Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I used Claude Code to get a second opinion on my MRI

antoine.fi

Post reply on HN
Print view View original

611–620 of 748 posts

Re: I used Claude Code to get a second opinion on my MRI

#611

Post by swiftcoder »

simianwords wrote: post #572
swiftcoder wrote: post #323

Earlier quoted context omitted.

Which would tell you what, exactly? The whole root of the problem is that the model doesn’t “know” either

This is untrue and probably shows lack of experience with using LLMs. In my experience, each time I get some hallucination, I can ask the llm whether it hallucinated or not and I get a correct response.

> each time I get some hallucination, I can ask the llm whether it hallucinated or not and I get a correct response.

You get a hallucination of a correct response, yes, and given that it's a yes or no question, this hallucination is more likely to be correct than the response to the original more complicated question. But make no mistake that it operates under the exact same constraints

Re: I used Claude Code to get a second opinion on my MRI

#612

Post by throwaway2037 »

AceJohnny2 wrote: post #117

> There's something incredibly peaceful about being in the hands of an expert you trust. [...] AI can absolutely shatter that feeling in an uncomfortable way [...] but I don't know if I can fully trust AI either. This really is key. We know we can't trust the AI, but at the same time we're also more comfortable asking the AI for clarifications or confronting it. Not having a time-bound appointment or paying by the ho…

You nerd sniped me with the story about your used car. What happened in the end? I really want to know! There are some fun YouTube channels that basically do the same. Someone who is an expert auto mechanic takes a used car to various repair garages and asks them to recommend a course of action.

Re: I used Claude Code to get a second opinion on my MRI

#613

Post by prmph »

wizzwizz4 wrote: post #606
prmph wrote: post #587

Earlier quoted context omitted.

I've also noticed the opposite problem: Sometimes the LLM, when asked a detailed question (probably with some lead-in), pushes back in a way that betrays that they fell back to general tropes without really considering the nuances of your specific context. This happens many times, and I usually have to lead the LLM through a chain of reasoning to prove to it that its objection, through generally sound, do not apply t…

> I usually have to lead the LLM through a chain of reasoning to prove to it What's the point of doing this?

So that hopefully we can go further in the discussion without it having to repeatedly bring up those (discredited) objections.

But it does forget, and I'd have to prime it again for another session.

Re: I used Claude Code to get a second opinion on my MRI

#614

Post by voidUpdate »

How do LLMs get information from images? Do they have to run essentially the opposite of an image generation model, taking an image and converting it into a description? I'm just concerned that the description wouldn't be able to encapsulate the information needed to differentiate exactly what is wrong with a shoulder. The image -> text model would need to know what it should actually report back to the LLM about the image, so that it doesn't just say "this is an MRI of a shoulder" or similar. It would be like a layperson describing a bridge, and asking an engineer if the bridge is safe based on that description

Re: I used Claude Code to get a second opinion on my MRI

#615

Post by engeljohnb »

kgeist wrote: post #341

A few years ago (before the AI craze), I was misdiagnosed with tuberculosis. I had a chronic cough, and an outsourced radiologist at a clinic found signs of tuberculosis. The findings were sent to the city's tuberculosis hospital, as required by the country's law. The doctors there took the radiologist's conclusion at face value and required me to stay at their hospital for at least 8 months under a strict, prison-li…

A second opinion is a smart move if one has doubts about their diagnosis. Doctors make mistakes, and even though I've worked with countless great doctors, I've never worked a job where there wasn't at least one who was undiscerning, or downright lazy and negligent. It's hard to tell people to trust their doctor when I know there are plenty of doctors out there like this.

But AI as of right now is worse than any bad doctor I've ever worked with.

Re: I used Claude Code to get a second opinion on my MRI

#616

Post by namelessone »

throwaway2037 wrote: post #612
AceJohnny2 wrote: post #117

> There's something incredibly peaceful about being in the hands of an expert you trust. [...] AI can absolutely shatter that feeling in an uncomfortable way [...] but I don't know if I can fully trust AI either. This really is key. We know we can't trust the AI, but at the same time we're also more comfortable asking the AI for clarifications or confronting it. Not having a time-bound appointment or paying by the ho…

You nerd sniped me with the story about your used car. What happened in the end? I really want to know! There are some fun YouTube channels that basically do the same. Someone who is an expert auto mechanic takes a used car to various repair garages and asks them to recommend a course of action.

Sounds like a fun watch! What is the name of the channel?

Re: I used Claude Code to get a second opinion on my MRI

#617

Post by weird-eye-issue »

voidUpdate wrote: post #614

How do LLMs get information from images? Do they have to run essentially the opposite of an image generation model, taking an image and converting it into a description? I'm just concerned that the description wouldn't be able to encapsulate the information needed to differentiate exactly what is wrong with a shoulder. The image -> text model would need to know what it should actually report back to the LLM about the…

No, it does not work like that, it actually can process the image itself there is not an intermediate image to text step

Re: I used Claude Code to get a second opinion on my MRI

#618

Post by yread »

lucfranken wrote: post #581
yread wrote: post #115

Earlier quoted context omitted.

Because they might bias you. And because you have your own brain, training and experience

That does make sense but the order of it might be: doctor analysis. Then show LLM as double check to doctor. Doctor assesses and may keep en improve the doctors first analysis?

Another problem is that general models' performance just sucks. From an upcoming conf. talk (in pathology) where they ran 2 Medgemma models on 100 slides with known diagnosis:

> Results: Full concordance with the reference diagnosis was 8% (27B) and 5% (1.5 4B; McNemar p=0.68), while partial matches were 29% vs 20% respectively (McNemar p=0.053). When correct diagnoses anywhere in the differential were counted, 51% (27B) vs 30% (1.5 4B), with 27B significantly superior (McNemar χ²=12.1, p=0.0005). Site-level performance varied widely (30–100%). Both models reported HIGH confidence in ~99% of cases irrespective of correctness.

i.e. highly confident, wrong 95% of time. in 49% of cases the real diagnosis wasn't even on models' differential. Doctor can hardly improve using something they can safely assume to be just noise.

https://ecp2026.abstractserver.com/programme/#/scientific/de...

Re: I used Claude Code to get a second opinion on my MRI

#619

Post by voidUpdate »

weird-eye-issue wrote: post #617
voidUpdate wrote: post #614

How do LLMs get information from images? Do they have to run essentially the opposite of an image generation model, taking an image and converting it into a description? I'm just concerned that the description wouldn't be able to encapsulate the information needed to differentiate exactly what is wrong with a shoulder. The image -> text model would need to know what it should actually report back to the LLM about the…

No, it does not work like that, it actually can process the image itself there is not an intermediate image to text step

How does a Large Language Model process images then?

Re: I used Claude Code to get a second opinion on my MRI

#620

Post by throwaway2037 »

themantalope wrote: post #492

Radiologist. I don’t read MR shoulder exams in my day to day practice, but from the few pictures shown , I can’t conclusively disagree with the original report. These models are generally terrible at reading medical images. The amount of public training data on the internet compared to the number of scans a radiologist reads in training is minuscule. There’s obviously a ton of medical images in general but very few,…

No trolling here: Do you feel threatened by the advance of AI/LLMs with respect to your field? I would. I am a computer programmer, and it absolutely feels threatening.
Post reply on HN