0
0
June 7, 2025
Stanford Health Care has begun piloting a groundbreaking artificial intelligence tool, ChatEHR, that allows clinicians to interact with patient medical records in a conversational, chat-based format. The innovative software, developed by a team led by Dr. Nigam Shah, Stanford Health Care’s chief data science officer, aims to make electronic health records (EHRs) more accessible and user-friendly for doctors, nurses, and other healthcare providers.
A New Way to Access Medical Data
Much like popular large language models such as GPT-4, ChatEHR enables clinicians to ask natural-language questions about a patient’s medical history, request summaries of charts, and retrieve specific data points. The AI pulls information directly from a patient’s health records, ensuring responses are relevant and secure.
“AI can augment the practice of physicians and other health care providers, but it’s not helpful unless it’s embedded in their workflow and the information the algorithm is using is in a medical context,” said Dr. Shah. “ChatEHR is secure; it’s pulling directly from relevant medical data; and it’s built into the electronic medical record system, making it easy and accurate for clinical use.”
Streamlining Clinical Tasks
Currently, ChatEHR is being tested by a select group of 33 clinicians at Stanford Hospital, including physicians, nurses, and physician assistants. Early users report that the tool saves significant time by surfacing relevant information quickly, allowing them to focus more on patient care and less on administrative tasks.
Dr. Sneha Jain, a clinical assistant professor of medicine and early adopter of ChatEHR, highlighted its impact: “Making the electronic medical record more user-friendly means physicians can spend less time scouring every nook and cranny of it for the information they need. ChatEHR can help them get that information up front so they can spend time on what matters—talking to patients and figuring out what’s going on.”
ChatEHR is particularly useful in high-pressure situations, such as emergency admissions or patient transfers, where clinicians must rapidly review extensive medical histories. Dr. Jonathan Chen, hospital physician and assistant professor, noted that the tool can distill hundreds of pages of records into concise, relevant summaries, and even answer follow-up questions to clarify patient histories.
Automations and Future Plans
The development team is also building “automations”—AI-powered evaluative tasks based on patient records. For example, ChatEHR can help determine whether a patient is eligible for transfer to another care unit or for hospice care, reducing administrative burdens and speeding up decision-making.
Looking ahead, Stanford plans to expand ChatEHR’s availability and continue refining its accuracy and utility. The team is using MedHELM, an open-source framework, to evaluate real-world performance and is developing features like source citations to further enhance trust and transparency.
“We’re rolling this out in accordance with our responsible AI guidelines, not only ensuring accuracy and performance, but making sure we have the educational resources and technical support available to make ChatEHR usable and useful to our workforce,” Dr. Shah said.
Disclaimer:
This article is based on information from the Medical Xpress article “Clinicians can ‘chat’ with medical records through new AI software, ChatEHR” (June 6, 2025). ChatEHR is currently in a pilot phase and not widely available. The software is designed as an information-gathering tool to assist clinicians and is not intended to provide medical advice or replace professional judgment. All clinical decisions remain the responsibility of qualified healthcare professionals. For more details, visit Medical Xpress.
