DBMI at Harvard Med (@harvarddbmi) 's Twitter Profile
DBMI at Harvard Med

@harvarddbmi

Department of Biomedical Informatics at @Harvard/@harvardmed: #datascience- & #AI/#ML-powered models of clinical care to advance human health. Chair @zakkohane.

ID: 2578833583

linkhttps://dbmi.hms.harvard.edu/ calendar_today20-06-2014 15:03:41

2,2K Tweet

7,7K Followers

681 Following

DBMI at Harvard Med (@harvarddbmi) 's Twitter Profile Photo

Register now for Precision Medicine 2024: Education in the AI Era on 10/1/24 organized by Arjun (Raj) Manrai! Keynotes Courtney Morales Hofmann & Holly Gilmer Michigan Head & Spine Institute -- (248) 784-3667, Ethan Mollick The Wharton School; GPT-4 debate Isaac Kohane vs. Peter Szolovitz MIT CSAIL. Full agenda: bit.ly/pm24hms

Register now for Precision Medicine 2024: Education in the AI Era on 10/1/24 organized by <a href="/arjunmanrai/">Arjun (Raj) Manrai</a>! Keynotes Courtney Morales Hofmann &amp; Holly Gilmer <a href="/MHSIDetroit/">Michigan Head & Spine Institute -- (248) 784-3667</a>, <a href="/emollick/">Ethan Mollick</a> <a href="/Wharton/">The Wharton School</a>; GPT-4 debate <a href="/zakkohane/">Isaac Kohane</a> vs. Peter Szolovitz <a href="/MIT_CSAIL/">MIT CSAIL</a>. Full agenda: bit.ly/pm24hms
Conversations on Health Care (@chcradio) 's Twitter Profile Photo

Some patients are concerned about how far #artificialintelligence is creeping into the exam room. But #AI has been part of #healthcare longer than most realize, according to NEJM AI Editor-In-Chief Isaac Kohane. Learn more about AI's potential: chc1.co/740. #podcast

Harvard Medical School (@harvardmed) 's Twitter Profile Photo

An AI tool is helping researchers understand how proteins work in different cell and tissue environments to better illuminate their role in health and disease bit.ly/3WXpFvE

Pranav Rajpurkar (@pranavrajpurkar) 's Twitter Profile Photo

When should we trust a radiology report generation model? When the metrics say to. But when should we trust the metrics? New paper ✨ ReXamine-Global, a framework for stress-testing metrics used to automatically score AI-generated radiology reports. Oishi Banerjee

When should we trust a radiology report generation model? When the metrics say to. But when should we trust the metrics?

New paper ✨ ReXamine-Global, a framework for stress-testing metrics used to automatically score AI-generated radiology reports. <a href="/obanerjee13/">Oishi Banerjee</a>
Countway Library (@hmscountway) 's Twitter Profile Photo

We're excited to share that the FREE sunscreen dispensers sponsored by Harvard Zhu Center for Global Cancer Prevention and Countway Library are installed and ready to use! Check them out at the #CountwayCommunityGarden and under the Countway Courtyard tent. 🌞 #sunsafety #countwaycares 🔗countway.info/sunsafety

Heng Li (@lh3lh3) 's Twitter Profile Photo

Preprint on "BWT construction and search at the terabase scale". We can compress 100 human genomes to 11GB in 21 hours, find SMEMs with it, do affine-gap alignment and retrieve similar local haplotypes. 7.3Tb commonly sequenced bacterial genomes ⇒ 30GB arxiv.org/abs/2409.00613

Preprint on "BWT construction and search at the terabase scale". We can compress 100 human genomes to 11GB in 21 hours, find SMEMs with it, do affine-gap alignment and retrieve similar local haplotypes. 7.3Tb commonly sequenced bacterial genomes ⇒ 30GB arxiv.org/abs/2409.00613
Elliot Hershberg (@elliothershberg) 's Twitter Profile Photo

This is absurdly cool. As a professor, drops a solo preprint describing creation of indices for terabytes of metagenomic data, implemented in one Github repo of carefully handcrafted C code with all files at the root level of the repo. The paper is just one 754 line Tex file.

This is absurdly cool.

