Identifying and Reducing Stigmatizing Language in Home Health Care With a Natural Language Processing-Based System...

Area of Science:

• Health Informatics
• Natural Language Processing
• Clinical Communication

Background:

• Stigmatizing language in clinical notes negatively impacts patient care quality.
• Natural Language Processing (NLP) offers a solution for identifying such language in electronic health records.

Purpose of the Study:

• To develop and evaluate an NLP-driven system (ENGAGE) for automatically identifying and replacing stigmatizing language in clinical notes.
• To refine the understanding of stigmatizing language within home health care (HHC) settings.

Main Methods:

• A mixed-methods approach using electronic health record data from HHC organizations (2019-2021).
• Aim 1: Refine the ontology of stigmatizing language through interviews and note analysis.
• Aim 2: Determine optimal NLP approaches for accuracy.
• Aim 3: Analyze prevalence by patient race/ethnicity.
• Aim 4: Develop the ENGAGE system with NLP methods and a user interface.

Main Results:

• Funding secured from the National Institute on Minority Health and Health Disparities.
• Recruitment initiated in May 2024; interviews completed for 9 participants as of March 2025.
• Anticipated completion of all study aims by April 2027.

Conclusions:

• The study will examine stigmatizing language in HHC settings using extensive data.
• Aims to develop systems for effectively reducing stigmatizing language among HHC nurses.
• Contributes to improving the quality of patient care through technological intervention.