back
user profile
brandonb
9,336karma·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
The best book I've read on engineering management I've read is Leading Snowflakes:
http://leadingsnowflakes.com/ But yes, there is a dearth of information on how to be a g…
comment
>But universally, “sparse micromanagement” (the best term I’ve heard for jumping in to some random issue, overturning all the decisions, and then disappearing) is the worst. Great essay. My favorit…
comment
Peter Norvig put it best: "The semantic web is the future of the web, and always will be." (For what it's worth, the startup school video that quote comes from is worth watching: http:…
comment
Obesity seems to impact long-term cardiovascular health only through the other numbers--i.e., raising your blood pressure and lipids. In the Framingham 30-year risk study ( http://www.ncbi.n…
comment
Be careful about which sources you trust. Here's are a couple other articles from sott.net's "Health and Wellness" page:
http://www.sott.net/article/287460-V…
comment
Sounds good. What I've mostly seen is that LDL, total cholesterol, and triglycerides seem to be highly correlated, and adding in any one of those three (assuming you also have HDL) gives the same…
comment
These models often compensate for competing risks of death—if you're curious, look up "Cox proportional hazard" to understand some of the math behind this. Your meta point is a good one…
comment
This app runs on Heroku, so it inherits all of the security controls described here:
https://www.heroku.com/policy/security …
comment
Have a citation for a risk model that uses triglycerides? "Predicting the Thirty-year Risk of Cardiovascular Disease: The Framingham Heart Study" ( http://circ.ahajournals.org/…
comment
Working on it!
comment
Ah, thanks! Will fix.
comment
Unfortunately it's hard but true. I'm on a diet too and it's hard to keep it up. But the benefits of losing weight are pretty clear--it basically improves all four of your numbers excep…
comment
Did you try the "Lifestyle debugger"? It's on the results page, below the graph and its explanation.
comment
It does when calculating your 10-year-risk, but not for lifetime risk. I'd like to add a feature to show you both 10-year and lifetime risks, but for now, the NIH has a 10-year-risk calculator:
…
comment
I haven't seen one yet, but I highly recommend knowing your cholesterol numbers since those will give a much more accurate result--both BMI and ABSI are very coarse-grained measures of what'…
comment
One warning-- "Cholesterol" tends to get used to mean two different things, and even otherwise clear writers like Gary Taubes don't always explicitly denote which one they mean:
1) th…
comment
If you're curious about the risk modeling research literature, here's a good example of models built for 30-year risk prediction:
http://circ.ahajournals.org/content/119…
comment
Ah, I wish I had seen that challenge before submissions closed! The risk models for heart disease are simple enough that I just implemented them in Javascript based on the Framingham papers, although …
comment
Thanks for the report! I'll work on Firefox speed--it's sort of an all-around problem with the Firefox experience.
comment
Hey! Which units would you prefer? For height/weight, I'd assume meters and kg? When you get your cholesterol measurements, do use mg/dL, mmol/L, or something else? What about bloo…
comment
Hey HN! This project was inspired by a personal experience I had--I put my numbers into a spreadsheet provided by the American Heart Association and found I had a 50% lifetime risk of a heart attack. …
comment
Cool! Send me an email—the address is on my profile.
comment
Congrats on the round! I'm curious how you differentiate yourself from the built-in speech APIs on iOS and Android?
https://developer.apple.com/library/mac/documentation…
comment
Cool post. I thought this was the most interesting point: "As an outside agency, we can’t (and shouldn’t) make this decision for Zidisha. However, it IS our job to inform them well enough to make…
comment
Holy shit! Congratulations.