Apple Watch can detect early signs of diabetes with 85% accuracy, study finds

Posted:
in Apple Watch edited February 7
Amid rumors that Apple is working on a non-invasive glucose monitoring system for Apple Watch, researchers are using cutting edge software science to prove the heart rate sensors in current-generation wearables can successfully detect early signs of diabetes.




As part of an ongoing study involving Apple Watch and Android Wear users, researchers at app developer Cardiogram and the University of California, San Francisco, trained a deep neural network called DeepHeart to distinguish people with and without diabetes at an accuracy of 85 percent.

The collaborative study pulled from 14,011 Cardiogram users enrolled with the UCSF Health eHeart Study to obtain 33,628 person-weeks of health sensor data. This information was used to train DeepHeart, which was presented with samples from people with and without diabetes, hypertension, sleep apnea, atrial fibrillation and high cholesterol, according to Cardiogram co-founder Johnson Hsieh.

"Typical deep learning algorithms are data-hungry, requiring millions of labeled examples, but in medicine, each label represents a human life at risk -- for example, a person who recently suffered a heart attack or experienced an abnormal heart rhythm," Hsieh said in a prepared statement. "To solve this challenge, researchers applied two semi-supervised deep learning techniques ('unsupervised sequence pretraining' and 'weakly-supervised heuristic pretraining') which made use of both labeled and unlabeled heart rate data to improve accuracy."

Hsieh notes a correlation between diabetes and a body's autonomic nervous system allows DeepHeart to detect the disease through heart rate readings. Specifically, as people develop early stage diabetes, their pattern of heart rate variability shifts in measurable ways.

Findings from the study and subsequent research paper (PDF link) were presented at the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) in New Orleans on Wednesday.

Cardiogram's latest study arrives amid rumors that Apple is developing noninvasive glucose sensors for integration in a future Apple Watch device. Considered a "holy grail" of modern medical science, such a system would allow diabetics to continuously monitor sugar levels without performing blood draws.

According to the most recent reports, however, the glucose sensing technology is years away from release.

Cardiogram co-founder Brandon Ballinger told AppleInsider that DeepHeart is ready to integrate glucose readings if and when Apple launches a Watch model with built-in glucose monitoring capabilities.

"If Apple includes a glucose monitor in the next Watch, we'll be the first developers to try it," Ballinger said. "We designed DeepHeart to be both multi-task (able to detect multiple health conditions) and multi-channel (able to incorporate multiple sensor data streams) for exactly that reason."

Actively used by more than a quarter million people, Cardiogram has been able to apply DeepHeart to detect a number of heart-related conditions using consumer grade hardware. Most recently, Cardiogram and UCSF researchers last May demonstrated Apple Watch can detect atrial fibrillation, a common heart arrhythmia that can lead to stroke, with a 97 percent accuracy. A few months later, Apple itself teamed up with Stanford on its own atrial fibrillation detection program called the Heart Health Study.

Cardiogram will further expand on its research initiatives in 2018 as it looks to apply deep neural network technologies to real-world scenarios, all in the hope of saving lives. One new feature due to arrive this year is direct in-app integration with DeepHeart, which should grant access to a much larger dataset for improved statistics.

Cardiogram is a free 55.2MB download from the iOS App Store.
«1

Comments

  • Reply 1 of 21
    foggyhillfoggyhill Posts: 4,658member

    Considering how diabetes is highly treatable (meaning sometimes merely a change in diet, not using some drugs) if caught early, this is great.

    Sometimes, people just need a wake up cal to tell them their heading their wrong way.


    tmayjahbladechiaairnerdradarthekatGG1mavemufcStrangeDaysjony0stantheman
  • Reply 2 of 21
    macguimacgui Posts: 751member
    A friend of mine was told he was pre-diabetic, and diabetes ran in one side of his family, the latter requiring daily insulin injections for decades.

