This is an old revision of the document!
ChatEHR is a set of capabilities developed at Stanford Medicine, for using a set of Large Language Models (LLMs) with a single patient's longitudinal medical chart in context. There are two ways to use the ChatEHR capability:
- via a fixed prompt automation, which applies an existing set of criteria to a patient's record and returns a response based on that patient's record. Examples include decisions about transfer eligibility, referrals to certain services, and creating summaries of a hospital course of stay.
- via a user interface, which is available as a tab inside of Epic Hyperspace to allow care providers (clinicians, nurses, pharmacists) to ask questions of a given patient's medical record.
News coverage
Origin
Nov 1, 2023 - chatEHR is first conceptualized building on the success of https://securegpt.stanfordhealthcare.org/ Nov 15, 2023 - A working demo is created as an AI-CARE project by a student. Jan - March, 2024 - Proof of concept work in ENT referral and Nursing summarization. https://pubmed.ncbi.nlm.nih.gov/40502261/ May xx, 2024 - the concept of using an LLM in context with a single patient record is fleshed out June 10, 2024 - second demo and prototype June 19, 2024 - presentation to Data Science Exec Committee, and permission to build July 2024 - First automation use-case implemented to automate chart review for inter-facility transfers Aug 15, 2024 - Backend architecture overhaul Aug 23, 2024 - Alpha testers get access to the UI Jan xx, 2025 - First user gets access for UI June 5, 2025 - Announcement of the pilot, with 30+ active users July 2, 2025 - Ramp up to 89 users (clinicians, nurses, residents, fellows, PAs, care managers, MD students)
