Hidden in Plain Sight: Stigmatizing Language in Patient Medical Records

ABSTRACT Respect for all patients as persons is a core principle of ethical clinical practice, which is embodied in the ways clinicians communicate about patients. Although medical records are an integral method of communicating about patients, few studies have evaluated patient records as a means of communicating attitudes of respect or disrespect from one clinician to another. Our own preliminary work has found that language used in medical records has a direct influence on subsequent clinicians who read the notes, both in terms of their attitudes towards the patient and their medication prescribing behavior. This is an important and overlooked pathway by which attitudes can be passed from one clinician to another and affect the quality of care patients receive. Our overarching goal is to improve respect for patients and thereby enhance the quality of patient care. The specific aims of this proposal are: (1) to define and develop a taxonomy of language in medical records using qualitative analyses with input from clinicians and patients across 5 different medical specialty areas, (2) to measure the use of different types of language in medical records using natural language processing (NLP) that can efficiently detect and quantify positive and negative language in electronic patient records, and then (3) to increase respect in healthcare environments using proven implementation science (IS) strategies (stakeholder engagement, education, audit and feedback, and champions) to motivate and enable health system change. Every encounter with a patient is documented in the medical record. Because language may have a powerful role in influencing subsequent clinician attitudes and behavior, attention to the language used in medical records could have a large impact on the promotion of respect for all patients.