on Feb. 23 for our Engineering in Medicine Symposium! Sessions will showcase: Single Cell, Machine Learning, Neuroscience of Decision-Making, Development + Aging, and Tissue Eng + Instructive Biomaterials. Register
#HassanFirouzi is 34yo, and is the father of a newborn daughter who was only 18 days old at the time of his arrest. He has been sentenced to death and is enduring severe torture in prison. In a video he begs, covered in bruises, “Help me, I need to see my daughter one more time.”
A stunning example of cloud iridescence, caused by small ice crystals scattering the sun's rays, filmed in Narathiwat, Thailand.
Credit: Orawan Thongchinda
Yesterday evening we got to welcome Luna Claire Elias to the world and our family. Biqi and Luna are doing great. Wishing you happy holidays as we enjoy our own little gift!
George taught me the motto "nice, bright, and hardworking" really is the foundation of how you build great culture. Thank you for recruiting me and supporting me through the past 7 years, George!
Nice. Bright. Hard-working.
Those words described the DBMI culture under the leadership of George Hripcsak, whose 15 years as DBMI chair brought innovations, new connections within @Columbia, and the next generation of informatics leaders. @Columbiapshttps://dbmi.columbia.edu/connections-innovations-culture-george-hripcsaks-15-years-as-chair-changed-dbmi-path/…
(please retweet) I am taking CS PhD students! If you are interested in ML, data science, health, or inequality, please apply to Cornell :)
We have an island campus in New York City and a fantastic group of students I feel lucky to collaborate with every day. Join us!
Very excited & proud to publish in @JAMACardio our study of remote hypertension and cholesterol management in more than 10,000 patients @BrighamWomens, bringing specialty care to diverse patients at scale & improving clinical care https://bit.ly/3zWmBW7, https://bit.ly/3WZd0b0
Today I gave a talk to 75 people seated around the single largest table I've ever seen. It weighs 4,500 lbs and I can confidently say I've sailed on boats smaller than it. Thanks to
seminar is Harvard Business School in 1 wk for medical professionals. I went yrs ago; it was phenomenal. Go over a case on Cleveland Clinic as a class, then their CEO shows up to share more! Repeat after lunch. Free if accepted. Apply: http://bit.ly/3Se8ly3
to accelerate development and implementation of machine learning in Cardiology across NYP, Columbia, and Cornell hospitals. Really excited for the road ahead..
AI day is a perfect example of Deep Learning at its finest. Mix and match all the greatest innovations to do something drastic and super ambitious. Congrats!
My wife and I went to our first birthing class today. Our instructor informed us she'd just gone viral for filming a hawk carrying off an entire dead rat from a trash can.
So that's my explanation of what it's like to live in NYC.
In New York City, the rats go viral for eating pizza – and the hawks go viral for eating rats. Watch this bird shock onlookers in the Upper West Side by descending into a trash can and pulling out a sizable "snack."
We're hiring a postdoc & staff scientist for ML in cardiac imaging! The perks:
💽 10M ECGs, 1.5M Echos, 15M CT/XRs
📊 Two ongoing clinical trials
👩⚕️ Models ALREADY running in hospital to help pts
Lab Info
https://pierreelias.github.io
Job Info
https://nature.com/naturecareers/job/762918…
Plz share!
Day 4 of #TCT2022 is here! We’re at the Innovation Theater for a series of lectures on #AI in #cardiology & #radiology | AI is not going to take your job, says
, et al. evaluate the capabilities of AI #ECG interpretation for #cvVHD, providing a potential roadmap for screening in the future.
Don’t miss this piece now out in #JACC! https://bit.ly/3zxklUk
We've published all the code used to generate our tables/figures as well. Find this work interesting? I've made a soup-to-nuts tutorial on doing ML with ECGs! https://github.com/PierreElias/IntroECG…
Fourth, you must think about positive predictive value to get doc buy-in. How many of my patients flagged as ++ must I send to find one new pt with disease? Challenge is that means asking what's underlying prevalence of unknown disease. Answer? Model many guesses!
Third, shifting model populations showed us worse performance in our 4th hospital. I don't think this is overfitting. NYP Lawrence is much older population, and we knew model performance was worse in older cohort. We admit ignorance to how well it will perform elsewhere.
Second, non-physiologic signals exist everywhere. To make sure ValveNet didn't cheat (label leakage), we excluded ECGs w/ V-pacing & baseline wander. Why? Because they're strong signals of whose sick, & we want to max learning on physiology. Painful to throw out a 3rd of our data
First, you can't trust AUROC plots. If I want to make mine look better, I just have to include more healthy young pts that the model can be very confident are negative for disease. Without VERY clear inclusion/exclusion criteria, they are meaningless.
, 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 🧵https://bit.ly/3boQBRs
Get hired for a new job in the place you've worked at for 7 years. Then find out they've had your birthdate wrong this whole time. Tell HR your correct birthdate to fix. And then get this email...
Man this was the best thing I read all week. June Huh seems immensely humble, and one of the funniest/extreme cases of the absent-minded prof. The anecdotes are hilarious. Thx
In all seriousness, are there consequences for going against what these justices said in their confirmation hearings? Is it perjury? Appreciate links to any useful legal analysis or historical precedence.