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

One whole-body MRI could replace multiple cancer scans

pharmatimes.com

Post reply on HN
Print view View original

141–150 of 236 posts

Re: One whole-body MRI could replace multiple cancer scans

#141

Post by nathan_f77 »

jedberg wrote: post #111

I've had this idea floating in my head for a while. Provide free annual full body MRIs to people, including being read by a radiologist, which they can take to anyone they want (doctor, lawyer, whatever). In exchange, they agree to send the org a copy of all their past and future medical records. The records are anonymized and tied to the MRIs. The MRIs and medical data is then pumped through machine learning algorit…

I've had the same idea for a long time, and I'd also like to see a charity start doing this. It's crazy that so many people are saying this is a bad idea. I think it has the potential to save millions of lives.

I was very tempted to join an AI startup in a similar space, but I decided to turn down their offer because they were a for-profit company, and that just didn't feel right. The offer was also too low, but I would have probably joined if they were a non-profit.

Re: One whole-body MRI could replace multiple cancer scans

#142

Post by koboll »

canada_dry wrote: post #128
paulsutter wrote: post #52

Earlier quoted context omitted.

You're describing a problem with the doctors, not a problem with the scans. I'm curious to understand the real motivation to avoid information. Is it something in the system, litigation risk? There are many ways to deal with incidentalomas. If full body scans were more widespread, maybe doctors would have confidence to deal with them properly. For example, watching them over time.

> watching them over time In my mind this is the key... a way to frequently and conveniently do a full body scan so that anomalies can be detected via the delta. Scanning and detection is a problem that likely could be tackled via machine learning. I'm hoping it's not too long before a method is developed where a low res MRI like scan is feasible at home (e.g. using radio or ultrasound). Done on a regular basis the s…

There is a point at which the radiation you're receiving from regular scans becomes harmful enough to outweigh the benefits of early detection.

Re: One whole-body MRI could replace multiple cancer scans

#144

Post by koboll »

louden wrote: post #118
nnq wrote: post #115

Earlier quoted context omitted.

MDs are idiots in this regard. Mainly because they've been thought medicine by other idiots. They have this stupid idea that "too much data" is bad, also stuff being a sign that you're a bad doctor if you order too much tests etc. It's a whole can of worms of crappy rationalizations here, that also hides the fact that doctors are not capable or trained to correctly deal with large volumes of data, so they know they w…

More data is not always better. The collection process itself can be dangerous or unpleasant for the patient. Several years ago I worked on a study looking at the spread of bacterial lung infections in long term hospital patient. In order to get the data, we would have to intubate patients that did not need it. In this case, the people who approve these studies rightfully ruled that getting that data would be too pai…

>In order to get the data, we would have to intubate patients that did not need it. In this case, the people who approve these studies rightfully ruled that getting that data would be too painful for the patients to allow.

I wonder what the patients who died because they had especially fast-spreading infections whose pace was not detected quickly enough would think of these altruists' wise decision to weigh the median level of "emotional distress" more highly than their lives.

Re: One whole-body MRI could replace multiple cancer scans

#145

Post by louden »

Brakenshire wrote: post #126
louden wrote: post #118

Earlier quoted context omitted.

More data is not always better. The collection process itself can be dangerous or unpleasant for the patient. Several years ago I worked on a study looking at the spread of bacterial lung infections in long term hospital patient. In order to get the data, we would have to intubate patients that did not need it. In this case, the people who approve these studies rightfully ruled that getting that data would be too pai…

> The collection process itself can be dangerous or unpleasant for the patient. That’s asinine, obviously he doesn’t mean more data is always better even if the test is invasive or dangerous. > Biopsies caused by benign findings from a full body scan are not without pain, emotional distress, risk or cost to the patient. Period. It must be weighed against the benefit that the patient would recieve (all in the aggregat…

In medicine, there are physically harmless tests that can still cause harm. Full body scans are one of them. If something is found, it will likely have an emotional impact on the patient. Not all people are equally rational. Not all people have a good grasp of the statistical nature of the findings. That applies to educated people and medical professionals who deal with this stuff everyday.

My point was not that either side was correct but rather that a simple statement like "more data is always better" is not as simple as they seem to think it is. Those of us who work in this field deal with balancing the risks as best we can so that we can detect the marginal elevated risk of something in a way so that the benefit outweighs the costs (financial, physical and emotional).

Re: One whole-body MRI could replace multiple cancer scans

#146

Post by jlpom »

refurb wrote: post #137
jlpom wrote: post #136

MRI are generaly considered safe but my personnal experience contradict this. I passed a 3T brain MRI (with gadolinium injection for angiography) ~80 days ago and my life has been seriously painful since then. I have experienced hypertension (often >170 of systole, seem unrelated but never had high tension of my life and like the rest of theses issues it appeared exactly after the MRI), sleep issues, head difficultie…

Reaction to the contrast agent?

