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

921–927 of 927 posts

Re: Midjourney Medical

#921

Post by bsiverly »

zephyreon wrote: post #677
nlkkjhlkjsd wrote: post #662

Earlier quoted context omitted.

I've been reading this website on and off for years now, and I remember one time I read that a silicon valley startup was selling a "smart cup" that would send you detailed statistics of how much water you drank (assuming you used your smart cup for every drink throughout the day). I suspect if I pitched this to doctors, they would say just drink when your thirsty; you don't need all that data. But that's not the poi…

> But considering they first plan to deliver this in a fancy spa, and that it's coming from a tech company, not pharma, my reflex is to question the medical value of this data. I would be remiss if I didn’t point out that the entire pharma industry is not exactly known for their motivation to research and develop therapies for the betterment of humanity. Case in point, the opioid crisis, wherein pharma’s goal was to…

It all depends how many times I need to go to their med spa to get the benefits of the imaging.

Re: Midjourney Medical

#922

Post by adjejmxbdjdn »

AbsurdCensor wrote: post #651
rvrs wrote: post #604

Earlier quoted context omitted.

>A) proactively keeping me healthy, This will never happen and arguably should not be the *medical* system's problem. It is just not feasible

I thought this was the main goal of things like preventative medicine. Earlier testing, and more frequent testing allows you to catch things while you still 'feel healthy' so they do not become a chronic problem in the long term. Simple things like tracking weight, blood pressure over time. Add in things like colonoscopies, breast exams, I would say most medicine should be preventative, ie keeping you healthy, rather…

Unfortunately most doctors’ training simply doesn’t cover preventative medicine. Most medical schools teach doctors pretty much only to respond to medical situations.

For example, a root cause of why there’s so much confusion among the general public when it comes to diet is that doctors receive very little nutrition training (maybe one course in their entire medical degree), so they know little about what the nutrition scientists are saying and have almost no knowledge of the primary literature and how to read and contextualize it.

And yet most people will give far more credence to doctors for nutrition advice over actual nutrition scientists and researchers even though the latter have real knowledge about the science, whereas the former are largely basing their ideas on conventional wisdom, or lately pushing fad/extreme/industry paid for diet because they realized they can make money off of it.

Things are improving, such as with heart disease doctors and their industry bodies because the link between diets high in say saturated fats and cardiovascular disease is so clear, they cannot ignore it, but the medical field has a long way to go still.

Re: Midjourney Medical

#923

Post by genocidicbunny »

owenpalmer wrote: post #920
genocidicbunny wrote: post #82

Earlier quoted context omitted.

> What's so bad about having some false positives? Having invasive surgery. Undergoing chemotherapy. The former is bad, the latter is basically a 'lets hope it kills the cancer before it kills you' situation. It's arguable which one is worse, but I'd rather not have to ever partake in either of them again.

Why would you jump from an ultrasound to chemotherapy? It's not meant to be a definitive diagnosis, it's just an early screening process...

Because that was exactly the jump for me. Ultrasound led to expedited surgery that happened within 2 weeks of the ultrasound. The results of the surgery led to chemotherapy. It wasn't long between the ultrasound and BEP being hooked up.

Re: Midjourney Medical

#924

Post by hannasanarion »

hn_throwaway_99 wrote: post #892
jmhmd wrote: post #880

Earlier quoted context omitted.

This is a critical point. I am curious what the team building this looks like? Do they have ultrasound physicists and clinical practitioners in addition to the AI researchers?

> I am curious what the team building this looks like? Do they have ultrasound physicists and clinical practitioners in addition to the AI researchers? Related to that point, I was so turned off by Midjourney's post about this because it absolutely reeked of all the red flags I've seen over the past 2 decades when Silicon Valley-types try to "disrupt" the medical field. The post was titled "Midjourney Medical", but i…

> The post was titled "Midjourney Medical", but it approached everything from a "wellness" perspective, i.e. how can individuals "optimize" their health by numerous scans/tests/analyses, it's a spa not a clinic, etc. etc.