    He started carefully monitoring his diet and mountain biking. The combination has kept diabetes at bay with no need for any drug therapy. He's disciplined enough that he no longer does the finger-stick testing daily.

    If the Watch could give an early warning, a lot of people could follow his path and avoid the disease and drug treatment.
    jahbladeairnerdStrangeDaysstantheman
  • Reply 3 of 21
    I am fairly critical of the eHeart Study. 

    They classified me as having COPD because I used to have chronic bronchitis, which was brought on by a dust allergen (the bronchitis immediately cleared up when I took an antihistamine. Pretty sure COPD doesn't work that way). I haven't had bronchitis in years since I started working from home. This is not symptomatic of COPD at all. Nor do I smoke or have emphysema. It's not even a condition my own doctor diagnosed or considers me a risk factor for. 

    When I told the eHeart Study people of the error, they told me they "couldn't fix it" but to tell any surveys I do not have the condition. This is stupid. For one thing, as a consequence, I will NOT be asked to join any non-COPD related studies. I will also no qualify for any COPD related studies. Effectively, they categorized me out of the program.

    When I told them I wanted to leave the program BECAUSE they have no process to correct a mis-"diagnosis" they never responded. And there is no opt-out in the app. Once you're in, you're in forever. 

    So I uninstalled the app and whenever the eHeart Study people send me an email I unsubscribe. 

    But if they are completely unwilling to fix bad data, and have no desire to make sure that they're accurately collecting data to begin with, I can't see how this study can be in any way effective.
    airnerdSpamSandwich
  • Reply 4 of 21
    Good for Apple! We're talking ~75% of adults in America...

    I read recently, a neurosurgeon said, 'if you're 30 pounds overweight, you have everything.' He's referring to heart disease, high blood pressure, pre-diabetes and some cancers, just to name a few.

    I noticed Tim is looking very trim. Looks like he's lost 20-30 pounds.  
    edited February 7 lolliverstantheman
  • Reply 5 of 21
    SoliSoli Posts: 7,305member
    foggyhill said:
    Considering how diabetes is highly treatable (meaning sometimes merely a change in diet, not using some drugs) if caught early, this is great.

    Sometimes, people just need a wake up cal to tell them their heading their wrong way.
    This has been my position since the Watch came out, but I got a lot of pushback about how it's not a reasonable expectation. I'm glad to see that there's some evidence to support this as being feasible.

    Even if we reversed this so that early warning signs are only be detectable in 15%, instead of 85%, that's still a huge win and a huge number of people that would benefit. 
    edited February 7 lolliver
  • Reply 6 of 21
    mike1mike1 Posts: 1,645member
    araquen said:
    I am fairly critical of the eHeart Study. 

    They classified me as having COPD because I used to have chronic bronchitis, which was brought on by a dust allergen (the bronchitis immediately cleared up when I took an antihistamine. Pretty sure COPD doesn't work that way). I haven't had bronchitis in years since I started working from home. This is not symptomatic of COPD at all. Nor do I smoke or have emphysema. It's not even a condition my own doctor diagnosed or considers me a risk factor for. 

    When I told the eHeart Study people of the error, they told me they "couldn't fix it" but to tell any surveys I do not have the condition. This is stupid. For one thing, as a consequence, I will NOT be asked to join any non-COPD related studies. I will also no qualify for any COPD related studies. Effectively, they categorized me out of the program.

    When I told them I wanted to leave the program BECAUSE they have no process to correct a mis-"diagnosis" they never responded. And there is no opt-out in the app. Once you're in, you're in forever. 

    So I uninstalled the app and whenever the eHeart Study people send me an email I unsubscribe. 

    But if they are completely unwilling to fix bad data, and have no desire to make sure that they're accurately collecting data to begin with, I can't see how this study can be in any way effective.
    Because you're just one tiny, statistically-irrelevant data point.
    netroxlolliverapplepieguy
  • Reply 7 of 21
    Bodes very well for the future.  There's a lot we can tell from heart information.  I was (correctly) diagnosed with sleep apnea several years ago based on an initial hunch my doctor got from an EKG.  I could easily see the Apple Watch eventually detecting this too.   

