Tau spatial distribution predicts domain‐specific cognitive performance: a machine learning approach
Different sets of brain regions best predict performance for each cognitive domain. Temporal lobe tau is highlighted for most domains, likely attributed to early accumulation. The parietal lobe is emphasized for attention and visuospatial measures, despite less tau. Semantic memory left-lateralization may be attributed to language production. Visuospatial right-lateralization likewise aligns with neuroimaging studies. Overall, the predictive regions of each cognitive measure align with functional connectivity studies, but constrained to regions with AD tau pathology. These results indicate high sensitivity of our cognitive measures to regional tau and the benefit of evaluating distinct brain regions depending on patient cognitive profiles.
Authors
- Nicole S. McKay (ORCID: https://orcid.org/0000-0003-4123-2548)
- Peter R Millar (ORCID: https://orcid.org/0000-0003-4588-739X)
- Austin McCullough (ORCID: https://orcid.org/0000-0001-9192-111X)
- Stephanie Doering (ORCID: https://orcid.org/0000-0001-5110-0640)
- Shaney Flores
- Jason J. Hassenstab
- John C. Morris
- Brian A. Gordon
- Tammie L.S. Benzinger
Institutions
- Washington University in St. Louis (US)
Publication Details
- Journal
- Alzheimer s & Dementia
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1002/alz70862_110262
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00