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

Apple Watch detects irregular heart beat in large U.S. study

reuters.com

Post reply on HN
Print view View original

91–100 of 242 posts

Re: Apple Watch detects irregular heart beat in large U.S. study

#91

Post by alsetmusic »

tedivm wrote: post #40
Zanni wrote: post #19

If I'm reading this right, the Apple Watch was actually more accurate in detecting arterial fibrilation episodes than the ECG patch they used for initial confirmation. The Apple Watch identified 2,000 people. The patch confirmed 33% of those, but then another 51% were confirmed by some undisclosed method.

That's not an accurate interpretation. Atrial fibrillation episodes are not constant- they come and go, and different people will have them at different frequencies. It's possible that people had an episode while wearing the watch but haven't had any episodes while wearing the ECG. ECGs are also less comfortable to wear than watches, so it's possible the people they sent them to didn't wear them as often (it's even p…

A proper study would probably compare the amount of hours of data.

Re: Apple Watch detects irregular heart beat in large U.S. study

#92

Post by Waterluvian »

I can see a future where my doctor gives me a wristband to wear for a month then return as a part of each annual checkup.

Though maybe it gets even better than that and we just all start wearing watches again.

I want that feature but I'm not a watch wearer.

Re: Apple Watch detects irregular heart beat in large U.S. study

#93

Post by hellofunk »

dbg31415 wrote: post #86
hellofunk wrote: post #52

Earlier quoted context omitted.

I don't want to live in a world where insurance companies or employers have any need or incentive to have this data. Like most developed nations outside the U.S. for example.

I'm from the US, but I live in a country with "national health care" and... look it sucks. You know what I miss? 1990s era health care for tech workers in the US. When you went in and everything was covered for a $20 co-pay. You want a specific medication, or a non-generic medication in Australia? Too bad. It's not that it costs more, you just can't get it. Things like Wellbutrin are as illegal as crack. And if you d…

That is most certainly not the experience I've had with nationalized health care in Europe. Sounds like an implementation problem more than anything.

Re: Apple Watch detects irregular heart beat in large U.S. study

#94

Post by SlowRobotAhead »

tedivm wrote: post #40
Zanni wrote: post #19

If I'm reading this right, the Apple Watch was actually more accurate in detecting arterial fibrilation episodes than the ECG patch they used for initial confirmation. The Apple Watch identified 2,000 people. The patch confirmed 33% of those, but then another 51% were confirmed by some undisclosed method.

That's not an accurate interpretation. Atrial fibrillation episodes are not constant- they come and go, and different people will have them at different frequencies. It's possible that people had an episode while wearing the watch but haven't had any episodes while wearing the ECG. ECGs are also less comfortable to wear than watches, so it's possible the people they sent them to didn't wear them as often (it's even p…

All good arguments for the watch it seems. I was a little eye roll at the ECG feature Apple added, but I’m happy to be proven wrong.

Re: Apple Watch detects irregular heart beat in large U.S. study

#95

Post by dkarp »

taurath wrote: post #78
threeseed wrote: post #72

Earlier quoted context omitted.

No they won’t. The market for luxury watches is growing every year and despite the arrival of different technologies e.g. Quartz, Digital they are still around. I actually think this will be an emerging market as people start to revolt against technology being everywhere. And for me smart watches are on whole detrimental to a person’s health since they raise stress levels through constant notifications.

I’ve turned off all notifications on my watch other than texts and phone calls - it’s nice to be able to walk outside without my phone, but still can call someone if we lose each other.

I don't have a smart watch, so I assumed it connects to your phone via Bluetooth. Is that not the case? Otherwise how can you leave the house without your phone also?

Re: Apple Watch detects irregular heart beat in large U.S. study

#96

Post by conistonwater »

BoingX4 wrote: post #67
iguy wrote: post #44

Earlier quoted context omitted.

It's entirely possible that a test which was net positive when applied "with probable cause", can even become a net negative if applied without. Because testing the whole population will produce many more false positives. I doubt the tests they are running here will actually go that far. But pervasive testing does need different trade-offs to targeted testing. At least we may have more complete data from which to und…

> Because testing the whole population will produce many more false positives. That is the issue that should get resolved with time. The watch will receive a lot of feedback from medical professionals to adjust its reporting because now we'll know so much more about what symptoms are really worth paying attention. But of course, there will be an adjustment period like what we are seeing now. This has always been true…

> That is the issue that should get resolved with time.

