Data‐driven staging of postmortem neuropathology corroborates Braak staging and in‐vivo clinical and cognitive assessments in Alzheimer's’ and Parkinson's diseases
Bibliographic record
Abstract
BACKGROUND: Identifying early biomarkers of neurodegenerative diseases is crucial for early disease intervention. Extending postmortem neuropathology insights to in-vivo helps link impairment to biomarker accumulation. SuStaIn is a data-driven approach that stratifies cross-sectional neuropathology into longitudinal progression, enabling stage inference at group and individual levels. We aimed at testing whether SuStaIn can infer Braak synucleinopathy and Alzheimer's Disease (AD) amyloid plaque and neurofibrillary tangle progression. METHODS: We applied OrdinalSuStaIn to Braak synucleinopathy gradings (2003; N = 110) to assess their progression. Similarly, we analyzed both plaque and tangle gradings from five brain regions in an AD cohort (N = 1300) and a control group (N = 972) using data from the Arizona Study of Aging and Neurodegenerative Disorders. To extend these findings in-vivo, we evaluated the association between SuStaIn-derived patient stages and cognitive performance. RESULTS: SuStaIn successfully replicated Braak Lewy body progression, showing pathology initiation in the brainstem and olfactory bulb and later spread to limbic and cortical regions. These stages correlated strongly with the clinical Hoehn and Yahr's Parkinson's Disease (PD) staging (r=0.96, p<0.0001). For AD, SuStaIn captured postmortem plaque and tangle progression, starting with entorhinal tangles, progressing to hippocampal CA1 tangle deposition, and then to neocortical plaque and tangle accumulation. SuStaIn stages were strongly correlated with cognitive last MMSE scores (r=-0.54, p<0.0001), Thal phases (r=0.80, p<0.0001), and Braak tangle stages (r=0.76, p<0.0001). advanced derived stages were associated with ApoE4 carriers in both data-driven and pathological stages, while controls exhibited lower pathology levels consistent with early stages. CONCLUSIONS: Data-driven approaches can elucidate neuropathological progression in PD and AD and capture additional nuances compared to previously used linear staging techniques. Here we first verify that as a staging tool, SuStaIn can corroborate Braak LB and tangle staging systems and provide a more quantitative model of deviations in individual cases. We further extend this approach in a large sample of postmortem AD neuropathology, showing that SuStaIn-derived patient stages applied to both tangles and plaques were associated with their clinical disease stage and cognitive performance.
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 | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".