Patient Perspectives on AI-Drafted Electronic Portal Messages
By
Kellie Owens
Athmeya Jayaram
Anand Chowdhury
Kathryn I. Pollak
Sam Klotman
Zachary Griffen
Miles Danielski
Ben Goldstein
Jennifer Maddocks
Matthew Roman
Eric G. Poon
Armando Bedoya
Joanna Cavalier
July 7, 2026
Clinical Scorecard: Insights from Patients Regarding AI-Generated Messages in Electronic Health Portals
At a Glance
Category Detail
Condition AI-Generated Messaging in Healthcare Key Mechanisms Use of generative AI to draft responses to patient messages in electronic health portals. Target Population Adult patients from a large academic health system. Care Setting Outpatient care using electronic health portals.
Key Highlights
Patients generally preferred AI-drafted responses over clinician-written responses. Satisfaction decreased when patients were informed that a response was authored by AI. The study aimed to understand patient perceptions of AI in clinical communication. Participants included a diverse group with varied demographic characteristics. Interviews explored patient interpretations of AI involvement in messaging. Guideline-Based Recommendations
Diagnosis
Management
Monitoring & Follow-up
Risks
Patient & Prescribing Data
Adult patients who completed a patient advisory committee survey.
Participants expressed varied views on AI-drafted messages and their implications for trust and communication.
Clinical Best Practices
Incorporate patient input when implementing AI tools in clinical workflows. Ensure transparency regarding AI involvement in patient communications. Consider patient preferences and perceptions when using AI in healthcare messaging. Related Resources & Content
