The Brain Health Assessment for Detecting and Diagnosing Neurocognitive Disorders
Bibliographic record
Abstract
BACKGROUND/OBJECTIVES: Brief cognitive screens lack the sensitivity to detect mild cognitive impairment (MCI) or support differential diagnoses. The objective of this study was to validate the 10-minute, tablet-based University of California, San Francisco (UCSF) Brain Health Assessment (BHA) to overcome these limitations. DESIGN: Cross-sectional. SETTING: UCSF Memory and Aging Center. PARTICIPANTS: Older adults (N = 347) (neurologically healthy controls (n = 185), and individuals diagnosed with MCI (n = 99), dementia (n = 42), and as normal with concerns (n = 21)). MEASUREMENTS: The BHA includes subtests of memory, executive function and speed, visuospatial skills, and language and an optional informant survey. Participants completed the Montreal Cognitive Assessment (MoCA) and criterion-standard neuropsychological tests. Standardized structural 3T brain magnetic resonance imaging was performed in 145 participants. RESULTS: At a fixed 85% specificity rate, the BHA had 100% sensitivity to dementia and 84% to MCI; the MoCA had 75% sensitivity to dementia and 25% to MCI. The BHA had 83% sensitivity to MCI likely due to AD and 88% to MCI unlikely due to AD, and the MoCA had 58% sensitivity to MCI likely AD and 24% to MCI unlikely AD. The BHA subtests demonstrated moderate to high correlations with the criterion-standard tests from their respective cognitive domains. Memory test performance correlated with medial temporal lobe volumes; executive and speed with frontal, parietal, and basal ganglia volumes; and visuospatial with right parietal volumes. CONCLUSION: The BHA had excellent combined sensitivity and specificity to detect dementia and MCI, including MCI due to diverse etiologies. The subtests provide efficient, valid measures of neurocognition that are critical in making a differential diagnosis.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".