PTOTRNOtherJMIR nursing2023

Home Health Care Clinicians' Use of Judgment Language for Black and Hispanic Patients: Natural Language Processing Study.

Maxim Topaz, Jiyoun Song, Anahita Davoudi and 4 others

PMID 37067893

WHAT IT FOUND

Home health care notes about Black and Hispanic patients contained judgment words like 'claims' and 'insists' more often than notes about White patients.

Visits were also shorter when notes contained judgment words. This suggests possible documentation bias, not proof of harm.

Key findings

01Judgment language appeared in 10% of visit notes and involved 38% of patients.

02In adjusted analysis, Black and Hispanic patients had higher odds of judgment language than White patients, reported as 5% and 9% higher odds.

03Visits averaged 46 minutes when judgment language was used and 70 minutes when it was not; adjusted analysis linked each judgment word to a 21-minute shorter visit.

STILL TO COME

How it was doneWhat they foundWhat it means for PTsWhat it means for OTsWhat 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.

Already have one?

What it does not show

The method counted judgment words without reading context, so words like states may be used nonjudgmentally. The analysis did not adjust for clinical factors such as cognitive status or mental health conditions. Visit length may not reflect quality of care, and time could be affected by administrative tasks or needing to reach another patient. The study did not compare nurses, physical therapists, occupational therapists, and social workers separately. It used records from one urban home health agency in 2019, so results may not generalise. It cannot show that judgment language caused shorter visits or worse care.

Declared interests

The authors declared no conflicts of interest.

The easy way to misread this

Do not conclude that judgment language caused shorter visits or poorer care. The study only reported associations, counted words without context, and visit length may not reflect quality.

Read it on PubMed →