Impact of Patient Communication Style on Agentic AI-Generated Clinical Advice in E-Medicine

Abstract excerpt

<h4>Background</h4> E-medicine use has surged, and health systems are exploring LLMs for message triage. However, it is still unknown whether patient tone alone alters AI-generated clinical or administrative decisions. <h4>Methods</h4> We created 1,000 clinician-validated primary-care vignettes (500 clinical, 500 sick-leave) and presented each in eight communication styles. Five agentic LLMs generated structur...

Topics

Open a Topic to create a Post that cites this publication.

• Antibiotic Use and Resistance
• Bacterial Identification and Susceptibility Testing
• Diagnosis, Differential
• Infant Development and Preterm Care
• Phenotype
• Rare Diseases
• Retinopathy of Prematurity Studies
• Streptococcal Infections and Treatments

Identifiers and source

Literature Corpus work

c854b897-00d3-5b5b-9e02-f82ecc996550

DOI

10.64898/2025.12.02.25341475