You’re over-egging it a bit. A well written SOAP note, HPI etc should distill to a handful of possibilities, that’s true. That’s the point of them.

The fact that the llm can interpret those notes 98% as well as medical trained individual (per the article) is being a little under sold.

That’s not nothing. Actually, that’s a big fucking deal ™ if you think thru the edge case applications. And remember, these are just general LLMs. Were not even talking medical domain specific.

Yeah; I think there’s more here to think on.