Table of Contents
Durham, North Carolina-based Duke Health spent nearly a decade waiting for the technology to catch up to an idea, and when large language models finally arrived, the health system built Scout itself rather than wait for a vendor to do it.
What This AI Tool Actually Does
The tool is Scout, an AI platform developed by the Duke Institute for Health Innovation that reads through a patient’s entire electronic health record, including notes going back years, labs, imaging reports and pathology reports, and synthesizes that information into a summary in one to three minutes. It lives inside Epic, the organization’s EHR system, so physicians access it from within their existing workflow.
The Problem Scout Was Built to Solve
“We saw a problem in healthcare where we have information overload,” Jeffrey Ferranti, MD, chief digital officer of the health system, told Becker’s. “Our doctors have electronic health records, but those records can be thousands of pages long, and synthesizing and organizing information in a way that makes sense to physicians, so they can take the very best care of patients, has always been a challenge.” Scout has been an idea internally for a while, but the institution lacked the technology to build it until generative and agentic AI matured enough to make it possible.
How This Tool Maintains Physician Trust
Every claim Scout generates links back to its source in the chart, letting a physician verify the underlying record rather than take the summary on faith. “If it says the patient had an X-ray or an MRI with a certain finding, there’s a link back to the source record in the EHR, so the doctor can review that,” Ferranti said.
Predefined and Custom Prompts for Specific Use Cases
Physicians reach Scout through a tab inside Epic, and access is limited to clinicians who already have a treatment relationship with the patient. For many specialties, the organization has built predefined prompts tailored to specific tasks; an oncologist preparing for tumor board or a transplant physician compiling a summary can pull up a prompt built for that purpose, and the health system tracks how well those prompts perform in practice. Physicians can also write their own prompts, and the institution has identified roughly 50 use cases it is testing across pre-visit planning, discharge summaries and tumor board preparation.
Training and Oversight Requirements for This Tool
Before any physician gets access, they have to complete training on the tool, a requirement Ferranti described as central to how the health system deploys Scout responsibly. “There always needs to be a physician in the loop,” he said.
From Pilot to Enterprisewide Rollout
The organization tested Scout with about 100 physicians before expanding, then took it enterprisewide in early July.
The Research Behind This AI Tool’s Expansion
That expansion followed a randomized controlled trial, still in preprint and not yet peer reviewed, that Ferranti said found clinicians completed tasks roughly 40% faster using Scout, with cognitive workload down 40% to 50% compared with manual chart review.
Why the Health System Built Scout Inside Epic
Duke has used Epic’s SMART on FHIR framework for years to build custom panels into the EHR, and Ferranti said he wanted to avoid a setup where physicians had to toggle between separate systems.
Why This Tool Was Built In-House Rather Than Bought
The health system chose to build Scout in house only after concluding no vendor or partner offered anything comparable. Building from scratch through the Duke Institute for Health Innovation is the last resort, reserved for cases where nothing else exists.
What’s Next and What This Means Going Forward
Duke Health Scout AI offers a concrete example of how building a tool directly inside an existing EHR workflow can address both physician adoption concerns and governance requirements simultaneously.
What This Means for the Future of EHR-Embedded AI
Duke Health Scout AI offers a concrete example of how building a tool directly inside an existing EHR workflow, rather than as a standalone application, can address both physician adoption concerns and governance requirements simultaneously. As the health system continues expanding Scout’s use cases and begins developing additional specialized AI agents, its experience may serve as a reference point for other academic medical centers weighing whether to build proprietary AI tools or wait for vendor solutions to mature.
For more healthcare industry updates, insights and news, visit DistilINFO. Click here to subscribe to stay informed.
