Overview of ChatEHR
ChatEHR, an AI software developed by Stanford Medicine, is designed to enhance the efficiency of chart reviews by allowing clinicians to interact with medical records through natural language queries.
Key Features
- Clinicians can ask specific questions about a patient’s medical history.
- The software automatically summarizes charts and performs various tasks.
- ChatEHR pulls data directly from a patient’s health records to provide accurate responses.
Current Implementation
The technology is currently in the pilot phase, being tested by a select group of 33 healthcare professionals at Stanford Hospital, including physicians, nurses, and physician assistants. This group is responsible for monitoring the software’s performance and refining its accuracy.
User Interaction
When clinicians access ChatEHR, they are welcomed with the message: “Hi, I’m ChatEHR! Here to help you securely chat with the patient’s medical record.” They can then input a variety of questions, such as:
- Does the patient have any allergies?
- What does their latest cholesterol test reveal?
- Have they had a colonoscopy?
Expert Insights
Nigam Shah, chief data science officer at Stanford Health Care, emphasized that while AI can enhance the work of healthcare providers, it must be integrated into their workflow and utilize relevant medical context. He stated:
“ChatEHR is secure, it pulls directly from relevant medical data, and it’s built into the electronic medical record system, making it easy and accurate for clinical use.”
Limitations
Shah clarified that ChatEHR is not intended to provide medical advice. Instead, it serves as an information-gathering tool, ensuring that all medical decisions remain with healthcare professionals.
Broader Context
In related developments, Samsung has partnered with Stanford Medicine to enhance the sleep apnea detection feature of the Galaxy Watch, while AI Medical Service (AIM) is collaborating with Stanford to validate diagnostic endoscopic AI for gastric cancer detection.
Other companies, such as Layer Health, are also working on automating chart reviews and improving the efficiency of medical records management.