Could this not be a regulatory thing? I am an idiot who knows nothing, but if I had a new device that I thought had medical potential, and I wanted to get some press, investment, maybe a little hype going before I was ready to seek regulatory approval, this is exactly what I would do, market it as a wellness device first, because if I say that my prototype is installed in a "clinic" i might start getting suspicious looks from the FDA that can make life harder when I do eventually apply for medical device approval.

Re: Midjourney Medical

#925

Post by mapkkk »

evrydayhustling wrote: post #889
mapkkk wrote: post #665

Earlier quoted context omitted.

This is exactly why it's a bad idea. I agree that if this technology comes to fruition, it should be in every clinical and research setting as a tool for us to further our understanding. It shouldn't be a commodified test anyone can do at any time they feel like it. There are so many examples this leading to over or misdiagnosing already. I've seen patients who thought they had diabetes because they got a CGM over th…

Understood; these are the failure modes of cheap, weak tests in a system designed for expensive, high signal tests. I get that it is causing a real pain when these are introduced willy-nilly -- so is there a way for the medical system to evolve into making productive use of such signals? Because the status quo is not working for a lot of folks in managing their own health, and just saying "it has to be this way" --wh…

This is a tough problem for sure, and I resonate with your sentiment that something has to be done with it.

In my personal (fully anecdotal) view, I think clinicians desperately need to get better at communication, as well as meta-communication. Right now the rift between the patient and practitioner is enormous, because Drs do not take the time to dutifully explain things and processes, and what pitfalls there may be, and like you said, just boil it down to "it has to be this way" and shrug.

Some of this is down to systems design, i.e. not enough time per patient;insufficient support staff (simple example is no nurse being present to take down history concurrently as you spend time with the patient, or no dictation facilities available so you have to manually type everything down during the consult, eating away what precious time you have w/ the patient); a specialist getting bombarded with things a generalist should have treated w/ no referral needed; jurisdictions where violence towards healthcare workers is prevalent and so on..

But I would wager that compassionate listening and communication is the lion's share in why there's this huge rift. We currently do not teach effective communication in medical school, students just see how their attending treats a patient, and they copy their style. Which is funny, because the first thing we were taught in preliminary internal medicine was that 80% of making a diagnosis (any diagnosis) is down to history taking and communication.

As for how exactly we would get institutions to take communication seriously, I have no idea.

Re: Midjourney Medical

#926

Post by mapkkk »

spongebobstoes wrote: post #656
mapkkk wrote: post #645

Earlier quoted context omitted.

We can and do full body scans. Typically in the context of research, or for focus/metastasis search in current clinical settings. The problem is that, in clinical practice, with every imaging technology there are trade-offs. Just because we see something out of the ordinary in a scan doesn't immediately tell us whether it's pathology, pathology worth investigating/treating, or if it's just a normal physiological vari…

"the people can't be trusted with knowledge" is a bad argument we don't need to do much differently to take advantage of this data anyway. doctors already ask patients what changed recently collect data passively. when a medical condition arises, you have a data source to correlate against the onset of the condition currently we have almost no data, so doctors need to run multiple tests to identify possible causes

It's not that I don't believe people can't be trusted with information. I regularly introduce basic diagnostic/statistical concepts to patients to explain why a certain test is needed, and why another would be wasted time and anxiety.

Tools are only effective in their purpose when one knows when and how to use them. Most things are imperfect, or a game of balancing benefits vs. shortcomings.

If a patient learns the potential pitfalls and strengths of a testing method, then I would trust them to apply it judiciously. But a biweekly medical scan you can go to as easily as a spa is not that.

Similarly: data matters, sure, but the quality of the data matters just as much. If the signal to noise ratio is too low then what's the point of gathering it?

Re: Midjourney Medical

#927

Post by lonely_wanderer »

nihonde wrote: post #535
lonely_wanderer wrote: post #166

Earlier quoted context omitted.

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 c…

I have thought about your position more and I realize I basically agree. More data isn’t strictly good, but in the right hands it is useful, and that choice should be left to individuals.

Also, it makes sense to me that, as technology improves and becomes cheaper, we should utilize it more. It may take time to come up with the proper process to maximize usefulness and reduce false positives, but it’s the path of progress.

I hope that in the future, humans consider it barbaric that we weren’t aware of things like cancer and tumors at the earliest stages, even if in many cases there’s no treatment necessary.

Post reply on HN