Challenges of Developing a Natural Language Processing Method With Electronic Health Records to Identify Persons With Chronic Mobility Disability.
Nicole D Agaronnik, Charlotta Lindvall, Areej El-Jawahri and 2 others
PMID 32446905WHAT IT FOUND
Wheelchair keywords in health records did not prove chronic wheelchair use.
Notes mentioned wheelchairs for transport, exams, temporary use, or another person. Reason and duration were often missing.
Key findings
01NLP screening flagged 1,482 notes (0.5%) containing wheelchair keywords, associated with 420 patients (2.8%).
02286 of the 1,482 flagged notes (19.3%, representing 105 patients) documented reason for and duration of wheelchair use.
03Wheelchair keywords appeared in four context themes: patient presents in a wheelchair, patient uses a wheelchair outside clinical settings, patient no longer uses or resists a wheelchair, and someone other than the patient uses a wheelchair.
STILL TO COME
How it was doneWhat they foundWhat it means for PTs
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 used records from a single large health care delivery system, so results may not apply to other EHR systems. The health system changed EHR software during the years studied, which may affect how notes are written. The search used a limited keyword list, so some wheelchair users may have been missed. The study could not measure how complete or accurate the keyword search was because full manual review of all notes was not feasible. Documentation often lacked reason and duration, so even manual review left uncertainty about chronic wheelchair use. The study did not test whether the keyword program could determine how long wheelchair use lasted.
Declared interests
The article metadata lists NIH extramural research support. The authors reported no conflicts of interest.
The easy way to misread this
Do not read a wheelchair keyword in an EHR note as proof that a patient chronically uses a wheelchair. The study found keyword mentions in transport, exams, temporary use, and other-person contexts, and 286 of 1,482 flagged notes documented reason and duration.