I get the impression that Theranos' tech could work for some applications if it was competently executed. There must be a huge amount of useful information in a capillary blood sample, and probably there is some level of tech that could extract it. Yes?
-
-
Replying to @RokoMijicUK
That’s what I thought but apparently
@halvorz disagrees.2 replies 0 retweets 2 likes -
Replying to @s_r_constantin @RokoMijicUK
my understanding (to be clear this is not my area of expertise) is that the tiny volumes of blood used inevitably lead to wildly variable results, especially if you want to run multiple tests from a single draw
3 replies 0 retweets 0 likes -
Replying to @halvorz @s_r_constantin
I doubt that there's literally no info in that blood. Maybe one needs to rethink all the tests. Instead of testing one compound, make a model that predicts things using all the available info and a big, sophisticated ML model. BTW, would I look good in a black turtleneck?
2 replies 0 retweets 2 likes -
Replying to @RokoMijicUK @halvorz
You need a biobank or hospital partnership to make that happen, but maybe!
1 reply 0 retweets 1 like -
But then you run into the same problem as uBiome. If you’re not measuring the levels of a specific molecule, but your own composite score, then you have to prove to the satisfaction of doctors and insurers that this score can be used to make actual medical decisions.
2 replies 0 retweets 0 likes -
Replying to @s_r_constantin @halvorz
I don't have a good intuition for how hard the regulatory hurdle is. But it's obvious to me that a composite score will outperform [M] for any single molecule M.
1 reply 0 retweets 0 likes -
-
Replying to @halvorz @RokoMijicUK
It might! But it isn’t in use *yet* and you have to convince doctors that it’s better than what they’re doing, and they’ll want human data, and they probably should.
1 reply 0 retweets 0 likes -
So unless you can go back in time and teach doctors from the 1950s or before about machine learning, you have to run human studies.
2 replies 0 retweets 0 likes
“Make human studies cheaper” is a great deregulation mission. “We don’t need no stinkin’ human studies” is a terrible one. (It figures that the latter is what has gotten political traction.)
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.