Original Medical Notes Versus AI Plain-Language Summaries

Background As patient access to electronic medical records becomes more widespread,understanding how individuals emotionally respond to their clinical documentation hasbecome increasingly important. A qualitative study analyzing 600 medical encounter notesauthored by 138 clinicians identified distinct patterns of language reflectingclinicians' attitudes toward patients. Five categories of negative language weredescribed (questioning credibility, disapproval, stereotyping, labeling patients as"difficult," and unilateral decision‐making), alongside six categories of positivelanguage (compliments, approval, self‐disclosure, minimizing blame, personalization, andcollaborative decision‐making). Prior research has demonstrated that access to clinicalnotes ('open notes') can influence patient experience, with potential benefits includingimproved understanding, greater trust, enhanced perceived quality of care, and increasedengagement in self‐care and health management. These benefits appear particularlypronounced with patients with lower education attainment or those from ethnic minoritygroups. Despite this, fewer than half of clinicians routinely discuss shared notes withpatients during visits.Rationale Language choices within clinical documentation may meaningfully shape howpatients perceive their diagnosis, their relationship with healthcare providers, andtheir emotional well‐being. For example, in a survey study of 100 healthy companions oforthopedic hand surgery patients, participants evaluated 19 commonly used medical termsand their synonyms using the Self‐Assessment Manikin (SAM). Terms such as "pain" wasrated more negatively than alternatives such as "discomfort" or "ache", while "rupture"elicited a more negative response than "tear" or "defect". These findings suggest thatfrequently used clinical terminology may also unintentionally elicit negative emotionalreactions. Patients may be particularly vulnerable to language‐related distress whenreading their own medical records. The tone, complexity, and structure of these notes,especially in surgical specialties, may impact patient trust and overall comfort, and, insome cases, may unintentionally erode trust or intensify anxiety. Emerging evidencesuggests that plain‐language summaries might mitigate these effects. In a small study of20 participants, artificial intelligence was used to generate plain‐language medicalnotes, which were perceived as more useful, supportive of the patient‐clinicianrelationship, and empowering for patients' understanding in their health. Although theimportance and benefits of accessible visit notes have been well established, thereremains limited empirical evidence regarding the optimal tone, structure, and language ofmedical documentation from the patient perspective.HypothesesPrimary hypothesis:There are no factors associated with patient ratings of trust and experience with theclinician (TRECS), including whether patients viewed their original medical record entryor an LLM‐generated plain language summary based on a curated version of the record(where PHI is removed) prior to the visit and other patient factors (demographics, mentalhealth clusters).Secondary hypotheses:There are no factors associated with emotional responses to viewing one's own medicalrecord entry, including whether patients view the original entry or an LLM‐generatedplain language summary based on a curated version of the record (where PHI is removed)prior to the visit and other patient factors (demographics, mental health clusters).Qualitative hypothesis:What themes does an LLM identify in patient verbatim comments regarding viewing theirmedical record entry or an LLM plain language summary?