|
Tim Miller
@
TMills
Boston, MA
|
|
Researcher in clinical #nlp at Children's Hospital Computational Health Informatics Program (CHIP) and Assistant Professor at Harvard Medical School.
|
|
|
1.918
Tweetovi
|
167
Pratim
|
453
Osobe koje vas prate
|
| Tweetovi |
|
|
Tim Miller
@TMills
|
21 h |
|
My alma mater @UMNComputerSci getting lots of shout outs from @edchi at #wsdm2020 keynote. pic.twitter.com/gAvrulvcL1
|
||
|
||
|
|
Tim Miller
@TMills
|
3. velj |
|
This looks awesome - could be a great resource for people in medicine looking to cross over to the computational side. twitter.com/jonhoo/status/…
|
||
|
|
||
| Tim Miller proslijedio/la je tweet | ||
|
Vinay Prasad
@VPrasadMDMPH
|
3. velj |
|
First, recall, there are 3 types of cancer
1. cancer that isn't going to do anything in your natural life (harmless)
2. cancer that may already be spread and will claim your life even if you find it early (spread already)
3. cancer that would be fatal, but caught by screening
|
||
|
|
||
| Tim Miller proslijedio/la je tweet | ||
|
Steve Crowley
@StevenJCrowley
|
2. velj |
|
Performance artist generates virtual traffic jams in Google Maps by pulling a wagon full of smartphones
simonweckert.com/googlemapshack… pic.twitter.com/m3bmQXvswI
|
||
|
|
||
| Tim Miller proslijedio/la je tweet | ||
|
Tom Gara
@tomgara
|
30. sij |
|
What an incredible scandal: A startup that makes medical records software used in tens of thousands of doctors offices was secretly getting paid by an opioid maker to insert a pop-up box suggesting opioid prescriptions latimes.com/business/story… pic.twitter.com/hymeMTkDyi
|
||
|
|
||
|
|
Tim Miller
@TMills
|
30. sij |
|
I don't understand - doesn't everyone with h. pylori infection typically get treated for it?
|
||
|
|
||
|
|
Tim Miller
@TMills
|
28. sij |
|
Totally agree. Rnns will return, mark my words!
|
||
|
|
||
| Tim Miller proslijedio/la je tweet | ||
|
Larry Hunter
@ProfLHunter
|
25. sij |
|
Doing this to smart young Iranians who want to do graduate school in the US is not only vilely cruel, but also self-destructive, on many levels. nytimes.com/2020/01/25/us/…
|
||
|
|
||
|
|
Tim Miller
@TMills
|
24. sij |
|
Best compliment i can give - i don't know whether i agree with this because I'm still thinking about it. twitter.com/chrislhayes/st…
|
||
|
|
||
|
|
Tim Miller
@TMills
|
24. sij |
|
My @Bos_CHIP colleague @maiamajumder is a must-follow if you are following the news about #nCoV and want level-headed up-to-the-minute analysis.
|
||
|
|
||
|
|
Tim Miller
@TMills
|
17. sij |
|
On the other hand, when I read "causal inference" my brain reads "casual inference", which sounds nice and relaxing.
|
||
|
|
||
|
|
Tim Miller
@TMills
|
14. sij |
|
You're too kind! 😊
|
||
|
|
||
| Tim Miller proslijedio/la je tweet | ||
|
|
Tim Miller
@TMills
|
13. sij |
|
My group at @bos_chip and @harvardmed is looking to hire a postdoc to work on building deep neural networks to learn patient representations across time for information extraction, prediction, clustering, etc. See here for more details:
scholar.harvard.edu/tim-miller/jobs
|
||
|
|
||
|
|
Tim Miller
@TMills
|
13. sij |
|
My group at @bos_chip and @harvardmed is looking to hire a postdoc to work on building deep neural networks to learn patient representations across time for information extraction, prediction, clustering, etc. See here for more details:
scholar.harvard.edu/tim-miller/jobs
|
||
|
|
||
|
|
Tim Miller
@TMills
|
13. sij |
|
Great point Kirk! Datasets like Thyme, i2b2, n2c2, etc., have lead to 100's of papers by other groups, including people from outside the clinical nlp world at top nlp venues. Methods proposals have nothing to do without the existence of good datasets for training and evaluation. twitter.com/kirk_roberts/s…
|
||
|
|
||
|
|
Tim Miller
@TMills
|
10. sij |
|
I shoveled snow at Lambeau exactly one time, for $7/hour over winter break when I was in college and couldn't get enough hours at my other job. I was used to shoveling my driveway. I learned a valuable lesson about how small my driveway was and how long one hour is. twitter.com/packers/status…
|
||
|
|
||
|
|
Tim Miller
@TMills
|
8. sij |
|
I’m so sorry to hear that, Melissa. You and your family will be in our thoughts.
|
||
|
|
||
| Tim Miller proslijedio/la je tweet | ||
|
Ellie Murray
@EpiEllie
|
3. sij |
|
This thread nicely highlights something that’s always bothered me with AI vs doctor comparisons — when the gold standard is the doctors’ diagnoses, AI can at best only ever do par.
If we want to move the needle, then we need to assess success on *outcomes* not diagnoses! twitter.com/VPrasadMDMPH/s…
|
||
|
|
||
| Tim Miller proslijedio/la je tweet | ||
|
Peter W. Singer
@peterwsinger
|
3. sij |
|
A good test of whether to take a politician or pundit seriously or not today is if they play the lame card of “Oh, so you think Solemani was a good guy?”
A generation of us saw that nonsense in 2003 and hopefully learned from it.
Judge act by the cost/benefits,
like an adult.
|
||
|
|
||
| Tim Miller proslijedio/la je tweet | ||
|
The Onion
@TheOnion
|
11. pro |
|
From The Archives: This War Will Destabilize The Entire Mideast Region And Set Off A Global Shockwave Of Anti-Americanism vs. No It Won’t trib.al/QwC3b1Z pic.twitter.com/rRZU0m9qMn
|
||
|
|
||