back
user profile
brandonb
9,346karma·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 paper is relevant to Long Covid, where many patients have reduced parasympathetic function and suffer post-exertional malaise (PEM). The fact that vagus nerve stimulation improves VO2Max in healt…
comment
These new guidelines make use of a new heart disease risk model, PREVENT. PREVENT predicts the risk of a heart attack, stroke, or other major cardiovascular event over the next 10 years or 30 years. B…
comment
The FDA standard for blood oxygen sensing is within 6% absolute, 95% of the time. So variability in the sensing is pretty normal, and you want to look at long-term trends rather than individual measur…
comment
This Deep Learning textbook by Ian Goodfellow is a good intro to the fundamentals:
https://www.deeplearningbook.org/ It does require some math, but has an appendix with a refresher.…
comment
Apple was in a patent dispute over this feature with Massimo. Their workaround is to calculate blood oxygen on the iPhone, using the sensors from Apple Watch. The Apple Watch hardware is otherwise the…
comment
Apple was in a patent dispute over this feature with Massimo. Their workaround is to calculate blood oxygen on the iPhone, using the sensors from Apple Watch. The Apple Watch hardware is otherwise the…
comment
In a study of 200,000 people, apolipoprotein B (apoB) and lipoprotein(a) [Lp(a)] give a much earlier and more accurate read on heart disease risk than the usual cholesterol tests. People with the same…
11 pts
comment
If you’re in the top quartile of Lp(a), your overall risk of heart disease is about 114% higher. This is because each Lp(a) particle is about 6x more atherogenic than a "normal" LDL particle…
comment
Researchers adapted the PREVENT equations to calculate the age of your heart (published in JAMA Cardiology this week). The PREVENT equations are statistical models that predict your risk of a heart at…