    Sleep apnea is not just about getting better quality sleep, it affects your heart - so don't ignore it if your doctor advised that you may have it.
  • Reply 8 of 21
    netroxnetrox Posts: 572member
    araquen said:
    I am fairly critical of the eHeart Study. 

    They classified me as having COPD because I used to have chronic bronchitis, which was brought on by a dust allergen (the bronchitis immediately cleared up when I took an antihistamine. Pretty sure COPD doesn't work that way). I haven't had bronchitis in years since I started working from home. This is not symptomatic of COPD at all. Nor do I smoke or have emphysema. It's not even a condition my own doctor diagnosed or considers me a risk factor for. 

    When I told the eHeart Study people of the error, they told me they "couldn't fix it" but to tell any surveys I do not have the condition. This is stupid. For one thing, as a consequence, I will NOT be asked to join any non-COPD related studies. I will also no qualify for any COPD related studies. Effectively, they categorized me out of the program.

    When I told them I wanted to leave the program BECAUSE they have no process to correct a mis-"diagnosis" they never responded. And there is no opt-out in the app. Once you're in, you're in forever. 

    So I uninstalled the app and whenever the eHeart Study people send me an email I unsubscribe. 

    But if they are completely unwilling to fix bad data, and have no desire to make sure that they're accurately collecting data to begin with, I can't see how this study can be in any way effective.
    You're not getting it. Your isolated case does not make it true for the majority of people. They cannot just "fix" because of a few were misdiagnosed. It's not how it works.
    stantheman
  • Reply 9 of 21
    foggyhillfoggyhill Posts: 4,658member
    Soli said:
    foggyhill said:
    Considering how diabetes is highly treatable (meaning sometimes merely a change in diet, not using some drugs) if caught early, this is great.

    Sometimes, people just need a wake up cal to tell them their heading their wrong way.
    This has been my position since the Watch came out, but I got a lot of pushback about how it's not a reasonable expectation. I'm glad to see that there's some evidence to support this as being feasible.

    Even if we reversed this so that early warming signs are only be detectable in 15%, instead of 85%, that's still a huge win and a huge number of people that would benefit. 
    We don't agree on much, but I've always tought Apple was going to much harder into health than anyone even thinks now, much much harder.

    This is an industry where privacy is important, it's a big ass mess of inefficiency and the user experience is the pits at all level from prevention to treatment.

    Oh, it's also a huge massive industry that seemingly Google and Amazon forgot as they dabble in ever privacy averse areas.

    If Apple just got a medium penetration in that market, they'd already double in size, there aren't many places a company its size can go that will give them that.

    People like to trot out Jobs and guess what he would be thinking, well we do know he was not happy by the state of an industry he dealt with a lot in the 5 years of his life.
    edited February 7
  • Reply 10 of 21
    araquen said:
    I am fairly critical of the eHeart Study. 

    They classified me as having COPD because I used to have chronic bronchitis, which was brought on by a dust allergen (the bronchitis immediately cleared up when I took an antihistamine. Pretty sure COPD doesn't work that way). I haven't had bronchitis in years since I started working from home. This is not symptomatic of COPD at all. Nor do I smoke or have emphysema. It's not even a condition my own doctor diagnosed or considers me a risk factor for. 

    When I told the eHeart Study people of the error, they told me they "couldn't fix it" but to tell any surveys I do not have the condition. This is stupid. For one thing, as a consequence, I will NOT be asked to join any non-COPD related studies. I will also no qualify for any COPD related studies. Effectively, they categorized me out of the program.

    When I told them I wanted to leave the program BECAUSE they have no process to correct a mis-"diagnosis" they never responded. And there is no opt-out in the app. Once you're in, you're in forever. 

