BackPsychiatry

Words matter: Stigmatizing language in medical records of individuals electing medication for opioid use disorder.

Drug and Alcohol DependenceResearch Authors: Matthew Perez; Elise N. Marino; Curtis Bone; Tara Karns-Wright; Jennifer S. PotterAIIM Authors: Anushka Aravindan, Layna ParaboschiApproved by President Reda RiffiPublication Date: 10/1/2025

Comprehensive Summary

This study examined how often stigmatizing and self-stigmatizing language appears in medical records for patients receiving medication for opioid use disorder (MOUD). The researchers analyzed over 6,000 clinical notes from nearly 1,400 patients treated in Texas between 2020 and 2021, across two treatment settings: office-based opioid treatment (OBOT) programs and opioid treatment programs (OTPs). Using a natural language processing tool based on the National Institute on Drug Abuse’s “Words Matter” guidelines, the authors identified words and phrases in clinical documentation that were considered stigmatizing. The results showed that stigmatizing language was extremely common, appearing in more than 80% of the notes, while self-stigmatizing language appeared much less often. Certain patient characteristics, such as age, rural status, education level, and income, were linked to higher rates of stigmatizing language. The study also found that stigmatizing and self-stigmatizing language appeared less frequently in OTPs compared to OBOTs. Overall, the findings suggest that both patient background and treatment setting influence how language is used in medical records.

Outcomes and Implications

This research highlights how language used in medical documentation can unintentionally reinforce stigma toward patients with opioid use disorder. Since medical records are shared among healthcare providers, stigmatizing language may affect future clinical decisions and worsen patients’ treatment experiences. Reducing harmful language could help improve patient trust, engagement, and long-term treatment outcomes. The study also shows that natural language processing can be a powerful tool for identifying stigma at a large scale and could be used to monitor documentation practices over time. With additional training focused on respectful, recovery-oriented language, healthcare systems may be able to reduce stigma and create more supportive environments for patients receiving MOUD.

Our mission is to

Connect medicine with AI innovation.

No spam. Only the latest AI breakthroughs, simplified and relevant to your field.