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

711–720 of 748 posts

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

#711

Post by lazide »

brokencode wrote: post #707
lazide wrote: post #704

Earlier quoted context omitted.

I literally just grabbed a random link. I’ve seen dozens of real life examples of poisoning. The poisoning issue makes it so that no one can use the internet for training anymore, because more and more internet content is poisoned as a side effect - or poisoned intentionally. And .001% of poisoned data is enough to screw things up if included in the training data. It’s also one reason why Google search results have b…

You’ve seen actual model poisoning? Or have you seen a model return the wrong answer due to what it saw in a search result? Or were they hallucinations perhaps? How do you know it’s due to poisoned training data? And do you even realize how much data 0.001% of the training data for a frontier models is? They’re trained on 10s of trillions of tokens, meaning you’d need hundreds of millions of tokens of poisoned data.…

No shit Sherlock, of course I’ve seen it. It was my job.

This is exhausting.

It’s like arguing crypto with someone who has never actually committed a line of code. Why do I even bother?

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

#713

Post by harhargange »

I was building a pc and the ai was hellbent on saying either the cpu pins are bent or motherboard is faulty. Both giving me a panic attack. The solution came from updating bios which i had done so ai ruled it out. But the shop owner did the bios update again and it worked

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

#714

Post by thewanderer1983 »

throwaway762 wrote: post #438
thewanderer1983 wrote: post #420

I was diagnosed with a rare blood disease called Essential Thrombocythemia (ET) which is part of a group of diseases called myeloproliferative neoplasms. This happened about three years ago. Recently, I decided to get a second opinion and my new specialist changed my diagnosis from ET to Polycythemia Vera (PV). She also highly recommended I quickly go and give blood to lower my haematocrit levels as it put me at a mu…

Interesting. I am also diagnosed with ET (from platelet counts, pathology report noting abnormal platelet morphology, and JAK2 mutation from a marrow biopsy). What made you seek a second opinion?

My original specialist wasn't very engaged with my condition. I was getting the same speech every six month visit. On my last meeting she incorrectly stated a condition I wasn't having with bleeding. My wife had a thyroid issue a number of years ago including cancer growth on it. Her first specialist was using older techniques for her treatment. We ended up going to another specialist who's focus of research was her condition. It was worlds better. Given that experience I decided to find another specialist who focused on my condition.

The first specialist ( hematologist) was referred from local GP. She is a a hematologist, but she wasn't focused on MPNs.

I recommend joining your local MPN alliance to keep up with what's going on in this field. I also recommend finding a specialist with a focus on MPNs. Looks at their papers or listed focus.

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

#715

Post by brokencode »

lazide wrote: post #711
brokencode wrote: post #707

Earlier quoted context omitted.

You’ve seen actual model poisoning? Or have you seen a model return the wrong answer due to what it saw in a search result? Or were they hallucinations perhaps? How do you know it’s due to poisoned training data? And do you even realize how much data 0.001% of the training data for a frontier models is? They’re trained on 10s of trillions of tokens, meaning you’d need hundreds of millions of tokens of poisoned data.…

No shit Sherlock, of course I’ve seen it. It was my job. This is exhausting. It’s like arguing crypto with someone who has never actually committed a line of code. Why do I even bother?

You’re expecting me to know your job? Give me a break.

I’m wondering the same thing. You keep talking of some grand poisoning problem but can’t point to any specific public information except an article saying that it’s possible. As if that was ever in doubt.

Guess we’ll just have to agree to disagree.

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

#716

Post by deaux »

throwaway2037 wrote: post #622
deaux wrote: post #565

Earlier quoted context omitted.

Absolutely. It's very unfortunate that this post used the worst example possible of using LLMs for medical purposes. General-purpose LLMs are _fantastic_ at medical diagnosis that do not involve imaging. I am completely convinced that given enough information and time, frontier models already outperform >90% of doctors on initial diagnosis of internal issues and suggesting medical tests to further reject or confirm t…

> General-purpose LLMs are _fantastic_ at medical diagnosis that do not involve imaging. Can you share the reasons that you believe this? > At the same time, they're worse than useless at anything involving medical imaging. What is special about medical imaging that makes AI/LLMs specifically bad?

> Can you share the reasons that you believe this?