    So I uninstalled the app and whenever the eHeart Study people send me an email I unsubscribe. 

    But if they are completely unwilling to fix bad data, and have no desire to make sure that they're accurately collecting data to begin with, I can't see how this study can be in any way effective.
    chronic bronchitis is a form of COPD. so they study classified you properly.
    nhtSolilolliverstantheman
  • Reply 11 of 21
    gatorguygatorguy Posts: 18,588member
    foggyhill said:
    Soli said:
    foggyhill said:
    Considering how diabetes is highly treatable (meaning sometimes merely a change in diet, not using some drugs) if caught early, this is great.

    Sometimes, people just need a wake up cal to tell them their heading their wrong way.
    This has been my position since the Watch came out, but I got a lot of pushback about how it's not a reasonable expectation. I'm glad to see that there's some evidence to support this as being feasible.

    Even if we reversed this so that early warming signs are only be detectable in 15%, instead of 85%, that's still a huge win and a huge number of people that would benefit. 
    We don't agree on much, but I've always tought Apple was going to much harder into health than anyone even thinks now, much much harder.

    This is an industry where privacy is important, it's a big ass mess of inefficiency and the user experience is the pits at all level from prevention to treatment.

    Oh, it's also a huge massive industry that seemingly Google and Amazon forgot as they dabble in ever privacy averse areas.

    If Apple just got a medium penetration in that market, they'd already double in size, there aren't many places a company its size can go that will give them that.

    People like to trot out Jobs and guess what he would be thinking, well we do know he was not happy by the state of an industry he dealt with a lot in the 5 years of his life.
    Google (Alphabet) is actually heavily involved in the medical arena, both in research and in developing cures and probably  far more so than Apple. But Android Wear gets short shrift from them. Why? I've no idea. Wearables seem like the logical choice for completing the circle of Google's medical-related work. Apple Watch very obviously is putting more effort in that part of it while Android Wear seems like a Google after-thought. Perhaps it's all simply because Apple wants to use medical to sell more Apple Watches, while Google doesn't have a hardware offering of their own at all...
    but they should IMHO.
    edited February 7
  • Reply 12 of 21
    nhtnht Posts: 4,121member
    dinkydogs said:
    araquen said:
    I am fairly critical of the eHeart Study. 

    They classified me as having COPD because I used to have chronic bronchitis, which was brought on by a dust allergen (the bronchitis immediately cleared up when I took an antihistamine. Pretty sure COPD doesn't work that way). I haven't had bronchitis in years since I started working from home. This is not symptomatic of COPD at all. Nor do I smoke or have emphysema. It's not even a condition my own doctor diagnosed or considers me a risk factor for. 

    When I told the eHeart Study people of the error, they told me they "couldn't fix it" but to tell any surveys I do not have the condition. This is stupid. For one thing, as a consequence, I will NOT be asked to join any non-COPD related studies. I will also no qualify for any COPD related studies. Effectively, they categorized me out of the program.

    When I told them I wanted to leave the program BECAUSE they have no process to correct a mis-"diagnosis" they never responded. And there is no opt-out in the app. Once you're in, you're in forever. 

    So I uninstalled the app and whenever the eHeart Study people send me an email I unsubscribe. 

    But if they are completely unwilling to fix bad data, and have no desire to make sure that they're accurately collecting data to begin with, I can't see how this study can be in any way effective.
    chronic bronchitis is a form of COPD. so they study classified you properly.
    Yah I was going to point that out but you beat me to it.
    lolliver
  • Reply 13 of 21
    My husband is Diabetic, I'm hoping for the watch to someday alert to low sugar, his will drop with very little warning.
  • Reply 14 of 21
    gatorguy said:
    foggyhill said:
    Soli said:
    foggyhill said:
    Considering how diabetes is highly treatable (meaning sometimes merely a change in diet, not using some drugs) if caught early, this is great.

