back
user profile
brandonb
9,345karma·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 paper's original title is 66 characters too long for HN. The "25% higher mortality" comes from the all-cause mortality result in "Findings", which is one of the main resul…
comment
This is really cool. Have you (or your colleagues) written anything about what you learned about ML for drug discovery?
comment
This study followed 5,294 people for 20 years. People in the highest third of inflammation (hs-CRP > 5) had 32% higher chance of heart disease and 25% higher mortality from any cause. Inflammation …
comment
Sometimes people assume heart disease is a modern problem that didn't plague ancient societies. This is one study that shows it's not.
comment
At least in the US, health insurers can’t raise rates or deny coverage based on pre-existing conditions. That was a major part of the Affordable Care Act.
comment
What’s your source on Apple not using the neural network for VO2Max estimation? They’ve been using on-device neural networks for various biomarkers for several years now (even for seemingly simple me…
comment
FWIW, we're working on something similar (you wouldn't necessarily need to write R or Python). Feel free to email me at bmb@empirical.health and I can add you to a beta once we have it ready…
comment
By 2018, the concept was definitely in the air since you had GPT-1 (2018) and BERT (2018). You could argue even Word2Vec (2013) had the core concept of pre-training on an unsupervised or self-supervis…
comment
In the paper, they say they can't release the weights due to terms of consent with study participants (this is from the Apple Heart and Movement study).
comment
Not yet -- this one is just a research study. Some of their previous research has made it into product features. For example, Apple Watch VO2Max (cardio fitness) is based on a deep neural network publ…
comment
I worked on one of the first wearable foundation models in 2018. The innovation of this 2025 paper from Apple is moving up to a higher level of abstraction: instead of training on raw sensor data (PPG…
comment
In medicine, there's often tradeoff between health and cost. GLP-1s are an obvious example, costing $10,000 per year but saving lives. This study shows an exception to that rule -- testing Lp(a),…
comment
This happens a lot in medicine due to believing observational data rather than randomized control trials. An entire book was written on Medical Reversal by the person who's now head of CBER at FD…
1 pts
3 pts
3 pts