ChatEHR Revolutionizes Patient Care with AI-Backed Software

Stanford Health Care's innovative AI-powered tool, ChatEHR, enables clinicians to access patient medical records through a conversational interface, streamlining time-consuming tasks and enhancing patient care. This technology has the potential to reshape the way healthcare providers interact with patient data, freeing up valuable time for more critical tasks. The tool's development has been ongoing since 2023, with a small group of 33 clinicians piloting its performance and refining its accuracy.

Key Takeaways:

• ChatEHR allows clinicians to ask questions about a patient's medical history, with the tool providing responses based on the patient's medical record.
• The technology has the potential to save healthcare providers time searching through extensive charts for test results or other pertinent background prior to conducting visits or testing.
• A 2020 study found that doctors spent an average of 16 minutes and 14 seconds per patient encounter using electronic health records, with chart review being the most time-consuming task.
• ChatEHR is currently being used by a small group of clinicians to monitor its performance, refine its accuracy, and enhance its utility.
• The tool's automation capabilities can help with tasks such as determining a patient's eligibility for hospice care or recommending additional attention after surgery.
• Other academic health systems, such as the University of Florida and the University of Texas Health Science Center, are also developing large language models for electronic health records.

Statistics:

• Doctors spent an average of 16 minutes and 14 seconds per patient encounter using electronic health records in 2020.
• Chart review took up 5 minutes and 22 seconds per patient on average.
• ChatEHR's automation capabilities can help determine a patient's eligibility for hospice care or recommend additional attention after surgery.
• Precision in providing an exact answer to a question with the University of Texas Health Science Center's natural language model, QuEHRy, was above 90%.
• Patient notes written by doctors and those written using the University of Florida's GatorTron were nearly identical in a 2023 study.

Sources:

• Clinicians can 'chat' with medical records through new AI software, ChatEHR - Stanford news release
• New 'ChatEHR' tool enables clinical conversation at Stanford - Healthcare IT News
• Stanford pilots ChatEHR - Becker's Health IT
• A large language model for electronic health records - NPJ Digital Medicine study from University of Florida researchers
• Medical AI tool from UF, NVIDIA gets human thumbs-up in first study - University of Florida news release
• quEHRy: a question answering system to query electronic health records - JAMIA study from University of Texas Health Science Center researchers