An Autonomous AI Agent for Clinical Information Synthesis and Patient Summarization in Electronic Health Records
10/8/2025 • Nature Medicine • License: CC BY
Lee, H.
Abstract
This study introduces an agentic AI capable of autonomously navigating complex EHR interfaces to perform information retrieval and synthesis. The agent was tasked with creating comprehensive referral summaries for cardiology consults. It reduced the median time for physicians to complete this task from 25 minutes to just 2.5 minutes, a 90% reduction, while maintaining 98% factual accuracy compared to human-generated summaries.
Source: View original
Clinical implications
Researchers developed an AI 'agent' that can act like a human user to navigate a patient's electronic chart, gather complex information, and write a summary for a specialist. This tool cut the time doctors spent on this task by 90%, freeing them up for other clinical duties.
This product uses publicly available data from the U.S. National Library of Medicine (NLM),
National Institutes of Health, Department of Health and Human Services; NLM is not responsible
for the product and does not endorse or recommend this or any other product.
Links to third-party publications are provided for research discovery.