As a professor, drops a solo preprint describing creation of indices for terabytes of metagenomic data, implemented in one Github repo of carefully handcrafted C code with all files at the root level of the repo.

The paper is just one 754 line Tex file.
Kun-Hsing Yu (@kunhsingyu) 's Twitter Profile Photo

Excited to share that our paper on a foundation AI model for cancer prognosis and pathology diagnosis is published in Nature today. nature.com/articles/s4158… DBMI at Harvard Med NIH NIGMS CDMRP American Cancer Society #AI #DigitalPathology

DBMI at Harvard Med (@harvarddbmi) 's Twitter Profile Photo

New AI model "CHIEF" (Clinical Histopathology Imaging Evaluation Foundation), from DBMI's Kun-Hsing Yu and colleagues, can perform a wide array of diagnostic tasks and was tested on 19 cancer types, giving it a flexibility similar to that of large language models such as ChatGPT.

New AI model "CHIEF" (Clinical Histopathology Imaging Evaluation Foundation), from DBMI's <a href="/kunhsingyu/">Kun-Hsing Yu</a> and colleagues, can perform a wide array of diagnostic tasks and was tested on 19 cancer types, giving it a flexibility similar to that of large language models such as ChatGPT.
DBMI at Harvard Med (@harvarddbmi) 's Twitter Profile Photo

The renovated Countway Library Library is a lovely space that DBMI at Harvard Med is lucky to share and pass through each day on our way to the upper floors. Check out slides 6-10 in the American Libraries 2024 Library Design Showcase. bit.ly/4cT9IwK

Adrian Cazares 🇲🇽 (@cazares_adr) 's Twitter Profile Photo

#Phages that target bacteria carrying #plasmids, a forgotten but fascinating interaction coming back to life. Our new short commentary article highlights past, present, and potential future research in this exciting area. Out in Nature Reviews Microbiology 👇 nature.com/articles/s4157…

Isaac Kohane (@zakkohane) 's Twitter Profile Photo

How should bemused medical educators think about the use of AI in their pedagogy? Among the many discussions on this topic at our annual Harvard Medical School DBMI at Harvard Med Precision Medicine conference, we are lucky to have Ethan Mollick speak about how he's restructured educational plans in

How should bemused medical educators think about the use of AI in their pedagogy? Among the many discussions on this topic at our annual <a href="/harvardmed/">Harvard Medical School</a>  <a href="/HarvardDBMI/">DBMI at Harvard Med</a>  Precision Medicine conference, we are lucky to have <a href="/emollick/">Ethan Mollick</a> speak about how he's restructured educational plans in
Marinka Zitnik (@marinkazitnik) 's Twitter Profile Photo

Had a fantastic time connecting with researchers at CZI Science #CellScience annual meeting and sharing our latest work. Now heading to Boston, aiming to make it just in time for DBMI at Harvard Med Science Day!

Had a fantastic time connecting with researchers at <a href="/cziscience/">CZI Science</a> #CellScience annual meeting and sharing our latest work. Now heading to Boston, aiming to make it just in time for <a href="/HarvardDBMI/">DBMI at Harvard Med</a> Science Day!
Isaac Kohane (@zakkohane) 's Twitter Profile Photo

Best part of being a Professor: working with doctoral students like Elizabeth Healey Payal Chandak working at the frontier of AI and clinical medicine. Seen here DBMI at Harvard Med Harvard Medical School Science Day (courtesy of Merck loaning their spacious conference center).

Best part of being a Professor: working with doctoral students like <a href="/Liz_Healey_/">Elizabeth Healey</a>  <a href="/payal_chandak/">Payal Chandak</a> working at the frontier of AI and clinical medicine. Seen here <a href="/HarvardDBMI/">DBMI at Harvard Med</a> <a href="/harvardmed/">Harvard Medical School</a> Science Day (courtesy of <a href="/Merck/">Merck</a> loaning their spacious conference center).
David Shaywitz (@dshaywitz) 's Twitter Profile Photo

If you care abt AI in medicine you're likely already following Arjun (Raj) Manrai & aware of him as co-host of fantastic @nejm AI podcast. Incredibly fascinating DBMI at Harvard Med science day to learn scope, vision, and achievements of his research: *palpable* integration of AI & med