    Sometimes, people just need a wake up cal to tell them their heading their wrong way.
    This has been my position since the Watch came out, but I got a lot of pushback about how it's not a reasonable expectation. I'm glad to see that there's some evidence to support this as being feasible.

    Even if we reversed this so that early warming signs are only be detectable in 15%, instead of 85%, that's still a huge win and a huge number of people that would benefit. 
    We don't agree on much, but I've always tought Apple was going to much harder into health than anyone even thinks now, much much harder.

    This is an industry where privacy is important, it's a big ass mess of inefficiency and the user experience is the pits at all level from prevention to treatment.

    Oh, it's also a huge massive industry that seemingly Google and Amazon forgot as they dabble in ever privacy averse areas.

    If Apple just got a medium penetration in that market, they'd already double in size, there aren't many places a company its size can go that will give them that.

    People like to trot out Jobs and guess what he would be thinking, well we do know he was not happy by the state of an industry he dealt with a lot in the 5 years of his life.
    Google (Alphabet) is actually heavily involved in the medical arena, both in research and in developing cures and probably  far more so than Apple. But Android Wear gets short shrift from them. Why? I've no idea. Wearables seem like the logical choice for completing the circle of Google's medical-related work. Apple Watch very obviously is putting more effort in that part of it while Android Wear seems like a Google after-thought. Perhaps it's all simply because Apple wants to use medical to sell more Apple Watches, while Google doesn't have a hardware offering of their own at all...
    but they should IMHO.
    Yeah and then they can serve ads on it. Sign me up?
    applepieguy
  • Reply 15 of 21
    cgWerkscgWerks Posts: 1,354member
    I can detect early signs of diabetes with about 100% accuracy if I just observe someone behaving typically for about a day. Unfortunately, it's pretty much everyone who hasn't shifted their diets to drastically reduce sugar and may-as-well-be-sugar-carbs.
    christopher126
  • Reply 16 of 21
    dsmith725 said:
    My husband is Diabetic, I'm hoping for the watch to someday alert to low sugar, his will drop with very little warning.
    Obviously, stay on doctor's protocol/meds until improvement is apparent.

    But get him on a vegan diet. Fruits and Veggies, mostly veggies. :)

    Recommend watching 'Forks over Knives" :)

    Best. 
    edited February 8
  • Reply 17 of 21
    cgWerks said:
    I can detect early signs of diabetes with about 100% accuracy if I just observe someone behaving typically for about a day. Unfortunately, it's pretty much everyone who hasn't shifted their diets to drastically reduce sugar and may-as-well-be-sugar-carbs.
    Agreed. Isreal just banned Heinz ketchup b/c only 40% is actual tomatoes/ketchup...the rest is sugar.

    How Americans allow food manufacturers to produce such crap is beyond me. Companies like McDonalds and Coke are bankrupting our healthcare system. 

    The most profitable isle in the grocery store is sodas (read sugar). The second most profitable isle is cereals (again, read sugar).

    Best
  • Reply 18 of 21
    cgWerkscgWerks Posts: 1,354member
    christopher126 said:
    Obviously, stay on doctor's protocol/meds until improvement is apparent. 
    But get him on a vegan diet. Fruits and Veggies, mostly veggies. :)
    Everyone is different, so they have to be careful, but it's pretty hard for any 'Westerner' to do harm to their diet by adding more veggies. :)
    The trick is finding a doctor who knows much of anything about good nutrition. Maybe add a good naturopath in with the traditional doctor.
    Most diabetes is a *result* of following gov't and doctor recommended diets. :(  And, nearly everyone could do a lot of good by drastically lowering sugars and certain carbs, and upping healthy fats.
  • Reply 19 of 21
    gatorguygatorguy Posts: 18,588member
    gatorguy said:
    foggyhill said:
    Soli said:
    foggyhill said:
    Considering how diabetes is highly treatable (meaning sometimes merely a change in diet, not using some drugs) if caught early, this is great.

