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

Midjourney Medical

midjourney.com

Post reply on HN
Print view View original

531–540 of 927 posts

Re: Midjourney Medical

#531

Post by vasco »

lazyasciiart wrote: post #421
vasco wrote: post #341

Earlier quoted context omitted.

It's obviously a lie to get us to accept no tests due to limited machines. The same as when COVID started masks "didn't help" because they didn't yet secure enough supply for everyone, then when they did, suddenly the masks helped. Every system that exists as a black box is more understandable with more sensing, not less. Our bodies are not special. It's also ridiculous that the proposition goes like: 1. Doctor knows…

So do you think the doctors should hide the data from you so you don’t know anything looks weird, or tell you it looks weird but they don’t think it’s worth investigating it? And do you think the average patient will say “ok that’s fine, I’m not getting a second opinion and if I die my family will sue you into the grave too”?

I believe doctors should tell you the truth and not assume you will do things later that are detrimental with the information as that has a lot of bad consequences.

Case in point, doing that during COVID I think amplified the wave of antivaxxers and medical denialists. Which itself had in my opinion a way worse effect on global health than almost anything else recently because now you have to convince a number of people to trust the medical system again.

Re: Midjourney Medical

#533

Post by davrosthedalek »

A_D_E_P_T wrote: post #515
justaguyonline wrote: post #204

Earlier quoted context omitted.

AI hype aside, this is one of those projects I'd like to know the open source stack of and the academic research behind. It's actually overlaps with an idea that started circling around in my head back when (deep) neural networks were the new hype cycle. What's the relation between sensor density and resolution? If their array could give femtometer resolution, how much could you drop the density when you only needed…

> femtometer resolution The diameter of a carbon atom is 154 picometers. Nobody's going down into the femtos. And you're not going to get atomic resolution, either, because humans move around too much and things like scanning electron microscopes need very stationary samples. Even microscopic vibrations can blur the final image. Which isn't to say that you couldn't get very good resolution...

Just for illustration: Gravitational wave detection is on the femtometer scale. The proton is about that size. We can measure these things, but the machines are, let's say, "big".

Re: Midjourney Medical

#534

Post by bigfudge »

arcticbull wrote: post #352
aipatselarom wrote: post #308

Earlier quoted context omitted.

Hypertension is asymptomatic for years and is prevalent in every demographic. Leaving it unattended it can cause stroke, heart attack, or organ damage through long-term vessel strain, by which time damage may be irreversible; detecting it on time can prevent this with lifestyle changes and medication. Diabetes is asymptomatic for years and is prevalent in every demographic. Leaving it unattended it can cause damage t…

At least the top 4, unclear about the 5th, are strongly associated with obesity. That would make someone high-risk and testing potentially warranted in like 70% of the population. Asymptomatic and low-risk is what I said. The incidence of hypertension is so high in the general population it’s almost always statistically supported (even though basically every doctors office takes it wrong, even cardiologists, amazingl…

I mostly agree with you by one small wrinkle is that the evaluation of screening is normally against a criteria of cost effectiveness as well as safety. So for some conditions, if cost effectiveness was the barrier to rollout it might still be worth it if you are rich?

Re: Midjourney Medical

#535

Post by nihonde »

lonely_wanderer wrote: post #166
nihonde wrote: post #141

Earlier quoted context omitted.

In Japan, the government gives everyone a battery of full body tests at least once per year. I guess you know better than Japan, right? The whole argument that "you'll worry yourself sick" is such patronizing trash. It's obviously programming that came from the insurance industry, and you lapped it right up.

I think there’s actually a difference between getting a battery of tests from a set of doctors (overseen by the government) tailored to your risk factors and a company trying to sell a fully body scan which they think you should casually get all the time.

I don't think there's much difference? The technicians that perform the tests are not doctors. You usually see a doc for 5 mins at the end, to discuss any anomalies. Even then, they're just going to refer you to see your GP or a specialist. At the end of the day, the ningendoku is just information that your doctors can access. I'd much prefer a high-resolution full body scan.

Either way, the patient should make the choice about whether they want that info, not an insurance company or a know-it-all armed with a dubious study concluding that asymptomatic conditions are better left undiscovered.

Re: Midjourney Medical

#536

Post by nihonde »

Barrin92 wrote: post #183
nihonde wrote: post #155

Earlier quoted context omitted.

