An Electronic Health Record Algorithm's Performance to Identify Cognitive Impairment in Primary Care.
Christine E Kistler, Molly E Lynch, Feng-Chang Lin and 3 others
PMID 41135594WHAT IT FOUND
Searching older adults' primary care records for dementia codes plus dementia medicines found true impairment in 27 of 36 flagged cases, but missed 18 of 45 chart-confirmed cases, so it is better for finding cases than ruling them out.
Key findings
01Review of the records found cognitive impairment in 45 of the 525 sampled older adults, most commonly as other symptoms/signs or unspecified dementia.
02The algorithm that added dementia medications flagged 36 patients, and 27 of those were confirmed to have impairment, but it still missed 18 chart-confirmed cases.
03No demographic characteristics were associated with disparities in detection rates for mild cognitive impairment or dementia.
STILL TO COME
How it was doneWhat they foundWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
This was a single health network in North Carolina, and only 525 charts were reviewed, so the algorithm may perform differently in other primary care systems. The researchers did not review all 10,000 charts, so the true performance may differ. No confirmatory clinical testing was done on people identified, and the algorithm was developed for research, not routine care. Only structured data were used; dementia biomarker laboratory results, delirium-related hospitalizations, and other medication classes were not included. Many diagnoses were vague, such as unspecified dementia or other cognitive symptoms, and lacked disease severity.
Declared interests
The authors declared no conflicts of interest. C.E.K. serves on the editorial board for JAMDA, stated unrelated to this work. The paper is listed as supported by NIH and non-U.S. government research support.
The easy way to misread this
Do not conclude this algorithm can be used to rule out cognitive impairment in individual patients. It missed 18 chart-confirmed cases, and the authors say it was developed for research purposes, not clinical care.