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

691–700 of 927 posts

Re: Midjourney Medical

#691

Post by sbarre »

nancyminusone wrote: post #676
moduspol wrote: post #643

Earlier quoted context omitted.

The way we figure out how to catch issues before you notice them (i.e. proactively keeping you healthy) and figure out the best ways to fix them (i.e. reactively helping you get back to healthy) is by having more data from more people in more situations, so we can make those determinations. I understand some of the current fatigue around biohacking and chasing perhaps-irrelevant metrics, but takes like this surprise…

I can easily and cheaply generate nore megabytes per second per dollar by oversampling a heart rate monitor at hundreds of megahertz. Hell, why not hook up a second channel to the same signal and record it twice for double the megabytes? Do you see the problem here? "yeah, but nobody's doing that" Well, then it certainly is odd of them to frame it tgat way, isn't it?

I think you (and others) are getting caught up in your own worse-case interpretation of the words of that statement, instead of looking at the intent of it.

It is perhaps not the best wording but I think it's pretty easy to take that "megabytes per second per dollar" statement and choose to interpret it less poorly, and more like "having better, cheaper and more abundant useful data about yourself and your health".

Re: Midjourney Medical

#692

Post by singpolyma3 »

StarlaAtNight wrote: post #642
spongebobstoes wrote: post #635

Earlier quoted context omitted.

do they need FDA approval to have a good impact? it doesn't need to be a licensed medical device for me to interpret the data, and then verbally tell my doctor what's wrong this is similar to how people get a lot of medical value out of chatgpt today

I wonder how doctors feel about people consulting ChatGPT. I know a doctor who can't stand people getting medical advice from quacks on TikTok, but that's probably a different problem/pattern

Since they hated Google I'm sure they also hate chatgpt.

Mostly they hate patients who have opinions

Re: Midjourney Medical

#693

Post by OGWhales »

GTP wrote: post #602
fastasucan wrote: post #586

Earlier quoted context omitted.

Because if a "condition" doesn't impact you, will it help to be aware of it? Over treatment can be a real problem. You dont want to take medisine you dont need, or spend much time in a hospital if there is no net positive outcome.

Just to add to this. My heart pumps blood in a known but different way than normal. I know because, to practice sports in my home country, it is required to undergo a specific checkup that includes an ECG. However, despite doing that visit many times, only two doctors ever mentioned this condition. The reason is that it causes no issue at all, so they just don't want to worry people for nothing by telling them their…

I would rather know that than have the information hidden from me. It's also not hard to imagine a scenario where such quirks are harmless on their own, but might be relevant in the future or for reasons the doctor is missing. I guess it's true some people would panic at any sort of quirk they find, but I find that frustrating as someone that doesn't think that way.

Further, as someone that has spent far too much time and money trying to find the root cause of a particular issue (with absurdly frustrating inefficiencies in terms of being bounced around, insurance nonsense, etc), I am generally in favor of improving our ability to find a lot of information in a manner like this. Doctors are generally good at finding very common issues they see all the time, much worse at anything uncommon. This can be a real problem. I think it could help the world a lot if we had something like this to improve our understanding of more outlier cases, we might find a lot of issues that were hard to catch without that scale of information. I also think preemptive scanning would catch a lot of issues that go otherwise unnoticed for much longer than they should go, something that also happened to me, but is mostly an issue of systemic inefficiencies in our current healthcare system rather than something that this technology is required to solve. In my case, doing some simple checks that they felt weren't necessary because I seemed healthy would've caught it much earlier.

Re: Midjourney Medical

#694

Post by ineedasername »

tmhrtly wrote: post #571

> You want as much data as you can get about your health as quickly and as cheaply as possible. In other words, you want a technology optimized for getting as many “megabytes per second per dollar” of information about your body. This is so far from my vision of what I want from healthcare. I want a healthcare system that is optimised around A) proactively keeping me healthy, and B) reactively helping get back to hea…

How do you keep robustly pro active without data? Of course megabytes of data isn't a direct measure of health. That also isn't what medjourney is proposing be the metric. They didn't say "doctors will review the storage requirements of your available data and be able to tell you...". It's a straw man. Comprehensive imaging isn't a full insight into health. Neither are many questions in a medical history. But accurate and easy to obtain medical imaging is certainly a strong addition. Neither are complete, both are extremely useful and important. It's defense in depth. Included in an annual physical, imaging from even existing methods would have saved the lives of more than one family member who died of cancer gone undetected despite following existing best practices for preventative health. It's also impractical and expensive, though cheaper than years before. Faster cheaper and more accurate seem better still when it will be an additional channel of information.