Rather than dealing with the issue—hypochondriacs or whatever—you prefer to remove the option for the non-hypochondriacs? The fact that doctors like your wife think that people who are concerned about their health and want more information is a problem tells me everything I need to know about your (and her) worldview. You've dressed it up as being pragmatic, but the reality is that you're arguing for censorship and a…

>that people who are concerned about their health and want more information is a problem It is a problem because there's evidence based standards for when examinations are indicated and prolong or improve a person's life. You being extremely concerned doesn't move that needle and subjecting you to tests simply because you're anxious is blatantly unethical and harmful to your psychological wellbeing. And nope this isn…

Something doesn't add up. The entire Japanese healthcare system is built around the idea that preventative testing for asymptomatic conditions is effective. You can read all about it, if you want.

Personally, I think you've swallowed some kind of health insurance industry black pill, whether you know it or not.

Re: Midjourney Medical

#537

Post by bigfudge »

vasco wrote: post #375
bigfudge wrote: post #374

Earlier quoted context omitted.

This kind of thinking (that it’s an obvious lie, perpetrated by a cabal) is the sort of superstitious bullshit that is going to jet us all killed. Look up Bayes theorem. As yourself how good a test would have to be if the base rate is low. Wonder what the probability of harm might be if the next advised test was invasive and the patients was anxious because a lump had been detected.

You should read til the end! No cabal, just stupidity and believing other people are stupid instead of telling them the truth and expecting them to act smart based on the information. Ask yourself, do you think billionnaires have yearly MRIs or that they wait for later because the doctor and themselves will be anxious? It's an argument that treats regular people as stupid.

First, many regular people are “stupid” in the sense that they do get anxious about things that ar slow probability and are not anxious about things that are high probability.

If you are a billionaire you also have a doctor with the time and expertise to properly evaluate the evidence in a Bayesian framework, and you have time to talk to them and understand and implications. That isn’t scalable.

Also, it’s quite likely that billionaires are having lots of unnecessary procedures and that harm is being caused. The mri scans are not the reason they live longer!

Re: Midjourney Medical

#538

Post by someothherguyy »

nirui wrote: post #392

I watched the video first without reading the text and thought, wow, Midjourney has gotten really good, they generated debris in the water exactly like what would happen in real life if the water is reused enough. Then I started reading the text, and realize it's not an ad for their video generating tool? Cool if each of it can do ~120000 scans per-month. But if I have to step in to a tank filled with debris and disc…

water filtration seems like the easy part

Re: Midjourney Medical

#539

Post by jibal »

jibal wrote: post #342
adastra22 wrote: post #259

Earlier quoted context omitted.

Only if you let them. The false positive thing is a nonissue that only arises from assuming you would respond to information a certain way.

That makes no sense at all, unless you're saying that people should respond to all such information by ignoring it.

P.S. The responses ignore what I actually responded to, which was a claim that "The false positive thing is a nonissue" -- where the "thing" is 99% false positives. The only way to respond to information such that "the false positive thing" becomes "a nonissue" is to never respond to it at all. The responses to my comment all address some strawman.

Re: Midjourney Medical

#540

Post by torginus »

arcticbull wrote: post #273
tgsovlerkhgsel wrote: post #233

I think a lot of medical diagnosis could be solved with mass data collection if it was cheap enough. Right now, blood draws are somewhat routinely done because they provide a lot of human-interpretable indicators from a small number of values, and there is some evidence that e.g. "dogs can smell cancer" etc. (i.e. some diseases cause detectable odors). With a big enough data set of [all kinds of bio values, including…

Don’t make me tap the sign. Bayes Theorem: https://en.wikipedia.org/wiki/Bayes'_theorem There’s a very good reason we don’t test asymptomatic people in low incidence populations. Basically all positives are false positives when you do that, no matter how accurate the test is. When you’re testing healthy randos for everything the odds of a positive being false have so many 9s it would make an SRE weep. Unless this is…

This is why you have multiple successive panels. If there's a disease that happens for 1 in 10k people, and you have a test with 1% FPR, 99 of 100 people will be false positive.

But what you can do then, is either run a more expensive, elaborate test or one that's proven to be statistically independent on the positive testing population.

FPR can even be a good thing. Let's say you have an expensive test with a very low false positive rate. Then you can mix together 100 samples, and get a test with a much worse FPR 100 times cheaper. Then you can repeat the same individually on the positive population.

This is fully automatic and you don't even think about it. Btw, this is why mass testing, and public healthcare can be better. You can amortize the cost of things across a large number of people for no disadvantage.

Post reply on HN