Arjun (Raj) Manrai

@arjunmanrai

Assistant Professor , . Stats+ML for improving clinical decision making and scientific reproducibility.

Boston, MA
scholar.google.com/citations?user…
Vrijeme pridruživanja: srpanj 2014.

Medijski sadržaj

  1. 27. sij

    Excited to announce a new version of our course at Harvard, BMI704: Data Science for Medical Decision Making, and to be teaching with . We'll release lectures, data, and an interactive text of data science methods at link below. Sched + Readings:

    Korisnici , , i
    29 proslijeđenih tweetova 97 korisnika označava da im se sviđa
  2. 8. sij
    Odgovor korisnicima

    A PAC of ML researchers?

    1 proslijeđeni tweet 4 korisnika označavaju da im se sviđa
  3. 6. sij

    Reproducing neural architecture search for some ML models can cost 3 R01 grants, but do most medical applications need this? Our take on the top challenges to reproducibility of machine learning in medicine in the latest :

    , , i još njih 3
    21 proslijeđeni tweet 53 korisnika označavaju da im se sviđa
  4. 18. pro 2019.

    Incredibly privileged to work alongside this group and proud of all they accomplished in 2019. Excited for the next year!

    2 proslijeđena tweeta 20 korisnika označava da im se sviđa
  5. 16. pro 2019.

    ⁦⁩ at ⁦⁩ today demonstrating the power of human networks to shape our health and our lives.

    3 proslijeđena tweeta 11 korisnika označava da im se sviđa
  6. 10. pro 2019.

    Breadth and depth on display at ⁦⁩

    1 proslijeđeni tweet 3 korisnika označavaju da im se sviđa
  7. 2. pro 2019.

    Honoring 's Pete Szolovits at , shares 3 articles by Pete that were decades ahead of their time and are being recapitulated today.

    20 proslijeđenih tweetova 55 korisnika označava da im se sviđa
  8. 12. stu 2019.

    ⁦⁦⁩ post journal club fun at ⁦⁩ just outside our new space! cc ⁦⁦⁩ ⁦⁩ ⁦⁩ ⁦⁩

    1 reply 3 proslijeđena tweeta 28 korisnika označava da im se sviđa
  9. 6. stu 2019.

    How can we measure the exposome comprehensively and associate it with disease? Watch 's talk live now:

    8 proslijeđenih tweetova 18 korisnika označava da im se sviđa
  10. 5. stu 2019.

    I just got this CV in response to this post. Thank you, internet.

    9 korisnika označava da im se sviđa
  11. 26. ruj 2019.

    ⁦⁩ recognizing talented undergrads and sharing impressive stories of students cracking difficult clinical cases.

    4 proslijeđena tweeta 16 korisnika označava da im se sviđa
  12. 26. ruj 2019.

    Boston Children’s COO Kevin Churchwell discussing how ⁦⁩ leads informatics efforts at the clinical front lines

    5 proslijeđenih tweetova 9 korisnika označava da im se sviđa
  13. 31. srp 2019.

    Snapshot of the heterogeneity in the number of patients, clinical tasks, and architectures used to train machine learning models applied to electronic health records data. From recent paper by et al.:

    5 proslijeđenih tweetova 13 korisnika označava da im se sviđa
  14. 25. srp 2019.

    The most cited in the past 3 years is a paper.

    1 reply 10 proslijeđenih tweetova 38 korisnika označava da im se sviđa
  15. 8. srp 2019.

    or ?

    Korisnici , i
    3 proslijeđena tweeta 2 korisnika označavaju da im se sviđa
  16. 9. lip 2019.

    That feeling when the inimitable shows your paper at ICML 2019

    Korisnici , i
    4 proslijeđena tweeta 30 korisnika označava da im se sviđa
  17. 26. tra 2019.

    Demographic factors alone explained ~45% of the variance in obesity prevalence across U.S. counties in this new study.

    8 proslijeđenih tweetova 12 korisnika označava da im se sviđa
  18. 25. tra 2019.

    A non-angelic usage of HARK we should all know: "hypothesizing after the results are known". Concise and important piece by on the "four horsemen of irreproducibility":

    1 proslijeđeni tweet 1 korisnik označava da mu se sviđa
  19. 10. tra 2019.

    A number of approaches to prioritize signals among the many significant findings may help, each with its own strengths and limitations. Here are a few we suggest: 9/n

    2 proslijeđena tweeta 4 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
  20. 10. tra 2019.

    There are key implications for non-genetic association studies incl. likely massive residual confounding in some cases. We will need to be nuanced with findings from large country-scale biobank studies going forward given the relationship between λ_X and sample size. 8/n

    1 reply 1 proslijeđeni tweet 1 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit

@arjunmanrai još nije poslao/la nijedan tweet s fotografijama ili videozapisima.

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:

    ·