Rethinking the residual approach: leveraging statistical learning to operationalize cognitive resilience in Alzheimer’s disease

Cognitive resilience (CR) describes the phenomenon of individuals evading cognitive decline despite prominent Alzheimer's disease neuropathology. Operationalization and measurement of this latent construct is non-trivial as it cannot be directly observed. The residual approach has been widely applied to estimate CR, where the degree of resilience is estimated through a linear model's residuals. We demonstrate that this approach makes specific, uncontrollable assumptions and likely leads to biased and erroneous resilience estimates. This is especially true when information about CR is contained in the data the linear model was fitted to, either through inclusion of CR-associated variables or due to correlation. We propose an alternative strategy which overcomes the standard approach's limitations using machine learning principles. Our proposed approach makes fewer assumptions about the data and CR and achieves better estimation accuracy on simulated ground-truth data.

Authors

Institutions

Publication Details

Journal
Brain Informatics
Published
2025-01-27
DOI
https://doi.org/10.1186/s40708-024-00249-4
Citations
3
Primary Topic
Dementia and Cognitive Impairment Research
Type
article
Field-Weighted Citation Impact
4.41

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Rethinking the residual approach: leveraging statistical learning to operationalize cognitive resilience in Alzheimer’s disease

Susan M. Resnick, Oliver Langford, Aaron P. Schultz, Timothy J. Hohman et al.
3 citations
Brain Informatics
Dementia and Cognitive Impairment Research
4.41
article

Rethinking the residual approach: leveraging statistical learning to operationalize cognitive resilience in Alzheimer’s disease

Susan M. Resnick, Oliver Langford, Aaron P. Schultz, Timothy J. Hohman, Sudha S. Seshadri, Tobey J. Betthauser, Keith A. Johnson, Ann D. Cohen, Michael Donohue, Rachel F. Buckley, Yen Ying Lim, Rebecca F. Gottesman, Prashanthi Vemuri, Colin L. Masters, Sid E. O’Bryant, Alexa S. Beiser, Timothy M. Hughes, Paul Maruff, Gillian Coughlan, Samuel N. Lockhart, Dorene M. Rentz, Colin Birkenbihl, Julie C. Price, Ilke Tunali, Samantha C. Burnham, Rory Boyle, Shubhabrata Mukherjee, Rebecca England Amariglio, Michael J Properzi, Susan Landau, Jasmeer P. Chhatwal, Hannah M Klinger, Madison Cuppels, Sterling C. Johnson, Reisa A. Sperling
article en
3 citations

Abstract

Cognitive resilience (CR) describes the phenomenon of individuals evading cognitive decline despite prominent Alzheimer's disease neuropathology. Operationalization and measurement of this latent construct is non-trivial as it cannot be directly observed. The residual approach has been widely applied to estimate CR, where the degree of resilience is estimated through a linear model's residuals. We demonstrate that this approach makes specific, uncontrollable assumptions and likely leads to biased and erroneous resilience estimates. This is especially true when information about CR is contained in the data the linear model was fitted to, either through inclusion of CR-associated variables or due to correlation. We propose an alternative strategy which overcomes the standard approach's limitations using machine learning principles. Our proposed approach makes fewer assumptions about the data and CR and achieves better estimation accuracy on simulated ground-truth data.

Brain InformaticsVol. 12(1)
Boston University (US), University of Southern California (US), University of North Texas (US), Brigham and Women's Hospital (US), University of Wisconsin–Madison (US), Harvard University (US), University of North Texas Health Science Center (US), The University of Melbourne (AU), The University of Texas at San Antonio Health Science Center (US), Eli Lilly (United States) (US), University of Pittsburgh (US), Vanderbilt University (US), University of Washington (US), Florey Institute of Neuroscience and Mental Health (AU), Massachusetts General Hospital (US), National Institute of Neurological Disorders and Stroke (US), Mayo Clinic in Arizona (US), Athinoula A. Martinos Center for Biomedical Imaging (US), National Institute on Aging (US), Wake Forest University (US), Monash University (AU), Seattle University (US), University of Pennsylvania (US), Vanderbilt University Medical Center (US), University of California, Berkeley (US)
Alzheimer's Association, National Institutes of Health
Climate action
Openalex Percentile: Top 7%
Dementia and Cognitive Impairment Research
4.41
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.