Detecting Language Associated With Home Healthcare Patient's Risk for Hospitalization and Emergency Department Visit.
Jiyoun Song, Marietta Ojo, Kathryn H Bowles and 13 others
PMID 35171126WHAT IT FOUND
An algorithm detected concerning signs in 18.1% of home health notes, mostly visit notes.
It did not test whether those signs predicted hospitalization or emergency visits.
Key findings
01The algorithm's overall performance in identifying Omaha System problems was good, with average F-score 0.84.
0218.1% of 2,321,977 notes were detected as having at least one concerning sign or symptom.
03Among notes with at least one concerning sign or symptom, 81% were visit notes, and concerning signs were almost nine times more likely in visit notes than care coordination notes.
STILL TO COME
How it was doneWhat they foundWhat it means for RNs
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
The concerning signs were selected through expert opinion, and expert agreement was fair. The algorithm was validated only on 1,000 notes from the same data set, not externally. All data came from one home health organization, so wording and documentation patterns may not match other agencies. The notes were from 2015 to 2017, so current documentation practice may differ. The study did not test whether the detected signs predicted hospitalization or emergency visits.
Declared interests
The authors reported no conflicts of interest. The paper is listed as supported by NIH and U.S. government funds.
The easy way to misread this
Do not read the high frequency of documented concerns as evidence that an early warning system will reduce hospitalizations or emergency visits. The study tested note detection, not outcome prediction or patient care effects.