alphaoverlord

I don’t think the examples shown reflect an element of critique.

If you have complete AV block, a leadless pacemaker is less good than one with multiple leads, since it allows pacing multiple chambers and maintaining synchrony between A and V.

Not all treatments are equally likely as well. Given how good dietary science is outside of cancer, less optimistic at rigorous studies in this area.

It’s a research dataset, similar to MNIST or CIFAR. Stanford does not want to be in the business of monetizing patient data, so it restricts commercial use.

With AIMI, we released EchoNet-Dynamic, the largest open dataset of echocardiograms (cardiac ultrasounds) and expert cardiologist labels as part of a paper published last year. The dataset went through a rigorous review to make sure no identifying information was leaked as part of the process. Happy to answer any questions.

There are definitely doctors who will space it out if you’re stable or do a phone refill

I have absolutely nothing against CGMs, but the author confounds measurement error (which can happen in both blood tests as well as subcutaneous measurement which a CGM does), thresholding on a population level (I doubt anyone thinks an A1c of 4.5 and 5.6 are the same), and weak evidence of impact in actual health outcomes. It’s fun in the same way a Fitbit/Apple Watch is fun, but I don’t think one should oversell it’s utility.

I think number of launches was used as a proxy for number of satellites launched in the last month - more satellites/launch shouldn't impact it that much.

Medical doctors at universities and medical schools generally make 50% of salaries for private practice.

Less, it’s not on label for aortic regurgitation, only aortic stenosis.

As a physician, I can say that is not true