The Incidence and Disparities in Use of Stigmatizing Language in Clinical Notes for Patients With Substance Use Disorder
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
OBJECTIVE: The language used to describe people with substance use disorder impacts stigma and influences clinical decision making. This study evaluates the presence of stigmatizing language (SL) in clinical notes and detects patient- and provider-level differences. METHODS: All free-text notes generated in a large health system for patients with substance-related diagnoses between December 2020 and November 2021 were included. A natural language processing algorithm using the National Institute on Drug Abuse's "Words Matter" list was developed to identify use of SL in context. RESULTS: There were 546,309 notes for 30,391 patients, of which 100,792 (18.4%) contained SL. A total of 18,727 patients (61.6%) had at least one note with SL. The most common SLs used were "abuse" and "substance abuse." Nurses were least likely to use SL (4.1%) while physician assistants were most likely (46.9%). Male patients were more likely than female patients to have SL in their notes (adjusted odds ratio [aOR], 1.17; 95% confidence internal [CI], 1.11-1.23), younger patients aged 18 to 24 were less likely to have SL than patients 45 to 54 years (aOR, 0.55; 95% CI, 0.50-0.61), Asian patients were less likely to have SL than White patients (aOR, 0.45; 95% CI, 0.36-0.56), and Hispanic patients were less likely to have SL than non-Hispanic patients (aOR, 0.88; 95% CI, 0.80-0.98). CONCLUSIONS: The majority of patients with substance-related diagnoses had at least one note containing SL. There were also several patient characteristic disparities associated with patients having SL in their notes. The work suggests that more clinician interventions about use of SL are needed.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it