Enhancing Early Dementia Detection in Primary Care with a Culturally Tailored Bilingual EHR Screening Tool
Bibliographic record
Abstract
BACKGROUND: Alzheimer's disease (AD) affects over 10% of individuals aged 65 and older, with Black and Hispanic/Latino individuals experiencing a 1.5-2.0 times higher prevalence than white individuals. Despite these disparities, AD remains underdiagnosed, particularly in non-white populations. Current dementia screening tools, such as the Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA), face challenges in time efficiency, accessibility, and cultural sensitivity. This study aimed to implement a brief dementia screening tool integrated into the electronic health record (EHR) and evaluate its impact on diagnosis, workup, and treatment in a diverse family medicine clinic in Los Angeles County. METHOD: The dementia screening tool (DST), developed collaboratively by the University of California Alzheimer's Disease Centers and the California Department of Public Health, was designed to be brief (<5 minutes) and adaptable. It includes a three-question patient questionnaire, an informant input option, and the Mini-Cog assessment. To enhance accessibility, the tool was translated and culturally adapted for Spanish-speaking patients. Patients aged 60+ completed the DST before their annual wellness visits, with results integrated into the EHR. This pre-post intervention study compared patients aged 60+ without a prior dementia diagnosis during the pre-intervention (February 2016-August 2022) and post-intervention (September 2022-June 2023) periods. Outcomes included new dementia diagnoses, medications, specialty referrals, labs, and imaging. RESULT: The DST was implemented, screening 996 patients in 10 months. Screening led to 35 specialty care referrals and 15 new dementia diagnoses. New diagnoses increased from 4.17% pre-DST to 4.80% post-DST all (OR 2.10, p = 0.02) and 6.43% among those screening positive (OR 2.57, p = 0.04). Dementia medication prescriptions rose from 2.93% pre-DST to 4.94% in the post-DST all group, reaching 6.87% among those who screened positive. Specialty referrals were more frequent post-DST all (9.13%) and even higher among those screening positive (14.16%). Post-DST, all secondary outcomes significantly improved, including increased use of diagnostic labs and imaging studies. CONCLUSION: Integrating a brief, culturally sensitive DST into primary care significantly improved dementia diagnosis rates, workup, referrals, and treatment. These findings highlight the potential for broader implementation of the DST to enhance dementia care and address health disparities in diverse populations.
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 | 0.007 | 0.017 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".