back
user profile
brandonb
9,342karma·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
That's an incredibly good visualization! Both beautiful and clear. Next time I'm explaining machine learning to somebody who's smart but not a computer scientist or statistician, this i…
comment
FWIW, Washington state is exceptionally good at treating cardiac arrest. See table 4 here:
http://jama.jamanetwork.com/article.aspx?articleid=182614 SCA survival rate of 16% in Seattl…
comment
FWIW, I work in a cardiology department and "Sudden Cardiac Death" and "Sudden Cardiac Arrest" are used interchangeably. You even hear the term "sudden cardiac death survivor&…
comment
Very cool! I think this could help with sudden cardiac arrest, where the heart stops pumping blood effectively and death happens within minutes--faster than an ambulance can arrive.
http:/…
comment
This is a big problem and I'm glad somebody is solving it! One question--have you considered adding the medical record or HealthKit data to the will? Much like being an organ donor, when you'…
comment
I recommend Mikey Dickeron's talk here:
https://youtu.be/0albm_hhQzM?t=3m40s Mikey was the first SRE at the scene of healthcare.gov and is now running the new US Digital Service…
comment
We know shockingly little about nutrition, but this paper is a great summary of what we do know from both association studies and randomized trials:
http://circ.ahajournals.org/content…
comment
I think I might be your competitor from eight YC batches ago, but good luck! You seem to have a great team.
comment
You don't necessarily need a fancy device to stimulate the vagus nerve. Patients with supraventricular tachycardias are taught to do vagal maneuvers, the simplest of which is gagging:
http:/…
comment
If you have thoughts on what you'd like to do in the ideal case, feel free to send them to brandon@cardiogr.am. We whipped this up over the weekend.
comment
My personal experience is that the Apple Watch's heart rate readings are usually within 5 minutes of my AliveCor. Unfortunately, none of the Android watches currently on the market have a sensor …
comment
Stress makes a big difference in my experience! It's actually the most common driver of heart rate increases in our data set. And it's potentially predictive of heart attacks, see the commen…
comment
Unfortunately I didn't record my heart rate during Google I/O, but you can see how WWDC compared to last night's Game of Thrones here (warning: spoilers):
http://cardiogr.a…
comment
I actually think the watch will have huge impact on heart disease (and am working on making that happen). The resolution of data you can get on the watch is just amazing, but we'll need some basi…
comment
My resting heart rate is usually 60-68bpm (varies quite a bit by day). I'm probably elevated overall since I'm also watching the server to make sure it's not crashing.
comment
Not the OP but I'm the "geek" mentioned in the title. This is updating live during the keynote. Let me know if anybody out there has questions!
comment
It's interesting that so many startups listed lack of product-market fit as the reason for failure, even though another startup with an adjacent idea has been able to get traction. For example, t…
comment
This is a great article! It's always surprised me that, in machine learning and statistics, we take an objective function like squared error as a "given" rather than trying to design an…
comment
I'm not sure this is the person we should listen to on engineering management. This quote is a huge red flag to me: "I advise developers, anytime they’re looking at job ads, serious develope…