To keep up to speed with recent work on abstractive summarization, I wrote a (little) lit review called "Sending out an SOS (Summary of Summaries)". link.medium.com/nyveXXbcG8

I am ready to get to work leading nychealthy, the finest health department in the country. Public health is a calling I've answered throughout my career—I invite you to read the remarks I shared earlier about my story. Please follow me at Dr. Michelle Morse medium.com/@NYCMayorsOffi…

In our Mayo Clinic Proceedings paper on pts admitted with #COVID19, we discuss findings helpful for early triage to floor vs ICU. Takeaway: EKG in ED is important--look for afib/flutter, RV strain, ST segment changes. Big thx to Nir Uriel, MD MSc and Columbia Medicine team! mayocl.in/31ZoteT

Our paper on causal inference explores the use of GANs for finding comparable cohorts. Congrats Amelia J. Averitt, MPH MA PhD, great work!

Attributable risks (ARs) support inference of whether an outcome is caused by an exposure. At #OHDSI2020, I will present my #NORAModel- a #Bayesian method of AR estimation that rectifies evidence at the population & individual-level. DM me! #CausalTwitter youtu.be/_FZWDbiNi4I

My paper got an #honorablemention in the #AMIA2020 Year in Review! It uses #epidemiology+#informatics+#EHRs to study the #opioid crisis. Read it here 👉 bit.ly/3nvgoaQ @BenSlovis Adler Perotte

A great reason to apply for a postgrad at DBMI - our faculty! 👀 the video below & apply (gsas.cuimc.columbia.edu/applying) by the Dec. 1 deadline! Noémie Elhadad @nicktatonetti Adler Perotte Chunhua Weng Sarah Rossetti Suzanne Bakken Virginia James Cimino ➡️ youtu.be/CtB2un1rf4I

Now, what if the confounders were specified as a function of interventions of interest: h(T)? Like population structure in a GWAS problem? We call this problem Estimation with Functional Confounders (EFC): nips.cc/virtual/2020/p… Work with Adler Perotte and Rajesh Ranganath.

I'm honored that Adler Perotte's and my poster -- #NORAModel -- was named best contribution for #MethodsResearch at #OHDSI2020.🥲There were so many wonderful presentations this year! If you're interested in learning more about this #Bayesian #machinelearning model, DM me!

A little casual causal philosophizing for your upcoming holiday celebration. Thanks Pod of Asclepius and Glen Colopy for the opportunity! Based on the great work of Amelia J. Averitt, MPH MA PhD. youtu.be/DOf2lVHzZS4

We looked at ECG abnormalities of #COVID19 patients, out in JAHA. Particularly alarming was afib/flutter pts had 59% mortality vs 21% in those without (HR 2.1 in Cox model). Many thanks to Elaine Wan, Nir Uriel, MD MSc, and Columbia Cardiology Fellows team. bit.ly/3hpBd5X

A true team effort - very proud of our work predicting complications of COVID in hospitalized patients. Thanks to our clinical colleagues. Great job Victor and Shreyas Bhave PhD, in particular! bit.ly/3qYy1Bu

Available FREE in #JAMIA, an article reviews development and validation of prediction models for mechanical ventilation and readmission in COVID patients. With authors Shreyas Bhave PhD, Noémie Elhadad, Jason Adelman MD MS, Pierre Elias, MD, & more! #COVID #readmission ow.ly/WaWL50E1foA

Congratulations to 2021 PhD graduate Tian Kang, who led the study "A neuro-symbolic method for understanding free-text medical evidence” recently published by #JAMIA. AMIA Chunhua Weng Adler Perotte ➡️ academic.oup.com/jamia/advance-…

In our latest News and Views: @nicktatonetti and Noémie Elhadad discuss new data on the use of fine-scale genetic ancestry as a potential new tool for #precisionmedicine nature.com/articles/s4159…

Welcome Gamze!!

Congratulations Amelia J. Averitt, MPH MA PhD!!

Come learn about ML in cardiology at our #AMIA2021 workshop! Discussing work/collabs of euan ashley Stanford AIMI David Ouyang, MD Columbia Cardiology Fellows Columbia DBMI Matthew Lungren MD MPH. Will share the best resources we've found to get you started. Sold out but show up and we'll make it work!

Come join us at the poster session 7:30-9pm New York Time (EST) at #neurips2021 Poster Session 2, Location A2! nips.cc/virtual/2021/p…. Joint work with Xintian Han along with @lycanduo, Thomas Wies, Adler Perotte, and Rajesh Ranganath!

Out today in JACC Journals, our ValveNet study shows a ML model can detect mod-severe left sided valve disease from ECG. This model is currently running live in our health system daily. Now let me tell you everything wrong with it! A brief 🧵 bit.ly/3boQBRs