Research labs have been trying this for years with every spectroscopy known to man - the signal is just too weak. I don't see any reason to think Apple has figured something out that labs of optics experts can't do on the benchtop.
Apple Monitoring Blood Glucose
131–140 of 142 posts
Re: Apple Monitoring Blood Glucose
#132Earlier quoted context omitted.
It would be very desirable, but all of the many companies who have tried to get accurate results non-invasively have failed. With Apple's resources, perhaps they'll lick the problem, but I wouldn't bet on it. So to answer your question: Probably because if a Type 1 Diabetic uses a non-invasive glucose monitor to determine their insulin dosage, much of the time they will overdose, and possibly fall into a coma or die.
A co-worker of mine is doing a similar kinda thing but with circulating tumor cells, so I have some 3rd hand knowledge of these kinda tests. Fact of the matter is that the human body is, chemically and pathologically speaking, fucking bulletproof. Our bodies are just super freaking good at maintaining homeostasis. This means that a lot of tests like blood-glucose, cancer diagnosis, etc that are trying for non-invasiv…
> your device MUST cover all those real people with families and children
Are you talking from a regulatory standpoint? Why couldn't Apple (or anybody) make a device that works on a limited range of skin colors? If you can't help everybody, does that mean you shouldn't help anybody?
Re: Apple Monitoring Blood Glucose
#133If this device is covered by insurances, this could become a potential cash cow.
Even if it isn't, I think it would still be a cash cow. I've never owned an Apple watch before, but if they got this working, I'd buy one in a heartbeat (assuming it's less than $1500). FWIW, I'm not diabetic, I just want the data.
Re: Apple Monitoring Blood Glucose
#134Earlier quoted context omitted.
A co-worker of mine is doing a similar kinda thing but with circulating tumor cells, so I have some 3rd hand knowledge of these kinda tests. Fact of the matter is that the human body is, chemically and pathologically speaking, fucking bulletproof. Our bodies are just super freaking good at maintaining homeostasis. This means that a lot of tests like blood-glucose, cancer diagnosis, etc that are trying for non-invasiv…
> your device MUST cover all those real people with families and children Are you talking from a regulatory standpoint? Why couldn't Apple (or anybody) make a device that works on a limited range of skin colors? If you can't help everybody, does that mean you shouldn't help anybody?
Regardless of the soundness of the logic of your reply, the way that idea would be seen by darker-skinned communities (especially like the African-american community in the US that is highly affected by DM-II) would be something like "Apple made a racist product and wants black people to die". Additionally, if the device only works on non-sweating, not moving, healthy, white/asian office workers out of bright sunlight who have not recently eaten nor have gone more than 5 hours without eating, it's not really something that helps anyone who would need it.
Re: Apple Monitoring Blood Glucose
#135Earlier quoted context omitted.
> your device MUST cover all those real people with families and children Are you talking from a regulatory standpoint? Why couldn't Apple (or anybody) make a device that works on a limited range of skin colors? If you can't help everybody, does that mean you shouldn't help anybody?
Regardless of the soundness of the logic of your reply, the way that idea would be seen by darker-skinned communities (especially like the African-american community in the US that is highly affected by DM-II) would be something like "Apple made a racist product and wants black people to die". Additionally, if the device only works on non-sweating, not moving, healthy, white/asian office workers out of bright sunligh…
People with darker skin aren't idiots. Current products like Fitbit trackers already work poorly on dark skinned people, so it's not anything new. I don't think that community is going to call Apple (or, more generally, physics) racist.
Also, I think you underestimate the market size of light skinned office workers with significant disposable income that don't need blood glucose monitoring but want it anyway. I'm one of them.
I wouldn't be surprised if Apple launched multiple devices. The $500-$600 watch would give blood glucose trends or some other derivative information. The $2000-$3000 watch would be the one that gives a medically useful measurement. They could iterate quickly on one and work through the ponderous regulation with the other. Maybe they would even license the technology to Medtronics or some other medical device company and let somebody else deal with the headaches.
Re: Apple Monitoring Blood Glucose
#136Earlier quoted context omitted.
Regardless of the soundness of the logic of your reply, the way that idea would be seen by darker-skinned communities (especially like the African-american community in the US that is highly affected by DM-II) would be something like "Apple made a racist product and wants black people to die". Additionally, if the device only works on non-sweating, not moving, healthy, white/asian office workers out of bright sunligh…
People with darker skin aren't idiots. Current products like Fitbit trackers already work poorly on dark skinned people, so it's not anything new. I don't think that community is going to call Apple (or, more generally, physics) racist. Also, I think you underestimate the market size of light skinned office workers with significant disposable income that don't need blood glucose monitoring but want it anyway. I'm one…
Wait, why would you want blood-glucose monitoring that is not medically proven to work or be reliable?
Like, yeah, maybe it works in a very limited set of situations, but that's the same as a broken clock that only tells the right time twice a day; you'd never know when the monitoring device is working 'correctly'. It would be a random number generator, effectively, if it was not proofed.
