Mark Sendak

@MarkSendak

restlessly trying to drive change in health care w/

Vrijeme pridruživanja: rujan 2015.

Tweetovi

Blokirali ste korisnika/cu @MarkSendak

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @MarkSendak

  1. proslijedio/la je Tweet
    2. velj

    Performance artist generates virtual traffic jams in Google Maps by pulling a wagon full of smartphones

    Poništi
  2. proslijedio/la je Tweet
    30. sij

    Without any doubt, this was the most inclusive conference I have ever attended! Congrats to , , and all the others for this!

    Poništi
  3. 30. sij

    Super excited to see what and come up with for 2021 in Toronto!

    Poništi
  4. proslijedio/la je Tweet
    30. sij

    Glad I don't have to keep this a secret anymore - is in Toronto next year! Excited to welcome everyone up to Canada in January ❄️❄️❄️ 🇨🇦🇨🇦🇨🇦

    Poništi
  5. proslijedio/la je Tweet
    30. sij
    Odgovor korisnicima i sljedećem broju korisnika:

    Absolutely. But a predictor in a model doesn't have to be on the causal pathway. And causal inferences from a prediction model should be avoided.

    Poništi
  6. proslijedio/la je Tweet
    30. sij
    Odgovor korisnicima i sljedećem broju korisnika:

    Indeed. Causal language/inference and any mention of confounding should be avoided in prediction model studies. Focus is on the ability to predict something from something else. Nothing more nothing less.

    Poništi
  7. 30. sij

    Wow, amazing keynote today. Worth watching!

    Poništi
  8. proslijedio/la je Tweet

    Thank you! It’s so important to us (and really basic logic, as it lets us attract and retain amazing parents in our conversations that are not properly accommodated elsewhere)

    Poništi
  9. proslijedio/la je Tweet
    28. sij

    A photo is a mathematical representation of your face.

    Poništi
  10. proslijedio/la je Tweet
    28. sij

    What fascinates me most about this paper is the mention of the “emotional labor” that had to be done by (presumably mostly female) nurses mediating between this diagnostic ML system and the egos of (presumably mostly male) doctors.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    28. sij

    Do you think is a far-off dream in healthcare? Think again! This cool review highlights some of the already-implemented applications of for EHR data. Some examples: -sepsis algorithms -ED triaging -PNA scoring -C. diff infection algorithm Check it out!

    Poništi
  12. proslijedio/la je Tweet
    28. sij

    Recommend reading this 👇by et al. Outside the scope of this current work, but would be useful to see a detailed critical appraisal of these 21 products, and see the (relatively thin?) evidence-base which attracted $$$ to produce at scale.

    Poništi
  13. proslijedio/la je Tweet
    28. sij

    Hi ! Here is the table + our paper link. TL;DR Achieving accountable and trustworthy AI means designing interventions as *socio*-technical systems with constant input from stakeholders and local expertise (not necessarily an explainable model).

    Prikaži ovu nit
    Poništi
  14. 28. sij
    Poništi
  15. proslijedio/la je Tweet
    28. sij

    So fun to see worlds collide: my old college friend and my tech+society friend co-presenting at about building trust and accountability into AI applications in medicine!

    Poništi
  16. 28. sij

    Also features the great work out of by

    Prikaži ovu nit
    Poništi
  17. 28. sij
    Prikaži ovu nit
    Poništi
  18. 28. sij

    It was fun to place our own work in the context of many others paving the way in this field (incl ) and it's exciting to see what's to come. Hope this helps share insights with folks who've been asking for real use cases

    Prikaži ovu nit
    Poništi
  19. 28. sij

    (5)Still a long way to go for any of these products to successfully scale and diffuse across settings. Many challenges remain.

    Prikaži ovu nit
    Poništi
  20. 28. sij

    (4)There is a great deal of stealth science. Many of the products have 0 peer-reviewed published findings. This includes anything related to statistical, clinical, or economic utility. Unfortunately, it's common:

    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·