Tweets
- Tweets, current page.
- Tweets & replies
- Media
You blocked @DrLukeOR
Are you sure you want to view these Tweets? Viewing Tweets won't unblock @DrLukeOR
-
Pinned Tweet
To open the black box of
#AI decisions, we decided to copy humans and use language. We train a#deeplearning system to mimic the important parts of radiology reports and show that doctors prefer this text over widely used visualisation methods. Blog post: https://lukeoakdenrayner.wordpress.com/2018/06/05/explain-yourself-machine-producing-simple-text-descriptions-for-ai-interpretability/ …pic.twitter.com/yZiCPO4mAbThanks. Twitter will use this to make your timeline better. UndoUndo -
Luke Oakden-Rayner Retweeted
For those interested, here is my earlier peer review of the chatbot study undertaken by
#babylonhealth#Horizon#BBChorizonhttps://coiera.com/2018/06/29/paper-review-the-babylon-chatbot/ …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Luke Oakden-Rayner Retweeted
Wow, can’t believe my wife pulled this pumpkin carving challenge off!
@morrisonMSK@_azoga@BFlanksteak@JeffersonRadspic.twitter.com/1vf4y1FBW1Thanks. Twitter will use this to make your timeline better. UndoUndo -
Luke Oakden-Rayner Retweeted
Sneak preview - How AI can detect breast cancer - Diagnosis on Demand? The Computer Will See You Now - Horizon, BBC Two Thurs 1st Nov, 9pm. Featuring
@kheironmedical and@Liz_ORiordan. Also available on iPlayer.https://www.bbc.co.uk/programmes/p06pt9w5 …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Luke Oakden-Rayner RetweetedThanks. Twitter will use this to make your timeline better. UndoUndo
-
Luke Oakden-Rayner Retweeted
#RSNA#AI Summit has been a great venue to understand how RSNA can catalyze the use of AI in#Radiology for multiple stakeholders. Look for the white paper on this topic coming out in the new Radiology:AI journal in a few months!#leadership#business…https://lnkd.in/ebvWC6bShow this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Luke Oakden-Rayner RetweetedThanks. Twitter will use this to make your timeline better. UndoUndo
-
Time to kick off day 2 of
#RSNA's strategic#AI summit. What better way than with#pinksocks from@eranrad :)pic.twitter.com/W3t2dpWszaThanks. Twitter will use this to make your timeline better. UndoUndo -
Luke Oakden-Rayner Retweeted
Kicking off the
#RSNA 2-day AI summit@EuSoMIIpic.twitter.com/VsUBCBnfjpThanks. Twitter will use this to make your timeline better. UndoUndo -
So far I'm meeting for dinner with
@eranrad at 6. Is anyone else interested? (missed@george5152@lmprevedello last tweet, not sure who else is on Twitter)Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Phew, after 24 hrs on planes I've arrived in Chicago for the RSNA AI summit! Is anyone catching up tonight?
@cekahn@SafwanHalabi@curtlanglotz@FalgunChokshiMD@Duotango@ParasLakhaniMD@eranrad or any others?Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Luke Oakden-Rayner Retweeted
I'm constantly in awe of our machine learning team at
@KheironMedical - Here is our recent work on generating synthetic medical imaging data at the highest resolution published to date. https://arxiv.org/abs/1807.03401 https://www.youtube.com/watch?time_continue=1&v=Ro-tZ6wYn1g …Thanks. Twitter will use this to make your timeline better. UndoUndo -
Luke Oakden-Rayner Retweeted
If you’re interested in AI research, this is a must read. It’s a thoughtful commentary explaining recent progress. “Recent developments tell us more about the problems tackled & the structure of our world than about neural networks per se”https://m-cacm.acm.org/magazines/2018/10/231373-human-level-intelligence-or-animal-like-abilities/fulltext …
Thanks. Twitter will use this to make your timeline better. UndoUndo -
The biggest statistical problem lies with assuming the human is perfect. Human-model PPV diff is 0.88 in the paper. If the human overcalled one case it would be 0.44, with 2 overcalled it is zero. Assuming a human spec of 90%, at least one overcall would occur ~ 20% of the time.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
To be clear, since it always comes up, I actually like the study. The effort required to apply a model like this in a clinical environment is no joke. But I'm skeptical of the numbers, and more skeptical of the discussion. Not convinced. Like most topics, more research needed.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
But
@vgulshan et al (JAMA, 2016) found individual ophthalmologists to have a specificity around 92% (compared against a panel of experts), exactly the same as the model in this study. So humans probably have a PPV of 12% as well!Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
The baseline in this case was a single expert interpretation, which precludes any assessment of how humans might perform at the task. Since humans are the baseline, they are assumed to be perfect.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
In this paper specificity was 92% (pretty good), and PPV was 12% (sounds bad, right?). But even if the specificity was 99%, the PPV would still have been only 50%! That is the problem with low prevalence disease, and screening in general.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Interesting facts about this study: Sensitivity could have been one of three values. 0%, 50%, or 100%. They found it was 100%.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
Is anyone else a bit flabbergasted that we have been heavily discussing a study with results based on a cohort which only contains 2 patients with referable retinopathy?https://twitter.com/EricTopol/status/1045695893146546177 …
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo -
About to kick off the
#RSNAspotlight18 course on#ArtificialIntelligence in Paris. I'm up first, with a light-hearted introduction to modern AI.pic.twitter.com/wvKoONLSp4Thanks. Twitter will use this to make your timeline better. UndoUndo
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.