A general practitioner redirected me to a neurologist, hopefully he will find out.

Re: One whole-body MRI could replace multiple cancer scans

#147

Post by saulrh »

stcredzero wrote: post #135
mattkrause wrote: post #112

Earlier quoted context omitted.

You're understating the costs. Determining whether something is (non) malignant isn't trivial. It often requires a more invasive test (e.g., biopsy, exploratory surgery). We try to avoid those procedures not just because we're cheap or afraid, but because they have a real risk of harming us 'squishy humans'. For example, detecting prostate cancer a few months earlier is often not a huge win on its own. It is even les…

You're understating the costs. I think you're correct in the current context. However, this strikes me as a sign of some kind of paradigm shift waiting to happen, enabled by the reduced cost of data gathering, data processing, and improvements in AI. There was a time when many things which are mass produced now were once handcrafted luxury items. Perhaps, as technology improves, it will one day be cost effective to t…

  Perhaps, as technology improves, it
  will one day be cost effective to
  take a whole body scan into account.
That's the really funny thing about this: A colossal library of full-body imaging studies over time is exactly the kind of technology that would make that library useable. Think about Google 411 and similar projects: Voice recognition was unusable until people dumped a ton of money into bootstrapping the necessary datasets and now I talk to my phone every day. Similarly, I bet that a bunch of that "anomalies are indistinguishable on images" is solely because we don't have enough images about non-malignant anomalies over time. The data itself would be the technology that makes it usable.

Re: One whole-body MRI could replace multiple cancer scans

#148

Post by Brakenshire »

epistasis wrote: post #130
Brakenshire wrote: post #126

Earlier quoted context omitted.

> The collection process itself can be dangerous or unpleasant for the patient. That’s asinine, obviously he doesn’t mean more data is always better even if the test is invasive or dangerous. > Biopsies caused by benign findings from a full body scan are not without pain, emotional distress, risk or cost to the patient. Period. It must be weighed against the benefit that the patient would recieve (all in the aggregat…

> but only the biopsy needs to be weighed against risk, not the scan. You're setting an arbitrary boundary because you don't want to consider the downsides. If you set the same boundary on the benefits of the MRI, then you wouldn't be able to include treatment of cancer as part of the upside to doing an MRI scan. Doctors are far wiser about these things than HN commenters that have never dealt with the complex tradeo…

People can (and did) make the same case against the thermometer.

Re: One whole-body MRI could replace multiple cancer scans

#149

Post by louden »

koboll wrote: post #144
louden wrote: post #118

Earlier quoted context omitted.

More data is not always better. The collection process itself can be dangerous or unpleasant for the patient. Several years ago I worked on a study looking at the spread of bacterial lung infections in long term hospital patient. In order to get the data, we would have to intubate patients that did not need it. In this case, the people who approve these studies rightfully ruled that getting that data would be too pai…

>In order to get the data, we would have to intubate patients that did not need it. In this case, the people who approve these studies rightfully ruled that getting that data would be too painful for the patients to allow. I wonder what the patients who died because they had especially fast-spreading infections whose pace was not detected quickly enough would think of these altruists' wise decision to weigh the media…

People have commited suicide because of medical test results that turned out to be wrong. A decision has to be made about how many tests are performed and under what conditions. Unfortunately, that will cause harm to people no matter where we, as a society, draw that line.

Re: One whole-body MRI could replace multiple cancer scans

#150

Post by petschge »

canada_dry wrote: post #128
paulsutter wrote: post #52

Earlier quoted context omitted.

You're describing a problem with the doctors, not a problem with the scans. I'm curious to understand the real motivation to avoid information. Is it something in the system, litigation risk? There are many ways to deal with incidentalomas. If full body scans were more widespread, maybe doctors would have confidence to deal with them properly. For example, watching them over time.

> watching them over time In my mind this is the key... a way to frequently and conveniently do a full body scan so that anomalies can be detected via the delta. Scanning and detection is a problem that likely could be tackled via machine learning. I'm hoping it's not too long before a method is developed where a low res MRI like scan is feasible at home (e.g. using radio or ultrasound). Done on a regular basis the s…

Obtaining the delta from two different images is actually non trivial. And contrary to what HN thinks, not every problem is trivially solved by machine learning.

Small point aside: an ultrasound scan -- even if it was every feasible at home -- would not be an MRI. MRI means you use the spin echo and relaxation of nucleii (mostly protons for medical MRI). It is not a generic word for "please give me a 3d image". Words have meanings, especially when they are technical jargon, and it is important to not dilute that if we want to be able to communicate efficiently and effectively.

Also: technology that is more mature than software tends to improve at a more measured pace, as all but the hardest breakthroughs have been obtained already. It is therefore unlikely that you will be able to replace a 10 million dollar machine by things in your home any time soon.

Post reply on HN