Besides, if you aren't a diabetic, why would you care? The human body is highly variable, from person to person, and even inside of a person after meals. All it would do, if it were accurate 'enough', is say some number that you can't control. Like, you aren't gonna take any insulin shots to mess with it, that would likely kill a normal person. I can't see any actual use for a healthy person. Trying to 'game' that (assumed reliable) number would just put you into a coma; we're supposed to have spikes in the concentration, that's how vertebrates work. Playing 'what-if' games with number would be like Russian Roulette, each experiment may kill you.
https://en.wikipedia.org/wiki/Blood_sugar
http://www.webmd.com/diabetes/daily-control-17/slideshow-blo...
http://www.everydayhealth.com/type-2-diabetes/symptoms/surpr...
Also, I'm not saying that people with dark skin are idiots. I'm saying that the 'optics' of Apple releasing that thing aren't 'good' as a large percentage of their 'customers' that have DM-II are dark-skinned, though not all by any means.
Re: Apple Monitoring Blood Glucose
#137Earlier quoted context omitted.
People with darker skin aren't idiots. Current products like Fitbit trackers already work poorly on dark skinned people, so it's not anything new. I don't think that community is going to call Apple (or, more generally, physics) racist. Also, I think you underestimate the market size of light skinned office workers with significant disposable income that don't need blood glucose monitoring but want it anyway. I'm one…
Wait, why would you want blood-glucose monitoring that is not medically proven to work or be reliable? Like, yeah, maybe it works in a very limited set of situations, but that's the same as a broken clock that only tells the right time twice a day; you'd never know when the monitoring device is working 'correctly'. It would be a random number generator, effectively, if it was not proofed. Besides, if you aren't a dia…
Perfect is the enemy of good. My Fitbit counts steps, but it isn't all that accurate from an absolute standpoint. Still, I find the day-to-day variances interesting.
Same goes for blood glucose monitoring. I'd like to see if I can find correlations between my mood, productivity, sleep, fasting, etc... and my blood glucose levels. Like step tracking, the absolute number doesn't matter.
Cook has already said that blood glucose measuring would be useful for people before they have diabetes. That's what makes me think it isn't necessarily a medical device they are building. At least not for version 1.
The last article is one of the things that would be super interesting for me to see. How do blood glucose levels change when I drink a diet soda vs water, for example.
Re: Apple Monitoring Blood Glucose
#138Earlier quoted context omitted.
Why would machine learning be able to overcome a lack of statistical power?
Did you miss the part about sensitive sensors? A single sensor may not be enough to classify accurately but multiple sensors measuring different things can sometimes work. Such sensor fusion has worked incredibly well for IMU's and also in self-driving cars.
That's how the Glucotrack claims to work. From their site:
GlucoTrack uses ultrasonic, electromagnetic and thermal technologies to non-invasively measure glucose levels in the blood. GlucoTrack is intended for use by Type 2 and pre-diabetics.
GlucoTrack combines the following technologies:
Ultrasound (speed of sound change within the tissue);
Electromagnetic (conductivity of the tissue);
Thermal (heat capacity of the tissue).
It's not approved by the FDA, but it appears to be selling in Australia, New Zealand, Spain, China, Korea, Italy and some others.
Re: Apple Monitoring Blood Glucose
#139Apple appears to be working on blood glucose monitoring as a way to address Type 2 Diabetes. Either the article is very wrong, or Apple is doing something very cute here. Type 2 diabetics do check their blood glucose -- occasionally. For non-insulin-using diabetics (aka. most type 2s) medical plans typically cover less than one test per day, because the evidence is that testing more frequently doesn't accomplish anyt…
> For non-insulin-using diabetics (aka. most type 2s) medical plans typically cover less than one test per day
My T2 father's plan covers 4 a day. He has a pretty lousy insurance plan, too. He hates having to prick his finger four times a day, so he often skips. He also hates all things Apple, but he still asked me what I knew about it.
If the next iPhone allows him to stop pricking his fingers four times a day, he'll buy one the day its released. I doubt he'd be the only one.
Re: Apple Monitoring Blood Glucose
#140Earlier quoted context omitted.
If Apple doesn't make this someone else will. If Apple doesn't make decent laptops and desktops then who else can? This is what bothers be about Tim Cooks priorities in health and celebrities next to his apathy towards computers. (I don't consider the iPad a computer I consider it a device)
The business problem is that the world has increasing apathy towards computers. “When we were an agrarian nation, all cars were trucks, because that’s what you needed on the farm,” Jobs said at [the] D8 conference in 2010. “But as vehicles started to be used in the urban centers, cars got more popular. Innovations like automatic transmission and power steering and things that you didn’t care about in a truck as much…
Yeah can't really argue against that logic, just arguing for someone to fulfil my needs to do my job.
Maybe it's time for a new "truck" company that focuses on the needs of the few and Apple can ditch computers and focus on the needs of the many.