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
This is a little different since the Apps SDK lets developers create specialized tool calls to their servers, and create specialized in-chat UI components. It's an evolution of the same concept a…
comment
HbA1c, or just diabetes as a binary variable, has been one of the main inputs into predicting heart attack risk for a long time. The main marker of kidney function, eGFR, was added with the AHA/A…
comment
The acoustic model of a speech recognizer used to be a GMM, which mapped a pre-processed acoustic signal vector (generally MFCCs-Mel-Frequency Cepstral Coefficients) to an HMM state. Now those layers …
comment
I learned speech recognition from the 2nd edition of Jurafsky's book (2008). The field has changed so much it sometimes feels unrecognizable. Instead of hidden markov models, gaussian mixture mod…
comment
It's a cool idea! This is going to become easier in the next year since TEFCA will let patients request their own medical records through the health information exchanges that have already been s…
comment
(OP here) Happy to answer any questions on this work!
comment
If the fire alarm didn't go off, you didn't sear hard enough. :)
comment
D’oh. You’re right. HN doesn’t let me edit the URL after posting, so will re-submit.
comment
> When I see that it is widely accepted that ApoB is better to measure than LDL-C, but the industry continues to measure LDL-C, but not ApoB, I wonder why. It makes me skeptical. Part of this is ju…
comment
Very interesting!
comment
Unfortunately, this is a limitation of nearly all nutritional studies. Partly we use mechanistic evidence to separate cause from effect--that's part of why the article goes into detail about, e.g…
comment
I see -- yeah, the Android metadata says "in-app messages". That refers to features where you can message support or a doctor within the app. We don't attempt to read your text messages…
comment
FYI: $190 is the price for the comprehensive health panel which includes a blood test and video visit with a doctor. You can track nutrition for free within the iPhone/Android apps.
comment
(OP) Yep--this is my philosophy. Obviously I'd love it if everybody used our product to improve their heart health, but I think it's better to write stuff that's informative and if peop…
comment
Photos are used to track nutrition -- you choose each photo to upload within the app. Location is only used, in context, to help find healthy meals near you. (You can use the app with or without enabl…
comment
This is honestly a limitation of nearly all nutrition research -- it's based on observational data. Part of the reason we expect fiber to reduce mortality, rather than simply being a marker of ot…