Development and validation of an electronic health record 3‐year risk model for diagnosis of dementia with and without Mini‐Cog scores
Leah R Hanson, A Lauren Crain, Sally K Gustafson, Ann M Werner, Aleta L Svitak, Lauren R O'Keefe, Patrick J O'Connor, Rebecca C Rossom · 2025
Read Development and validation of an electronic health record 3‐year risk model for diagnosis of dementia with and without Mini‐Cog scores by Leah R Hanson, A Lauren Crain, Sally K Gustafson, Ann M Werner, Aleta L Svitak, Lauren R O'Keefe, Patrick J O'Connor, Rebecca C Rossom (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11715639.txt.
Description
Leah Hanson and co-authors build a three-year dementia risk predictor that runs on ordinary electronic health record data. Dementia cases are set to triple by mid-century, and over half of cognitive impairment now goes undiagnosed in primary care. Their 2025 model starts from a routine primary care visit by patients sixty-five and older with no impairment diagnosis.
Two machine learning methods — an ensemble learner and a sparse regression — compete to forecast diagnosis within three years. A second version adds the Mini-Cog, a three-minute screening test, where clinics have it. The point is triage: flag the few charts worth a closer look today. Health systems get a validated sieve for the scarcest resource in dementia care, clinician attention.
Catalog record
| CREATOR | Leah R Hanson, A Lauren Crain, Sally K Gustafson, Ann M Werner, Aleta L Svitak, Lauren R O'Keefe, Patrick J O'Connor, Rebecca C Rossom |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 3 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |