Live data from Hacker News

Fitbit's 150B hours of heart data

finance.yahoo.com

1–10 of 137 posts

Re: Fitbit's 150B hours of heart data

#2
A low (R)HR isn't always indicative of good health. High blood pressure can cause your HR to drop, for instance.

I hope they're actively researching their data set, I suspect we can learn a lot from it. They might even be able to detect certain arrhythmias, though that can't be easy with just an optical sensor which only reads HR.

With a user base this large, I'm sure people have died while wearing their fitbit. Maybe they could help predict/prevent the sudden cardiac death syndrome that many young athletes are afraid of?

Re: Fitbit's 150B hours of heart data

#4
> modern smartwatches and fitness bands can track your pulse continuously, day and night, for months. Imagine what you could learn if you collected all that data from tens of millions of people!

Please no. Surely nobody thought collecting health data from all their users was a good idea, right?

> That’s exactly what Fitbit (FIT) has done. It has now logged 150 billion hours’ worth of heart-rate data. From tens of millions of people, all over the world.

Argh…

> Fitbit also knows these people’s ages, sexes, locations, heights, weights, activity levels, and sleep patterns.

Just stop it already.

> Before you freak out: Fitbit’s data is anonymized. Your name is stripped off, and your data is thrown into a huge pool with everybody else’s. (Note, too, that this data comes only from people who own Fitbits — who are affluent enough, and health-conscious enough, to make that purchase. It’s not the whole world.)

"Anonymized". Just with the data posted above, it seems like it'd be pretty easy to correlate the data to a person. And auto-enrolling everyone who buys a health product is not an excuse to mine all their data.

Re: Fitbit's 150B hours of heart data

#5

Now if only it were accurate...

Am a Garmin user for years. Was in a hospital ~10 months ago and was connected to a heart-rate-monitoring-thingy via a finger-clip. At the same time I had my Garmin Fenix 3 on my other arm. Was looking at the screen and comparing it to what my watch was showing and it was +-2 points at all times. Tried holding my breath to see what happens and both were almost identical.

Re: Fitbit's 150B hours of heart data

#6

Now if only it were accurate...

Am a Garmin user for years. Was in a hospital ~10 months ago and was connected to a heart-rate-monitoring-thingy via a finger-clip. At the same time I had my Garmin Fenix 3 on my other arm. Was looking at the screen and comparing it to what my watch was showing and it was +-2 points at all times. Tried holding my breath to see what happens and both were almost identical.

Optical heart rate when not moving is pretty easy to do.

Measurements are much harder when the user is moving around erratically, such as is typical with exercising.

Source: I worked on a fitness product using optical HR for 3 years.

Re: Fitbit's 150B hours of heart data

#7

> modern smartwatches and fitness bands can track your pulse continuously, day and night, for months. Imagine what you could learn if you collected all that data from tens of millions of people! Please no. Surely nobody thought collecting health data from all their users was a good idea, right? > That’s exactly what Fitbit (FIT) has done. It has now logged 150 billion hours’ worth of heart-rate data. From tens of mil…

I wonder to which extent tracking data is really anonymized since users can still request to delete it, as described in the privacy policy [1].

> If you choose to delete your account, please note that while most of your information will be deleted within 30 days, it may take up to 90 days to delete all of your information, like the data recorded by your Fitbit device and other data stored in our backup systems. This is due to the size and complexity of the systems we use to store data.

[1] https://www.fitbit.com/legal/privacy-policy#your-rights-to-a...

Re: Fitbit's 150B hours of heart data

#8
post #6

Earlier quoted context omitted.

Am a Garmin user for years. Was in a hospital ~10 months ago and was connected to a heart-rate-monitoring-thingy via a finger-clip. At the same time I had my Garmin Fenix 3 on my other arm. Was looking at the screen and comparing it to what my watch was showing and it was +-2 points at all times. Tried holding my breath to see what happens and both were almost identical.

Optical heart rate when not moving is pretty easy to do. Measurements are much harder when the user is moving around erratically, such as is typical with exercising. Source: I worked on a fitness product using optical HR for 3 years.

Even the phone apps work pretty well while stationary:

https://play.google.com/store/apps/details?id=com.repsi.hear...

https://play.google.com/store/apps/details?id=com.supersimpl...

https://play.google.com/store/apps/details?id=si.modula.andr...

Re: Fitbit's 150B hours of heart data

#9
post #7

> modern smartwatches and fitness bands can track your pulse continuously, day and night, for months. Imagine what you could learn if you collected all that data from tens of millions of people! Please no. Surely nobody thought collecting health data from all their users was a good idea, right? > That’s exactly what Fitbit (FIT) has done. It has now logged 150 billion hours’ worth of heart-rate data. From tens of mil…

I wonder to which extent tracking data is really anonymized since users can still request to delete it, as described in the privacy policy [1]. > If you choose to delete your account, please note that while most of your information will be deleted within 30 days, it may take up to 90 days to delete all of your information, like the data recorded by your Fitbit device and other data stored in our backup systems. This…

If it's anonymised well enough it wouldn't be possible to delete it, which may well be the case.

Re: Fitbit's 150B hours of heart data

#10

> modern smartwatches and fitness bands can track your pulse continuously, day and night, for months. Imagine what you could learn if you collected all that data from tens of millions of people! Please no. Surely nobody thought collecting health data from all their users was a good idea, right? > That’s exactly what Fitbit (FIT) has done. It has now logged 150 billion hours’ worth of heart-rate data. From tens of mil…

While I definitely agree that there are large privacy concerns when collecting health related data, I disagree with the sentiment that it's always a bad idea. There is a huge net benefit to modernizing medicine and getting to an AI that is more accurate then doctors. Creating those datasets is a leap towards that direction.
Post reply on HN