Firstly, please keep in mind I'm talking about the entire doctor population of the world here. Not sure which particularly bubble of this earth you have experience with, but note how half the word's population lives in India/China/Indonesia/Pakistan/Nigeria/Brazil/Bangladesh/Russia. Now I do believe that it holds the same for e.g. Europe and non-China East-Asia, but still.

How many patients has the world-wide average doctor seen? How long have they been a doctor?

How many have they seen with the particular condition the patient has?

How much time do they spend listening to and reasoning about a patient? The median in the world is likely under 3 minutes.

How many real-world incentives do human doctors have to deal with?

Given infinite time and resources, and zero external incentives, maybe the median human doctor would outperform the LLM at this task. But this is completely detached from the real world.

> What is special about medical imaging that makes AI/LLMs specifically bad?

LLMs: Besides lack of training data as mentioned elsewhere, they're simply not trained for high-fidelity image processing in general. It's not limited to medical imaging. It's a bit like the "How many Rs in strawberry" thing, but worse.

As for "AI" in general, medical image analysis is a very active field. These tend to be purpose-built though, not general-purpose. It seems likely at some point they'll become mainstream, but there's still a way to go.

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

#717

Post by RussianCow »

Esophagus4 wrote: post #639
RussianCow wrote: post #535

Earlier quoted context omitted.

Also, there are multiple "correct" ways to code something, so imperfect code that solves the problem is still useful. A medical diagnosis is either correct or incorrect.

En, I think you’re just trying to justify your pre-existing position that this can’t work. https://www.nature.com/articles/s41746-026-02619-0 https://www.nature.com/articles/s44360-025-00007-8?fromPaywa... Different prompt approaches and training doctors to use LLMs can improve accuracy of LLM-assisted diagnosis. It’s pretty reasonable to hypothesize that LLM “peer review” could improve that as well.

> En, I think you’re just trying to justify your pre-existing position that this can’t work.

I never said it can't work. I just said that finding the correct medical digagnosis is different than finding a solution to a software problem.

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

#718

Post by b800h »

ricardobayes wrote: post #554
b800h wrote: post #340

Earlier quoted context omitted.

Well it was a nightmare for my mother's do-nothing GP surgery in the UK. She had several conditions which were being handled completely separately without central coordination, and her health was in serious decline. We went in with a list of 20 AI-generated questions based on her conditions and treatment (which I was able to screen as I have a bio postgrad, but not medical training), including those related to NICE g…

UK has probably the worst healthcare in the developed world. In part perhaps due to UK blindly accepting any kind of medical degree (doctors and nurses) from all over the globe. Yes, you heard that right, they verify the validity of the degree but there is no formal standardized exam to sit to practice in the UK.

Her nurses frequently couldn't speak English. I had to spell out her medical conditions letter by letter so that the nurse could input it onto the medical system. She was entering gibberish / wrong info until I stepped in, as I was watching the PAS out of interest.

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

#719

Post by spwa4 »

capr wrote: post #708
spwa4 wrote: post #669

Earlier quoted context omitted.

Or more specifically in this case: the patient was obviously insisting on a diagnosis and treatment based on ... a slightly hurting shoulder, with zero visible or detectable phenomena. So the doctors gave him what he wanted: a treatment ... and Claude told him the treatment was a placebo. Correctly, I might add. Yeah, it is absolutely not what the patient wanted to hear. BAD doctors! Except ... no, not really. Does t…

so the doctors acted just like the LLM

Quite the opposite. The doctors are disagreeing with the LLM, and when the patient doesn't accept, they're putting in a minimal lie in the deontologically accepted way.

This seems to be to be near the opposite of what a sycophant (ie. an LLM) would do.

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

#720

Post by close04 »

microgpt wrote: post #401
close04 wrote: post #226

Earlier quoted context omitted.

I’m not sure what the “revelation” is? How is this related to what I said? Putting that aside, your philosophy sounds shallow. Death is certain, but how long you have to live and the quality of that life are not predefined. An incompetent passenger-pilot trying to save you from a crash will at worst make no difference. But an incompetent doctor can teach you that death isn’t necessarily the worst outcome.

There are many healthy psychological ways to accept the certainty of eventual death. But the process is inevitably painful. I think the different ways people accept death explains a lot of people's psychology, like how you can guess people's attachment styles or Freudian stage fixation. For instance, billionaires who pour all their money into anti-aging research clearly are not handling it well.

I thought LLMs are better than random weak sauce replies. Micro indeed.
Post reply on HN