back
user profile
brandonb
9,339karma·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
(I worked on healthcare.gov) Some of my colleagues are doing just this. Stay tuned.
comment
I'll bet the "Wizard of Oz" strategy would work well for this idea. Start off by NOT building any of the fancy infrastructure—the crawler, crunchbase joiner, LDA algorithm to cluster in…
comment
Is anybody here working on an Apple Watch app? Feedback on the (v1) APIs?
comment
I wonder if somebody could build a bayesian filter for Epic alerts. If we can filter out the Nigerian prince scams from your email, why not apply that to save lives?
comment
"Improvements are not consciously forbidden, and making things better is not discouraged. But like an enormous traffic jam, no single person has room to do much of anything. Coordinating a number…
comment
That seems rather cynical, doesn't it? Why don't you ask the people who work at USDS if they're having trouble getting interest from the agencies? That would be a way to test your hypot…
comment
Short answer: no real security issues. AWS itself runs everything from credit card processors to hospital software, they have great documentation on how to design your system so that you comply with t…
comment
I'm sorry you had a bad experience. I am sure it was not their intention to bait and switch; I've forwarded your comment to somebody at USDS so that they can make sure things like this don&#…
comment
"There is no political will to do so." That was true a couple of years ago, but healthcare.gov was a wakeup call, and everybody from the president on down takes reforming government IT serio…
comment
And on the flip side, computers can suggest beautiful theorems to mathematicians by making it easy to run virtual experiments. There's now a burgeoning field of pure math called "Experimenta…
comment
This is cool! I couldn't quite tell from the article, but do you see this as an alternative to Prime and, if so, how is it different? EDIT: One more question: the article says you've reached…
comment
For those who don't know Jason, he's the author of Selenium, founder of Sauce Labs, and was part of the "tech surge" to fix healthcare.gov.
comment
Depends on what you're doing. For most consumer products, it's less about domain expertise and more about capturing "lighting in a bottle." The founders of YouTube weren't nec…
comment
Super cool idea! I love the fact that the interface is so simple and intuitive; I think that makes machine learning accessible to a much longer tail of problems that people would not have previously c…
comment
What an excellent post! I don't agree with every point, but this is thoughtful, clearly articulated, and the thought process reminds me of PG's best writing.
comment
There are many truths here, but I keep seeing HN articles with variants on the following piece of advice: "As a founder your sole aim is growth. If you don’t have growth now, you are failing.&quo…
comment
Thank you! That's helpful. If you'd ever like to talk further feel free to email me (email on my profile).
comment
I'm not tashfeens, but given that you have a CS degree and an MD, I'd be curious as to what makes you skeptical about healthcare startups. Or, conversely, what should a healthcare startup do…