Evaluating ChatGPT for converting clinic letters into patient-friendly language: a quantitative study.

Area of Science:

• Medical Communication
• Artificial Intelligence in Healthcare

Background:

• Patient comprehension of medical information is crucial for treatment adherence.
• Clinician time constraints often limit personalized patient communication.
• Previous methods for simplifying medical language have limitations.

Purpose of the Study:

• To evaluate ChatGPT's ability to translate clinical letters into patient-understandable language.
• To assess if AI translation preserves essential clinical information.
• To measure the impact of translated letters on patient understanding and satisfaction.

Main Methods:

• A single-blinded, quantitative study design was employed.
• Twenty-three clinical letters from eight specialties were translated using ChatGPT.
• Patient representatives rated their understanding of original and translated letters.

Main Results:

• ChatGPT translations retained all clinical information.
• Patient understanding and satisfaction significantly increased post-translation.
• The need for patients to seek medical help for letter interpretation decreased.

Conclusions:

• ChatGPT is a valuable tool for translating clinical letters into accessible language.
• AI-assisted translation improves patient comprehension and preference for medical correspondence.
• This technology offers a scalable solution to enhance patient-clinician communication.