Re: Midjourney Medical

#695

Post by unholiness »

sroussey wrote: post #305
convnet wrote: post #287

Earlier quoted context omitted.

It's a controversial and complicated idea. The downside, and the reason why most doctors do not recommend full body scans, is that every human body is a bit weird and there will almost always be something "wrong" that will be visible in a full body scan. This can lead to unnecessary testing, anxiety, and even unnecessary procedures. Many of these oddities flagged by the scan would never have caused any actual issues…

If the whole population had a full body scan every quarter, the “weird” things would feel more like the noise they are. But we would have great data over time, both individually (weird tends to only matter if they are changing) and as a population.

Overdiagnosis will be a major problem long after we have the data.

It's just hard convince people with a general feeling something's wrong and a specific picture of something wrong that the two are almost certainly unconnected.

Re: Midjourney Medical

#698

Post by baggachipz »

renegade-otter wrote: post #654
randusername wrote: post #632

> Beyond that, regulation is the next limit. Normally, for every diagnostic medical capability you need FDA approval. We’re starting by just giving you detailed body composition maps — and we’ll be submitting regular test results to the FDA for increased capabilities. This is just not how the FDA works. At all. You can't just email them slideware and marketing materials to keep them in the loop. You have to hire an a…

That may be true, but the FDA is no longer run by fiduciaries of the United States.

Just grease the right tanned palms, and you're good to go!

Re: Midjourney Medical

#699

Post by KaiserPro »

aeonik wrote: post #570
GTP wrote: post #560

I find the technology side intriguing and worth a deeper dive. But I'm not convinced about their view of having people casually going to a spa every week and getting a full body scan. AFAIK, some doctors tend to avoid full-body scans. The reason is that each body is different and has its own quirks. If you do a scan for no reason other than "I can do it fast", chances are that the scan will show something unusual. Bu…

Why can't we do full body scans, learn about these "quirks", and document them in the wider science literature? I understand there are many benign tumors that doctors prefer to ignore in people, but eventually when scanning becomes portable and safe enough having regular access to scans could really help a lot of conditions.

Good question!

Full body scanning is expensive, and in some cases not that higher resolution. CT full body scans are cheap and high resolution, but you are being blasted with Xrays for long periods. So there is a not inconsiderable health implication.

To get good data, ideally you need to have a longitudinal study, as in you measure people monthly/weekly and then correlate that to life outcomes. The ethical issue is that you'll see lots of lumps and bumps growing, and this could lead to lots of invasive checks. You can't not check because that's not fair "here is something that looks like cancer, if we grab it now it will stop you needing chemo. But it could just be a cyst."

So, its really really expensive to have 100k people getting monthly full body MRIs for 10+ years. Even more expensive to get them at the right resolution.

I think, that if these scanners are good and that is _Very much_ not proven. Then having a long term study would be good. I however have deep misgivings about how effective field array ultrasonic scans are, also safety.

I also do not trust midjourney, a company that exists through large scale copyright infringement to handle that data safely, ethically or in a way that would allow decent science to be done from it.

Re: Midjourney Medical

#700

Post by andai »

christina97 wrote: post #685
moduspol wrote: post #643

Earlier quoted context omitted.

The way we figure out how to catch issues before you notice them (i.e. proactively keeping you healthy) and figure out the best ways to fix them (i.e. reactively helping you get back to healthy) is by having more data from more people in more situations, so we can make those determinations. I understand some of the current fatigue around biohacking and chasing perhaps-irrelevant metrics, but takes like this surprise…

GP is saying that the goal should be something entirely different from gathering lots of data. Do you think the average person wants a higher resolution time series of their weight, or better access to a higher quality doctor, cheaper?

The synthetic doctor is raised on megabytes.

(They need to be high quality megabytes, of course!)

Post reply on HN