| Description |
- Background: The 21st Century Cures Act provides patients with access to their clinical notes, but most patients, particularly those with limited health literacy (HL), have difficulty understanding and utilizing them for health-based decisions and adequate management of care. Thus, there is a critical need to improve the comprehensibility of clinical notes and ensure that patient access to medical information facilitates equitable health outcomes. This study introduces a novel clinical application of GPT4, evaluating the effect of GPT4-based plain language translation of discharge summary notes (DSNs) on subjective and objective comprehension, self-reported confidence, and time spent reading each DSN.
Methods: We enrolled 553 patients from December 2023 to February 2024. Participants were ≥18 years old, able to read English, had no diagnosis of cognitive impairment, and had an appointment scheduled within two months of enrollment at the Duke University Health System (DUHS). Patients read four DSNs (two untranslated, two GPT4-translated) related to common reasons for admission to an inpatient general medical service: congestive heart failure (CHF) community acquired pneumonia (CAP), diabetic ketoacidosis (DKA), acute ischemic stroke (AIS). After reading each DSN, patients answered questionnaire items assessing subjective perceptions and objective accuracy comprehension. Effects of translation on comprehension outcomes were analyzed with linear mixed models.
Results: Across all four DSNs, GPT4-based translation improved objective comprehension by 61% (β=1.18, p<0.001), reduced time spent reading by 51% (β=-0.57, p<0.001), improved subjective comprehension by 18% (β=2.32, p<0.001), and improved self-reported confidence by 45% (β=1.94, p<0.001). It also strengthened the association between objective comprehension and confidence by 67% (p<0.01). Improvements were greater in Black and Hispanic patients, older patients, male patients, and those who reported limited health knowledge (p<0.01). In particular, objective comprehension improved an additional 22% and 39% among Black and Hispanic patients respectively (p<0.01).
Conclusions: GPT4-based translation substantially improved patient comprehension of disease course and management while reducing time spent reading DSNs, especially in marginalized populations that historically have low rates of HL. While further research is needed to validate results in additional demographic groups and study downstream effects on health decision-making and outcomes, this offers great promise in closing the health literacy gap between various patient demographics in internal medicine.
|
|---|
