Skip to main content

Stanford Medicine researchers have developed an AI-powered health record software called ChatEHR. The app is designed to help clinicians quickly access and interpret patient medical records.

The tool is still in its pilot phase and is being tested by a group of 33 clinicians at Stanford Hospital. The goal is to streamline everyday tasks, like reviewing charts and summarizing a patientโ€™s history, so providers can spend more time on patient care. Instead of digging through pages of charts, healthcare providers can simply type questions like โ€œHas this patient had a colonoscopy?โ€ or โ€œWhat medications are they currently taking?โ€ and get answers pulled from the record.

Early users say itโ€™s already helping them find the information they need faster and with less hassle.

According to Nigam Shah, the chief data science officer at Stanford Health Care, who led the team in developing the software, โ€œChatEHR is secure; itโ€™s pulling directly from relevant medical data; and itโ€™s built into the electronic medical record system, making it easy and accurate for clinical use.โ€

While itโ€™s not meant to offer diagnoses or treatment advice, ChatEHR can handle a wide range of information-gathering tasks. For example, when a patient arrives at the emergency room, it can provide the admitting doctor with key information from the patientโ€™s medical history, such as past surgeries, test results, and current medications.

ChatEHR can also help in cases where patients are transferred from other hospitals to Stanford. These patients often arrive with extensive medical records, sometimes hundreds of pages long. ChatEHR can summarize that information and allow clinicians to get up to speed quickly.

The team behind the software is also working on automations that use patient history to support decisions, such as whether someone qualifies for a transfer to another facility or needs extra care after surgery.

In addition, the developers are refining ChatEHR using a framework called MedHELM, which helps test how AI tools perform in clinical settings. Theyโ€™re also adding features like in-text citations so clinicians can see exactly where information came from in the patientโ€™s record.

AI is becoming a bigger part of healthcare, and Stanford Medicineโ€™s work on ChatEHR shows how it can help providers work smarter and spend more time focused on patients.

About the author: