Attached is a very interesting article about efforts at Johns Hopkins to use AI in conjunction with EHR and patient communication tasks. It involves generative AI (written output such as chart summaries), ambient AI (which listens to patient encounters and can help summarize information and prompt tasks in the workflow), and more. Some will be back-end services that help speed the provider's work, and some will actually communicate with patients. We are all about to be inundated with/subjected to AI-assisted healthcare, whether we know it or not.
Subscribe to Taylor English Insights by topichere.
So, for most of our systems that have picked up on ambient AI, a listening device, the ambient part of it is listening to a clinical encounter, whether it be an outpatient visit, an ER history or inpatient rounds.
And on the back-end, the AI tool, usually what's now known as a large language model, such as GPT, then takes the spoken word between the multiple parties and constructs it into a new generative paragraph.
It's using the actual function of those large language models to generate a paragraph of content, usually then around a specific prompt. Given that model, "Please write a history based on this medical background."
/Passle/5fe0c4f453548a10fc881e09/SearchServiceImages/2024-02-06-16-16-46-327-65c25b6e9e14f56dc129e31c.jpg)
/Passle/5fe0c4f453548a10fc881e09/SearchServiceImages/2024-05-13-18-10-36-007-6642579ca261e1b4e2247625.jpg)
/Passle/5fe0c4f453548a10fc881e09/SearchServiceImages/2024-05-14-17-03-05-942-664399499011a769f969a8a2.jpg)
/Passle/5fe0c4f453548a10fc881e09/SearchServiceImages/2024-03-03-14-30-26-178-65e48982874d427f58ce6094.jpg)