecular measurements and to the number of APOE4 alleles, but was less to AD-related psychometric test scores, suggesting contribution of advanced brain aging to these scores.

◌ CITATION ONLY
Full text is not openly licensed for redistribution here. Read it at the source:

Read at source →

Provenance

Source
OpenAlex
DOI
10.48550/arxiv.2109.03723
Canonical
link ↗
Fetched
2026-10-16 MST

Cite this

APA
Hwang, G., Abdulkadir, A., Erus, G., Habes, M., Pomponio, R., Shou, H., Doshi, J.J., Mamourian, E., Rashid, T., Bilgel, M., A, Y.F., Sotiras, A., Srinivasan, D., Morris, J.C., Marcus, D.S., Albert, M., Bryan, R.N., Resnick, S.M., Nasrallah, I.M., &amp; Davatzikos, C.A. (2021). Disentangling Alzheimer's disease neurodegeneration from typical brain aging using machine learning. <em>arXiv (Cornell University)</em>. https://doi.org/10.48550/arxiv.2109.03723
Vancouver
Hwang G, Abdulkadir A, Erus G, Habes M, Pomponio R, Shou H, et al. Disentangling Alzheimer's disease neurodegeneration from typical brain aging using machine learning. arXiv (Cornell University). 2021. doi:10.48550/arxiv.2109.03723.
BibTeX
@unpublished{gyujoon2021Disent, title = {Disentangling Alzheimer's disease neurodegeneration from typical brain aging using machine learning}, author = {Gyujoon Hwang and Ahmed Abdulkadir and Güray Erus and Mohamad Habes and Raymond Pomponio and Haochang Shou and Jimit J. Doshi and Elizabeth Mamourian and Tanweer Rashid and Murat Bilgel and Yong Fan A and Aristeidis Sotiras and Dhivya Srinivasan and John C. Morris and Daniel S. Marcus and Marilyn Albert and Robert Nick Bryan and Susan M. Resnick and Ilya M. Nasrallah and Christos A. Davatzikos and David A. Wolk}, journal = {arXiv (Cornell University)}, year = {2021}, doi = {10.48550/arxiv.2109.03723}, }

Research neighborhood

References, citing works, and semantically nearest findings. Click a node to open it.

Related findings