Stanford Rolls Out AI-Backed Software That Summarizes Electronic Health Records

Stanford Health Care is rolling out a new artificial intelligence-backed software called ChatEHR.

The technology, which is in a pilot stage, enables clinicians to “ask questions about a patient’s medical history, automatically summarize charts, and perform other tasks. [It] uses information from individuals’ health records to provide its response.” Nigam Shah, chief data science officer at Stanford Health Care, says the technology 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.”

The software is currently only accessible to “a small cohort of individuals at Stanford Hospital – 33 physicians, nurses, physician’s assistants, and nurse practitioners,” who are “monitoring its performance, refining its accuracy, and enhancing its utility.”

Clinicians can ask the tool questions like “Does this person have any allergies? What does their latest cholesterol test show? Have they had a colonoscopy? Were the results normal?” It is not meant for medical advice but instead for gathering information “that can expedite the process and, ideally, save time.” It can also be used to gather information on a patient’s whole medical history quickly when they come into an emergency room. Transfer cases could also benefit from the tool. The team is also working on so-called “’automations,’ or evaluative tasks based on a patient’s history and record.”