Programs
Cognitive and neurological health
Cognitive and neurological health: difficulty control for adaptive cognitive training and dementia risk stratification from brain MRI and speech.
Projects
Target, evidence, next check — kept apart
A target is what the project set out to reach. Evidence is what has been measured, in which scope. The next check is what would change the reading.
| Project | Internal target | Evidence so far | Next check |
|---|---|---|---|
| 16-2 · Adaptive cognitive training | Difficulty convergence in at least 95% of simulated episodes | Synthetic harness (cog16) · Common synthetic checks | Import stratum-level summary statistics inside the data-use zone, re-freeze the fixture and re-run; then test a response generator whose functional form differs from the scheduler's model. |
| 16-3 · Dementia diagnosis | External cohort AUROC of at least 0.90 | Synthetic harness (cog16) · Common synthetic checks | After approved data import, run the same harness with ADNI and OASIS-3 as the two external directions and evaluate speech separately; the synthetic figures are then replaced. |
Evaluation data
16-2 · Official OASIS-2 demographic workbook
Washington University OASIS-2 visit metadata
16-2 · ADNI data notes · NCT02301546
ADNI longitudinal assessments and registered cognitive training trials
16-3 · Official OASIS-2 demographic workbook and MRI archives
OASIS-2 MRI visit metadata
16-3 · 2020 official split and test labels
DementiaBank ADReSS Challenge 2020
16-3 · Provider data definitions and access conditions
ADNI / OASIS-3 / DementiaBank
Boundary cases recorded before evaluation
16-2 · Adaptive cognitive training
- Convergence to 70–80% correct responses in simulated episodes
- Difficulty changes after repeated errors, fatigue or delayed responses
- 100% blocking of phrases tagged for negative emotional effects in the fixed test
16-3 · Dementia diagnosis
- Whether MRI and speech can be matched by participant and visit
- Performance changes across scanners, sites and audio settings
- Lock model weights and diagnostic definitions before external evaluation
What the evidence covers
16-2
Convergence in simulation evaluates the behaviour of the training policy. Clinical cognitive improvement requires different evidence.
16-3
Single-modality evaluation is available pending imaging and speech matched to the same participant and diagnostic visit.