Revealing Individual Neuroanatomical Heterogeneity in Alzheimer’s Disease
Bibliographic record
Abstract
Abstract Alzheimer’s disease is clinically heterogeneous, in symptom profiles, progression rates and outcomes. This clinical heterogeneity is linked to underlying neuroanatomical heterogeneity. To explore this, we employed the emerging technique of neuroanatomical normative modelling to index regional patterns of variability in cortical thickness in individual patients from the large multi-site Alzheimer’s Disease Neuroimaging Initiative. We aimed to characterise individual differences and outliers in cortical thickness in patients with Alzheimer’s disease, people with mild cognitive impairment and cognitively normal controls. Furthermore, we assessed the relationships between cortical thickness heterogeneity and cognitive function, amyloid-beta, tau, ApoE genotype. Finally, we examined whether individual neuroanatomical normative maps were predictive of conversion from mild cognitive impairment to diagnosed Alzheimer’s disease. Data on cortical thickness from the 148 brain regions of the Destrieux FreeSurfer atlas was obtained from T1-weighted MRI scans of 1492 participants scanned at 62 different sites. A neuroanatomical normative model was developed to index normal cortical thickness distributions using a separate healthy reference dataset (n= 33,072), employing hierarchical Bayesian regression to predict cortical thickness per region using age and sex. These regional normative models were then fine-tuned to the ADNI dataset after which cortical thickness z-scores per region were calculated, resulting in a z-score ‘map’ for each participant. Regions with z-scores < -1.96 were classified as outliers. Patients with Alzheimer’s disease had a median of 12 outlier regions out of a possible 148. Individual patterns of outlier regions were highly variable, with the highest overlap in the parahippocampal gyrus at only 47% of patients. For 62 regions, over 90% of these patients had cortical thicknesses within the normal range. Patients with Alzheimer’s disease had significantly more outlier regions than people with mild cognitive impairment or controls [ F (2, 1022) = 95.39), P = 2.0 x ×10 −16 ]. They were also statistically more dissimilar to each other than were people with mild cognitive impairment or cognitive normal controls [ F (2, 1024) = 209.42, P = 2.2×10 −16 ]. Having a greater number of outlier regions was associated with worse cognitive function, CSF protein concentrations and an increased risk of converting from mild cognitive impairment to Alzheimer’s disease within three years (HR =1.028, 95% CI[1.016,1.039], P =1.8 ×10 −16 ). Individualised normative maps of cortical thickness highlight the heterogeneity of Alzheimer’s effects on the brain. Regional outlier estimates have the potential to be a marker of disease and could be used to track an individual’s disease progression or treatment response in clinical trials.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".