back
user profile
brandonb
9,344karma·1,335submissions·January 17, 2011
about
Data for good.
Co-Founder at Empirical Health (https://empirical.health). Don't die of heart disease.
Before: Co-Founder @ Cardiogram (ML for heart health)
CTO at Sift Science (YC S11, machine learning to fight fraud)
Data Science @ UCSF Cardiology
HealthCare.gov rescue team
Google (Android speech recognition, search ads ML)
brandonb.cc
recent activity (1,335 total)
comment
Our academic partner at UCSF Cardiology hosts their study on their own domain ( https://www.health-eheartstudy.org/ ). If you sign up through the links to Health eHeart provided at mRhy…
comment
Yes! We plan to support other devices like Fitbit and Android Wear. My co-founder and I both worked on Android at Google, so we'd love to get back to Android Studio.
comment
We do plan to support other devices like Fitbit and Android Wear. The reason we started with Apple Watch is that 1) the heart rate sensor is quite good, and 2) we can target millions of people with on…
comment
Oh sorry—that's confusing. You'll actually have two accounts. One for the Cardiogram app using your choice of Facebook / Twitter / Email, and one for Health eHeart study (our partn…
comment
Yeah! Absolutely. In healthcare we call it "patient compliance," but it's really just usability. My guess is that by the time we get to the Apple Watch or Android Wear 3 or 4, it'l…
comment
We're lucky in that information covered by HIPAA (e.g., the medical record) is handled by our academic partner at UCSF, the Health eHeart study (health-eheartstudy.org). I think it's a bit o…
comment
If we succeed in training an accurate enough machine learning algorithm, I think the primary purpose will be to screen for asymptomatic atrial fibrillation, and then use a Holter or Zio Patch for a fi…
comment
Sure! Hit me up at brandon@cardiogr.am.
comment
Thank you for participating! And that's exactly what we're measuring—how accurate is the Watch, and in what circumstances does it make errors? The anecdotal evidence is very conflicting, whi…
comment
And if you're curious as to what atrial fibrillation looks like when measured on an Apple Watch in workout mode, here's an example (bottom-right corner):
https://twitter.com/…
comment
We (Cardiogram) have been working with UCSF cardiology on exactly this problem: detecting abnormal heart rhythms using Apple Watch data. The more data our algorithm sees, the more accurate it gets. If…
comment
I'm glad you're ok! Heart rate data is such a window into our emotional lives. There was the guy who recorded a breakup on his Fitbit: http://www.buzzfeed.com/stephaniemlee&#…
comment
Getting some spikes is normal while you're in REM sleep. Here's an example of restful sleep vs sleep after a night of drinking:
http://imgur.com/l9RVeK5 In general, we…
comment
Yancheng was awesome to work with. We + UCSF actually just launched a continuation of his work via the mRhythm Study: https://mRhythmStudy.org
If you have an Apple Watch, you can cont…
comment
Hey all—I'm one of the machine learning engineers involved in the study. Let me know if any of you have questions on how deep learning applies to medicine, HealthKit, Google Fit, or anything else…
1 pts
comment
Hey HN, Johnson and I are co-founders of Cardiogram, and we're working with UCSF cardiology (the Health eHeart project) to launch the mRhythm Study today. We'll be giving a talk with more te…
comment
That's really cool! Might use this for my next project.
comment
You can sign up for our (upcoming) Android Wear beta on the homepage: https://cardiogr.am
comment
Apple Watch is pretty great at measuring heart rate in my experience. Part of the difference may be the circumstances in which the measurement is taken—in the clinic, "resting heart rate" is…
comment
Yep—resting heart rate is a good proxy, and readily measurable from Apple Watch. A definitive study would randomly assign people to an exercise routine, follow them for 20-30 years, and then measure h…
comment
I thought their metric ("physical activity index") sounded interesting, but at least from the WSJ article, it seems to be a bit of a black box. I'd love to see Mio publish some analysis…
comment
Yes—that's certainly our long-term goal. This analysis is a first step, but before providing personalized recommendations, I think we'd want to do a lot more validation. There are a lot of c…