A tool like this would revolutionize the relationship busy healthcare workers relate to hospital policies and stop the stifling “That’s against policy” that we get when we are trying to do something innovative for our patients
Hey nostr:npub1cmmswlckn82se7f2jeftl6ll4szlc6zzh8hrjyyfm9vm3t2afr7svqlr6f and anyone else familiar with LLMs… nostr:npub1hudtuvkqr970j7s4lgsqf937wjme7khntgt99zdzrsxd05ax3lyqzlvgug and I were interested in setting up a tool that allows us to query our current local policies.
For example, if I have a patient that needs to stay intubated from the operating room (breathing tube), it would be helpful to ask: “Am I allowed to bring this patient to the Post Anesthesia Care Unit, and if so what are the specific monitoring requirements that we have in our policies?”
Is this something very challenging to setup? We have all the policies available, and it’s always extremely time consuming going through them to find the answer. #asknostr
Discussion
nostr:npub1h8nk2346qezka5cpm8jjh3yl5j88pf4ly2ptu7s6uu55wcfqy0wq36rpev - any guides you recommend on setting something like this up?
Probably Paul Itoi, Obi Nwosu, or Kody Low would be good resources, but I’m working on figuring out a lot of this stuff myself and will have my own versions of walkthroughs when I get there. Just stuck on my Ai machine still so everything’s held up by it.
Lots of people are building these sorts of things and I would probably use PremAi if I was trying to accomplish it. But you need a good LLM combined with a solid knowledge graph. You could probably do a LoRA style training of the LLM on the actual policies as well, while having it pull information from the source, but just so it better understands the context.
Maybe something similar to Perplexity Ai would be useful here if you can give it your own data source.
I remember something that might be useful but give me a bit to find it. Looking now…
Fuck… another GD rabbit hole
