Discover and read the best of Twitter Threads about #deepmedicine
Most recents (6)
#ArtificialIntelligence has the ability to bring the fourth industrial revolution. Healthcare is deemed to be an industry which can get transformed the most.
#DeepMedicine
#DeepMedicine
@EricTopol is a #cardiologist, historian of the present and a #MedicalFuturist.
He believes that the way we practice medicine now ( #ShallowMedicine ) relies too heavily on human inputs and is thus plagued by human biases and imperfections.
#DeepMedicine
He believes that the way we practice medicine now ( #ShallowMedicine ) relies too heavily on human inputs and is thus plagued by human biases and imperfections.
#DeepMedicine
"The physical examination seems to have become an anachronism, a vestigial remnant, of clinical care."
"The avoidance of touch is bad medicine." thelancet.com/action/showPdf… by @richardhorton1 @TheLancet
like the plea for this in #DeepMedicine to make #healthcare more human again
"The avoidance of touch is bad medicine." thelancet.com/action/showPdf… by @richardhorton1 @TheLancet
like the plea for this in #DeepMedicine to make #healthcare more human again
@richardhorton1 @TheLancet More on the essentiality of touch in medicine @hastingscenter by Robert Truog onlinelibrary.wiley.com/doi/epdf/10.10…
@richardhorton1 @TheLancet @hastingscenter From #DeepMedicine, the section on the primacy of the physical exam for the patient-doctor relationship. Human touch.
Most deep learning #AI work to date has been supervised. 1. Now we're seeing a trend towards much more unsupervised, aka "self-supervised" (after @ylecun) or weakly supervised.
Figure from @GaryChoy in #DeepMedicine
Figure from @GaryChoy in #DeepMedicine
It's even worse than that. In the US, 3 consecutive years of declining life expectancy (unprecedented) and now ~$11,000 per person #healthcare spending economist.com/graphic-detail… @ECONdailycharts @TheEconomist
And the negative outlier US data extends to other key metrics including infant, childhood and maternal mortality
from #DeepMedicine
from #DeepMedicine
Why did the outcome curves for the US vs other countries start to diverge around 1980?
@afrakt explored that last year @UpshotNYT: nytimes.com/2018/05/14/ups… w/ many ideas including "administrative costs," the longevity metric, lack of price controls, prospective payments began, etc
@afrakt explored that last year @UpshotNYT: nytimes.com/2018/05/14/ups… w/ many ideas including "administrative costs," the longevity metric, lack of price controls, prospective payments began, etc
Some features that differentiate Shallow Medicine, as currently practiced, and the potential of #DeepMedicine, powered by #AI
Scratches the surface of the book, some supportive data in this thread
Scratches the surface of the book, some supportive data in this thread
There are at least 12 million diagnostic errors/ year and the leading cause is failure to consider the diagnosis (which relates to System 1 thinking)
Humans have 185 different types of biases which leads to misdiagnosis. Example: failing to diagnose heart attacks because doctors think they don't occur in people age < 40
A reflection back on the #NHS review (topol.hee.nhs.uk) and some differences between #US and #UK #healthcare:
1. The #1 source of jobs in both countries is from healthcare, which continues to rise with a steep slope (mostly non-physicians)
1. The #1 source of jobs in both countries is from healthcare, which continues to rise with a steep slope (mostly non-physicians)
The #US now spends more than $11,000 per person for healthcare, while the #UK ~$4,000. Yet life expectancy has declined in the #US for each of the past 3 years, while it continues to increase in the #UK (graph adopted from @OurWorldInData)
3. The @commonwealthfnd ranks the #UK first and the #US last of 11 countries overall, with differences in 5 sub-categories charted here
commonwealthfund.org/press-release/…
commonwealthfund.org/press-release/…
