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

321–330 of 748 posts

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

#321

Post by lazyasciiart »

ethbr1 wrote: post #297
kjellsbells wrote: post #259

Earlier quoted context omitted.

The problems isnt LLMs per se, it is the shift to trusting the output of the machine coupled with a decline in verifying that the output is reasonable. It's basically what your teachers warned you about with wikipedia in eight grade except applied to all areas of life, including medicine. Dictation is already high-stakes and LLMs do not automatically reduce that risk. Here is an example. My provider sent me this note…

> Again the problem is not dictation, or LLMs. The problem is humans ignoring their responsibility to check the output of a machine. 100%. Also, management. I wish someone would go ahead and coin an AI version of Amdahl's law that states the work speedup from AI is dependent on amount of unverified AI output used. Iow, if you 1:1 verified everything, there would be no time savings. Ergo, you get management saying (1)…

But that’s trivially false. There is an entire category of work where it is hard to come up with an answer and easy to verify the answer, which means that if you verified everything there would still be a large time savings.

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

#322

Post by w10-1 »

ricardobayes wrote: post #7

That might be doctors new nightmare: people who second guess everything with AI. Previously it was "google your symptoms".

It's not just the second-guessing. It's the getting in the ballpark but striking out: explaining in detail why they are not correct. A little bit of patient knowledge requires a tremendous amount of doctor time to explain away the ignorance.

It's a 180 for me: While I believe doctors should explain diagnosis or treatment decisions when asked, I don't believe they should be taxed with explaining away alternatives. In my anecdotal 2nd- and 3rd-hand experience, doing that is taking at least a third of their time (on roughly 5% of the patients who think demanding answers will make things better) -- with zero improvement to diagnostic accuracy or treatment effectiveness. Doctors already consult with other doctors, and it makes no sense for them to have to consult with ignorant patients or treat their AI psychosis on top of their disease. It doesn't increase patient autonomy any more than adding a steering wheel for child car seats would help toddlers learn to drive.

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

#323

Post by swiftcoder »

simianwords wrote: post #62
swiftcoder wrote: post #56

Earlier quoted context omitted.

Because you don’t have any way of telling if it actually used the image presented, or based it’s conclusions on a different image it made up

Really? You know you could just ask it.

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

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

#324

Post by doawoo »

perching_aix wrote: post #303
janmatejka wrote: post #205

Earlier quoted context omitted.

Because some people develop actual psychosis. They go down some rabbit hole with an LLM until the LLM makes them believe they invented new kind of physics that makes them go harassing experts who obviously try to ignore them because its all nonsense.

Graciously diagnosed for them by random unqualified people on the internet with an agenda, frequently before even any relevant interaction: "Oh you like LLMs? You must in AI psychosis!" Let's not pretend it is anything more than the run of the mill wet fart of a culture war label. It's quite literally the "TDS" of the anti-AI crowd.

That's really not the argument being made here, and you're panning it further by claiming this is staunchly anti-LLM.

The idea here is to signal that you can absolutely use LLMs to help you figure something out. But also, they're wrong a lot. So use your own brain too.

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

#325

Post by linsomniac »

nostrebored wrote: post #97
linsomniac wrote: post #91

~2 years ago I used ChatGPT "deep research" to investigate a chronic sinus infection I'd been fighting for ~3 years. After seeing 3 GPs and 3 visits with an ENT, I fed all the observations I had into the AI. In particular, I couldn't get the ENT to explain why he visually saw, via a scope, evidence of allergic reaction in my sinuses, but then later concluded, after an allergy test, that it couldn't be treated via all…

Daily allergy tablets are associated with huge increases in early onset Alzheimer’s. Glad you found something that works, but might be good to get some of the allergen injections :)

That seems to be only for first generation, drowsy-making, tablets. Second gen formulas don't cross over the blood/brain barrier.

https://www.myalzteam.com/resources/zyrtec-and-alzheimers-me...

There IS one year-old finding that suddenly stopping Zyrtec after daily 3-month use may lead to nasty itching, and if that happens you can re-start and then taper off. https://www.fda.gov/drugs/drug-safety-communications/fda-req...

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

#326

Post by aetherson »

operatingthetan wrote: post #286
aetherson wrote: post #279

Earlier quoted context omitted.

You're confusing the training method with the internal process. If I had you repeatedly attempt to learn how to make believable completions of partial documents about a given topic, you would eventually learn things about that topic and could use your knowledge to create more believable completions of documents about that topic.

LLMs do not learn. You put it out to pasture and create a new one. "Memory" in a session is essentially a context window party trick.

They learn during training, which is what we're talking about.

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

#327

Post by linsomniac »

darkwater wrote: post #143
nostrebored wrote: post #97

Earlier quoted context omitted.

Daily allergy tablets are associated with huge increases in early onset Alzheimer’s. Glad you found something that works, but might be good to get some of the allergen injections :)

Wait, what?? Now I'm getting in panic mode because I do take regularly anti-hystaminic tablets/pills (the newer ones, based on ebastine because they don't make me feel sleepy)

You don't seem to need to worry, second gen tablets seem to be fine: https://claude.ai/share/9c6eaaa5-e734-4267-b540-ddc0188daf6b

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

#328

Post by aetherson »

goodpoint wrote: post #307
aetherson wrote: post #279

Earlier quoted context omitted.

You're confusing the training method with the internal process. If I had you repeatedly attempt to learn how to make believable completions of partial documents about a given topic, you would eventually learn things about that topic and could use your knowledge to create more believable completions of documents about that topic.

believable != true

Sure. But that's not the subject.

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

#329

Post by FromTheFirstIn »

aspenmartin wrote: post #310
operatingthetan wrote: post #299

Earlier quoted context omitted.

I consider that to be the illusion of learning. You are not wrong, I think they may actually learn in the future though. But not today.

That’s strange to me, what would you define as learning?

To acquire new knowledge and build your understanding. They don’t understand so they can’t learn

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

#330

Post by david-gpu »

rafterydj wrote: post #15

I feel like I'm going nuts. There are other commenters saying this is a good practice they've also done for other injuries. You are saying you are an actual radiologist and immediately clock the problems with its advice. I have seen this pattern over and over again. Anytime someone is an actual expert at anything, AI output appears insufficient or incomplete or outright misleading. It is only when you do not know wha…

Last week I went to a highly-specialized tertiary clinic about further treatment for a rare medical condition that I was diagnosed and treated for as a child. The two very specialized doctors I met there confirmed a diagnostic mistake that a specialist had made ten years ago. The only reason I pursued a second opinion, ten years later, was because Google Gemini had explained to me that the specialist ten years ago had performed the wrong type of test for my condition.

Do these LLMs make mistakes? They sure do, I see it all the time. But they can also help people make breakthroughs.

And this isn't the only time that Gemini has helped me diagnose long-term health issues, either.

I am not advocating to trust anything they say blindly, but they can be a great place to form new hypotheses and learn the right terms to look for when you are unfamiliar with a subject.

Post reply on HN