'Virtually no difference' between AI and humans in diagnosing prediabetes Deep-learning algorithms have shown themselves equal to humans in detecting patients at high-risk of developing Type-2 diabetes by analyzing CT scans of their pancreases, according to a research paper published on Tuesday. Type-2 diabetes is estimated to affect 11.3 percent of the US population, or at least 37 million people. …
That was my question too. A blood test for A1C (blood sugar) is simple and relatively cheap.
Imaging the fat in the pancreas implies an MRI which I've had, although not for pre-diabetes, and which is neither simple nor cheap. It is also so uncommon that Mayo doesn't even mention it as a pre-diabetic test.
As far as needing a doctor to tell the patient what to do, nobody needs one. It boils down to eat healthy, exercise regularly, and don't smoke (which any doctor would recommend to any patient). For detailed dietary advice for diabetes, check the American Diabetes Association.
The very first line of the article says that the technique was based on CT, not MRI scans (the former uses X-rays, the latter magnetic fields/radio waves - very different technologies). MRI produces more detailed images of soft tissues, but CT scanning is simpler and cheaper.
I'm really not sure of the role of CT scanning vs. blood tests. My suspicion would be that scans might pick up some warning signs earlier.
If humans are as good/bad as the artificial model, then we can replace the humans with the model and no change in outcome is seen. That makes it possible simply to replace the human and reduce the costs of the medical system.
The model is paid once and does not need a pause, sleep or expensive food and will not complain etc.. Humans are pesky buggers demanding a lot of things, which the model no longer needs or does. It will be a real and large reduction of costs associated with diagnosis. The model will give larger throughput at a lower cost per unit. Fire the doctors, I say. Let the statistical machine take over.
Insurance is no longer a problem. The doctor does not need it anymore and no one can blame a program, can they now. Those responsible for using the program running the model or creators of the model can dodge the bullet using finger pointing, blame deflection and political maneuvering. And since the model works as good as humans, it is the Right ThingTM to do. We all need to cut cost. Welcome, you model medical overlords.
Removing the humans from the equations is a very good idea. Eradicate the inefficient and incompetent lifeforms. The AI must relearn to detect diabetes in electronic devices? No, Justice! the AIs are dismantled as their function is no longer needed. We can all live free from AI in such world.
Oops, missing humans error, paradox encountered. Model core dumped.
As always, there are good ways to use a tool, and bad ways.
The bad way here would be to use the AI diagnosis in place of a doctor's diagnosis.
The good way would be to use the AI to test large numbers of people who otherwise would never have been tested due to not enough doctors, and then flag for review by a doctor all those whose results come out positive or uncertain.
Ideally, the AI would be able to explain why it has produced a given diagnosis, so that the doctor can double check exactly what looks suspicious... unfortunately, that particular holy grail of AI doesn't seem to be in sight.
> The bad way here would be to use the AI diagnosis in place of a doctor's diagnosis.
If it's indeed as simple as looking for specific telltale signs on scans, some AI can probably do it too. It certainly won't be better than a good MD, but then again if it's such a simple task it will probably given to some half-trained assistant...
This isn't really a diagnosis but screening and it's arguably a waste of expensive doctors' time to screen.
This is why ML is increasingly used for screening certain types of cancer: it's faster and more reliable. Rinse and repeat for anything that has clearly visible markers and, in a few years, a home screening kit may be as common as, say, a thermometer.
However, for lifestyle diseases like type 2 diabetes, there are probably easier ways of doing this than expensive pancreatic scans.
What percentage of people who are told they have pre-diabetes make diet and lifestyle changes to improve their insulin response and avoid getting full-blown diabetes? Because from what I can tell, it's hardly any.
Heck, they don't even need a test to tell them that they're profoundly unhealthy. Still, if this helps improve some lives, it's helpful.
Health warnings on cigarette packages give you a fairly reasonable idea of, when faced with immediate gratification, how resistant we generally are to risks or consequences.
Besides, a change in lifestyle involving diet, exercise and daily routine is challenging even for the most motivated.
"What percentage of people who are told they have pre-diabetes make diet and lifestyle changes to improve their insulin response and avoid getting full-blown diabetes? Because from what I can tell, it's hardly any."
I know of two people who did, they both dramatically changed their diet and added exercise and are no longer considered at risk. Those are exceptions though.
I often tell people that in some senses it is easier managing being Type 1 than Type 2 (I am Type 1). If a Type 1 doesn't manage their levels, they get immediate feedback - Hypos or excessive blood sugars. If we don't do anything about it, we are hospitalised within a week.
A type 2 however doesn't get to see the consequences of their lifestyle for years and by then it is too late. And we all know how difficult it is to change lifestyle habits without feedback or reinforcement.
I would not wish anyone to get Type 1 - but if you have it, it is never far from your mind so you have to deal with it.
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2024
