Leo Bman

MD/PhD student @Iowa, aspiring general surgeon (applying 2021)

[Leo Bman @LeoBman]

@DanMatasic Great read and good work Dan, thanks for sharing

[Matthew Lungren MD MPH @mattlungrenMD]

The skies tell us end is near... 😨

BUT antidote to tragedy is generosity 😇

Introducing RSPECT! @RSNA Pulmonary Embolism CT Dataset

𝟏𝟐𝐤 𝐂𝐓𝐬 - 𝐞𝐱𝐩𝐞𝐫𝐭 𝐥𝐚𝐛𝐞𝐥𝐬 - 𝟓 𝐬𝐢𝐭𝐞𝐬 - 𝟒 𝐜𝐨𝐮𝐧𝐭𝐫𝐢𝐞𝐬

Available now!

@kaggle challenge: https://t.co/l1LKrJQ4ko

[Leo Bman @LeoBman]

@ianpanmd I'm curious to take a look & may be able to help out. thanks!

[Lauren Oakden-Rayner 🏳️‍⚧️ @DrLaurenOR]

"The medical #AI floodgates open, at a cost of $1000 per patient."

My new blog post on the unexpected, important, and controversial decision for Medicare in the US to pay up to $1000 per case for a #machinelearning model to detect stroke on CT scans.

https://t.co/SWvwYuySDv

[AI at Meta @AIatMeta]

FastMRI uses AI to generate MRIs from about ¼ the data as a conventional scan. See how it works:
https://t.co/u1OodJ1JTs

[Leo Bman @LeoBman]

@hardmaru False. Video game skins ;)

[Leo Bman @LeoBman]

@ben_j_radford @fchollet See @fchollet response here https://t.co/n2WLE2EDju

Sounds closer to completely out-of-sample

[STAT @statnews]

Congratulations to these 32 teams who have advanced to Round 2 of our #STATMadness competition!
Cheers to you, #Breakthru32!

@kochinstitute
@EmoryMedicine
@Texas_Heart
@UCIrvineSOM
@UCSDMedSchool
@BrighamWomens
@StJudeResearch
@MDAndersonNews
@WeillCornell
@UofUHealth

[Leo Bman @LeoBman]

@NeuroStats @GaelVaroquaux @danilobzdok @KordingLab @bttyeo @f2harrell I've never run across the situation where the outcome measure was missing and I wanted to impute it, but if it was me I would only use these samples in the training data, and then check if including these observations actually improves test set performance

[Leo Bman @LeoBman]

@fchollet The "cellular automata" notebook shows people are starting to think a bit outside the DL/CNN box https://t.co/dn5fHeZgK0

[Leo Bman @LeoBman]

@sarim_m @AmineKorchiMD Agreed. I think things like @EyeDiagnosis and @CaptionHealth are good examples of fitting into clinical workflow. 1st allows autonomous referral to specialist in primary care setting. 2nd could expand number of people able to take diagnostic quality images.

[STAT @statnews]

BREAKING: FDA approves a generic version of the drug Martin Shkreli monopolized https://t.co/yB7EDy728a

[Leo Bman @LeoBman]

@ClaraGFaria1 @BioGoertz @AcademicChatter I've never tried matlab, but my comp psych lab uses R. R has a big community base online like python

[Leo Bman @LeoBman]

@GaelVaroquaux @C_Allefeld @condaforge R package installations seem to handle dependencies well 95% of the time. Moving from r to python I was surprised by how much more complicated things got, with needing separate envs via conda to keep things straight

[Leo Bman @LeoBman]

@woeaton @AcademicChatter This is an ad

[Brain @Brain1878]

Hippocampal vascularization patterns vary between individuals. Perosa et al. show that a mixed hippocampal supply, as opposed to a single one, provides a hippocampal vascular reserve that protects against cognitive impairment. https://t.co/t3KOyMFowr

[Antonio Regalado @antonioregalado]

Amazing new case of a genetic drug developed for a single child w/ a unique DNA mutation. N-of-1 medicine.

Told by @Erika_Check & chronicling persistence of @BradMargus, science of @timyu; commentary from @eperlste, @DrStanleyCrooke + more

https://t.co/G9IZfRw89b

[Leo Bman @LeoBman]

Really interesting and well written paper on meta-learning

problem:
DL models sequentially trained on new classes of data "forget"/overwrite what was prev learned

solution:
Arch that learns to gate model updates, allowing diff parts of ntwk to specialize

#AI #MachineLearning

[Jeff Clune @jeffclune]

Learning to Continuously Learn. ANML meta-learns to reduce catastrophic forgetting, and can learn at least 600 tasks (Omniglot classes) sequentially and performs well on most afterwards. arXiv https://t.co/BZzRHOSz9P NeurIPS talk https://t.co/mXkF359d9v Led by Shawn Beaulieu 1/2

[Leo Bman @LeoBman]

Very cool digital phenotyping project by fellow grad student @TannerKoomar

A booth that sits in @uihealthcare clinics and gathers language phenotypes

[Tanner Koomar @TannerKoomar]

Always working to engage more of the public in scientific research. To that end, we have deployed this soundproof booth in a hospital clinic waiting room where patients can participate in our language research while waiting for their appointment! #sciComm https://t.co/3rULFUphST