Development of a Prototype for Patient Artificial Intelligence Guided E-messages (PAIGE)

Poster Number: P45
Presentation Time: 05:00 PM - 06:30 PM

Abstract Keywords: Large Language Models (LLMs), Clinical Decision Support, Documentation Burden
Primary Track: Applications
Programmatic Theme: Clinical Informatics

We conducted a feasibility study of constructing a conversational agent prototype embedded within a patient portal to display follow-up questions, seek patient responses for additional context to improve effective communication between patients and clinicians. Using input from 6 physicians about 7 primary care scenarios, we generated follow-up questions from a local fine-tuned large language model and GPT-4. The prototype of Patient Artificial Intelligence Guided E-messages (PAIGE) will be evaluated to assess patient and provider impact.

Speaker(s):
Siru Liu, PhD
Vanderbilt University Medical Center

Author(s):
Siru Liu, PhD - Vanderbilt University Medical Center; Allison McCoy, PhD, ACHIP, FACMI, FAMIA - Vanderbilt University Medical Center; Laura Zahn, MS; Elise Russo - Vanderbilt University Medical Center; Courtney Zott, MPH; Nicole Gauthreaux, MPH - NORC at the University of Chicago; James Swiger, MBE - AHRQ; Edwin Lomotan, MD - AHRQ; Dean Sittig, PhD - University of Texas Health Science Center at Houston; Prashila Dullabh, MD - NORC at the University of Chicago; Adam Wright, PhD - Vanderbilt University Medical Center;