    Sometimes, people just need a wake up cal to tell them their heading their wrong way.
    This has been my position since the Watch came out, but I got a lot of pushback about how it's not a reasonable expectation. I'm glad to see that there's some evidence to support this as being feasible.

    Even if we reversed this so that early warming signs are only be detectable in 15%, instead of 85%, that's still a huge win and a huge number of people that would benefit. 
    We don't agree on much, but I've always tought Apple was going to much harder into health than anyone even thinks now, much much harder.

    This is an industry where privacy is important, it's a big ass mess of inefficiency and the user experience is the pits at all level from prevention to treatment.

    Oh, it's also a huge massive industry that seemingly Google and Amazon forgot as they dabble in ever privacy averse areas.

    If Apple just got a medium penetration in that market, they'd already double in size, there aren't many places a company its size can go that will give them that.

    People like to trot out Jobs and guess what he would be thinking, well we do know he was not happy by the state of an industry he dealt with a lot in the 5 years of his life.
    Google (Alphabet) is actually heavily involved in the medical arena, both in research and in developing cures and probably  far more so than Apple. But Android Wear gets short shrift from them. Why? I've no idea. Wearables seem like the logical choice for completing the circle of Google's medical-related work. Apple Watch very obviously is putting more effort in that part of it while Android Wear seems like a Google after-thought. Perhaps it's all simply because Apple wants to use medical to sell more Apple Watches, while Google doesn't have a hardware offering of their own at all...
    but they should IMHO.
    Yeah and then they can serve ads on it. Sign me up?
    Do smartwatches get ads? Serious question. Seems a poor place to present one if they do. 

    EDIT: Nevermind, I looked and yes both Apple and Google permit ads on their respective platforms smartwatches (ex. TMZ app). Kinda dumb IMO...
    edited February 8
  • Reply 20 of 21
    foggyhill said:

    Considering how diabetes is highly treatable (meaning sometimes merely a change in diet, not using some drugs) if caught early, this is great.

    Sometimes, people just need a wake up cal to tell them their heading their wrong way.


    Not a diabetic, but deal with Diabetics in the Hospital where I work every day. It is not as cut and dried for everyone. Someone making an Upper MIddle Class income and living in an affluent area and great insurance has very different options from the poor, elderly and disabled. We do not see many people with Professional Degrees and high incomes coming in with CV disease and Diabetes- they come in with sports injuries and such. The poor smoke too much, weigh too much, eat poorly, drink too much, tend to not see the Doctor regularly, do not exercise, do not get enough sleep and many times do not take their medicine properly or at all.

    The big problem with many with Metabolic Syndrome (essentially pre-diabetes), is that eating healthy generally costs more and can be (logistically) more difficult.
    Food Deserts are for real in many poor communities and getting to a store where you can buy healthier food is a problem. Stores stock what sells- not what is good for you, so if you live in an area where most eat poorly, your choices can be very slim.

    Also, eating health usually involves more preparation compared to the processed stuff you can slap in the oven- which is also heavily laced with sodium.

    I eat a fairly healthy diet, but it costs more in time and money than what many would or could afford to pay.

    The same is true of exercise, which helps Diabetics by taking off weight. There are countless people far from a gym, pool, or safe park where they can exercise. In some cases dropping weight and keeping it off can reverse diabetes, but you have to have a place to go. Again, I have access to a full gym with indoor swimming pool from 5AM -10 PM 363 days a year (closed Christmas and Easter) but it cost me $53 a month and many cannot ford that or do not even have the option where they live.

    Finally, most low or fixed income people who this would benefit the most do not have $300 for a watch and $1000 for an iPhone that it tethers to. A lot of them are living paycheck to paycheck and many retired people have nothing income wise other than a Social Security Check- otherwise not much. It is easy to generalize about personal behavior and choices, but we all do not walk the same path and most do not start out advantaged. My Dad was an Electrical Engineer, but not everyone starts that way.
Sign In or Register to comment.