Automated detection of cognitive impairment in clinical practice
Bibliographic record
Abstract
OBJECTIVE: Cognitive impairment is now recognized as an impending public health crisis. About one-third of adults are concerned about their cognition, and the prevalence of objective cognitive impairment is much higher among those with neurological disorders. Existing screening tools are narrowly focused on detecting dementia in older adults and must be clinician-administered and scored, making them impractical for many neurology practices. This study examined the utility of a brief, self-administered, computerized cognitive screening tool, the Brief Assessment of Cognitive Health (BACH), in identifying cognitive impairment in adults. METHODS: 912 adults (ages 18-84) completed BACH and a neuropsychological battery. Multivariable models were developed to provide a BACH index score reflecting the probability of cognitive impairment for individual patients. Predictive accuracy was compared to that of the Montreal Cognitive Assessment (MoCA) in a subset of 160 older adults from a Memory Disorders clinic. RESULTS: The final multivariable model showed good accuracy in identifying cognitively impaired individuals (c = 0·77). Compared to MoCA, BACH had superior predictive accuracy in identifying older patients with cognitive impairment (c = 0·79 vs. 0·67) as well as differentiating those with MCI or dementia from those without cognitive impairment (c = 0·86 vs. c = 0·67). CONCLUSIONS: Results suggest that cognitive impairment can be identified in adults using a brief, self-administered, automated cognitive screening tool, and BACH provides several advantages over existing screeners: self-administered; automatic scoring; immediate results in health record; easily interpretable score; utility in wide range of patients; and flags for treatable factors that may contribute to cognitive complaints (i.e., depression, sleep problems, and stress).
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".