Sublime
An inspiration engine for ideas
Clean Eating
sari • 24 cards
1/ Patient race in health datasets is often reported coarsely: for example, both Indian and Chinese patients are categorized as “Asian”. Does the coarse coding of race hide disparities in clinical machine learning performance?
In our new working paper (!), we find that it does. https://t.co/8rIsj2GvzP
Raj Movvax.comWhen I look at a patient’s blood panel for the first time, my eyes immediately dart to two numbers: apoB and Lp(a). I look at the other numbers, too, but these two tell me the most when it comes to predicting their risk of ASCVD. ApoB not only tells me the concentration of LDL particles (which, you’ll recall, is more predictive of disease than the
... See morePeter Attia MD • Outlive: The Science and Art of Longevity
Culture of Fermentation
david • 1 card
medical
Utkarsh Singh • 1 card
Chemistry
Kevin Mialky • 16 cards