Bear in mind that this hasn't happened for the other major overdiagnosis issue (cancer screening), and the best solution found so far there is to screen less. This really isn't the sort of thing where natural technological progress is enough to be comfortable saying things like "it'll get resolved with time". There are already counterexamples to what you're saying, it's not a matter of an "adjustment period".

Re: Apple Watch detects irregular heart beat in large U.S. study

#97

Post by vowelless »

brandonb wrote: post #82

I work at a related company (Cardiogram), and there's a surprising amount of signal locked in the humble heart rate sensor -- we've run multiple studies with UCSF showing accurate detection of sleep apnea, high blood pressure, and even diabetes using off-the-shelf heart rate sensors and a deep neural network, DeepHeart: https://blog.cardiogr.am/screening-with-wearables-what-do-th... If you're an engineer or payer rel…

Link doesn't work.

Re: Apple Watch detects irregular heart beat in large U.S. study

#98

Post by iguy »

conistonwater wrote: post #96
BoingX4 wrote: post #67

Earlier quoted context omitted.

> Because testing the whole population will produce many more false positives. That is the issue that should get resolved with time. The watch will receive a lot of feedback from medical professionals to adjust its reporting because now we'll know so much more about what symptoms are really worth paying attention. But of course, there will be an adjustment period like what we are seeing now. This has always been true…

> That is the issue that should get resolved with time. Bear in mind that this hasn't happened for the other major overdiagnosis issue (cancer screening), and the best solution found so far there is to screen less. This really isn't the sort of thing where natural technological progress is enough to be comfortable saying things like "it'll get resolved with time". There are already counterexamples to what you're sayi…

If I understand right, one of the problems in the case of cancer is that we don't have great data about the people without symptoms who wider screening would catch. Once we catch them, we treat them, and many recover. But to say how many of those would have been fine anyway, we'd have to know more about the un-screened rest of the population.

The hope with widespread cheap screening would be that it might avoid this. If heart-rate smartwatches become as common as smartphones, we could train our treatment model on everyone, and do better. Or at least this sounds mathematically plausible to me (not an expert).

Whether it will come to pass, or whether doctors will continue to treat as now (anything which an eyeball test says looks like an early stage of a known disease) I don't know.

Re: Apple Watch detects irregular heart beat in large U.S. study

#99

Post by GuiA »

Waterluvian wrote: post #92

I can see a future where my doctor gives me a wristband to wear for a month then return as a part of each annual checkup. Though maybe it gets even better than that and we just all start wearing watches again. I want that feature but I'm not a watch wearer.

The future is your insurance company making you wear a smart watch 24/7 if you don’t want to pay a huge premium. I predict it’s going to be a huge quagmire over the next decade or so.

Re: Apple Watch detects irregular heart beat in large U.S. study

#100

Post by Someone »

hawaiianbrah wrote: post #74
pfranz wrote: post #25

Earlier quoted context omitted.

Nothing specific to this article, but this comes up often in medicine. Sure, you can pay to run more tests, find some things earlier (along with some false positives), but the outcomes and treatment aren't any different than if you waited for more obvious symptoms and could take a more accurate test.

What? An ounce of prevention and a pound of cure and all that. Early detection is key in a lot of situations, so how could earlier not be better? Why wait unnecessarily?

The cure may statistically be worse than doing nothing.

For example, prostate cancer can kill, but more people die with prostate cancer than of prostate cancer, in the latter case often with minor symptoms.

Detecting it before it bothers people helps those it would kill, but subjects lots of others to testing, and those tests will initially have false positives that unnecessarily stress those it wouldn’t kill.

Worse, the side effects of treatment can include incontinence and erectile dysfunction that can significantly affect quality of life for those were follow-up tests also produce false positives.

Thats’s why there is discussion on whether screening for prostate cancer makes sense, and if so, for whom. See for example https://www.cochranelibrary.com/cdsr/doi/10.1002/14651858.CD....

Post reply on HN