Applying natural language processing to understand symptoms among older adult home healthcare patients with urinary incontinence.
Danielle Scharp, Jiyoun Song, Mollie Hobensack and 3 others
PMID 39601443WHAT IT FOUND
Only 29% of home healthcare episodes for older adults with urinary incontinence had symptoms documented in notes.
Anxiety was most common, urinary symptoms rare. Episodes for Black, Asian/Pacific Islander, and Hispanic patients were less likely to have any symptoms documented than White patients.
Key findings
01Symptom information was found in 2% of clinical notes and in approximately 29% of home healthcare episodes.
02Anxiety was the most common documented symptom, while urinary frequency/urgency and urinary hesitancy/retention were among the least common.
03Episodes for Asian/Pacific Islander, Black, and Hispanic patients were less likely to have any symptom documented than White episodes, and the difference remained significant after adjustment.
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 study analyzed only symptoms documented by clinicians. Patients may report symptoms that are not documented. Urinary incontinence was counted only if it was present on admission to home healthcare. Patients who developed urinary incontinence during an episode were not captured. The statistical comparisons excluded multi-racial and Native American patients because those groups had small sample sizes. The researchers did not calculate recall or F-score, so the study did not measure how well the algorithm found all relevant notes. The data were from 2015 to 2017 and from one home healthcare agency in the Northeastern United States. They may not reflect current documentation or other settings. The algorithm was developed and tested on clinical notes from that agency.
Declared interests
The paper lists NIH extramural research support. The authors declared no conflicts of interest.
The easy way to misread this
Do not read low symptom documentation as proof that patients had few symptoms. The study counted only what was written in clinical notes. Patients may report symptoms that are not documented.