Isaac Kohane
@zakkohane
Computer science + Biomedicine = Medicine as a Knowledge Processing Discipline @harvardMED @HarvardDBMI Prof/Dept Chair https://t.co/6qcUd2RfDs MD/PhD @NEJM AI EIC
ID:34615585
https://dbmi.hms.harvard.edu/person/faculty/zak-kohane 23-04-2009 13:48:01
12,0K Tweets
10,7K Followers
608 Following
I am very much looking forward to the 2024 Symposium on Artificial Intelligence for Learning Health Systems (SAIL) this coming week. Great lineup of speakers & panelists sail.health #sail24 #bioinformatics #artificialintelligence #healthcare
That's a wrap on this semester's DBMI at Harvard Med BMI702 Intro to #Biomedical #AI class! 🎓
Explore the syllabus and course materials, open to all: zitniklab.hms.harvard.edu/BMI702/ Harvard Medical School Harvard Data Science Initiative Kempner Institute at Harvard University
Isaac Kohane Having shared a few patients with Nicholas A. Christakis, he is also a mighty fine doctor.
Congrats.
Michael Baym Steven Strogatz [email protected] Such a good story about how a fine career unfolds. :-)
Congratulations Steven Strogatz [email protected] and Nicholas A. Christakis!!
What a day for science twitter!
#FortuneHealth is excited to welcome Isaac Kohane (Isaac Kohane), chair of the Department of Biomedical Informatics (@HarvardDBMI) at Harvard Medical School (@harvardMED), to our conference May 20–21.
See our full list of speakers here 👉 bit.ly/3Wsi6Ph
Excited to share our #echofirst foundation model is now published in Nature Medicine!
Trained on 1M Cedars-Sinai A4C echo-report pairs, EchoCLIP has strong performance on wide range of cardiac diagnostic benchmarks, including LVEF in Stanford Medicine videos (MAE 7.1%).
It's high time for a Human Envirome Project. One example why a comprehensive approach is needed: jamanetwork.com/journals/jaman… CC Chirag Patel
Policy $$$$$: Seems that payers (e.g. Medicare.gov MedicaidGov CMSGov UnitedHealth Group Aetna Humana Centene) and providers would be most interested in standardizing benchmarks for LLM medical coding. Literally billions of dollars in play depending on bias/performance.
Its been a month since we released UNI and CONCH, a vision only and a vision-language foundation model for computational pathology w/ Nature Medicine articles. The models have been downloaded over 233k times on @HuggingFace we are analyzing the early impact, see where people are…