@madhumitasushil Profile picture

Madhumita Sushil

@madhumitasushil

Assistant Professor @UCSF_DOCIT, @NeurosurgUCSF, @UCSF_BCHSI. Prev clinical NLP, neural network interpretability @clipsua, research intern @Google Research

Joined November 2010
Similar User
Amelia J. Averitt, MPH MA PhD photo

@AJAveritt

UCSF Bakar Computational Health Sciences Institute photo

@UCSF_BCHSI

Monica Agrawal photo

@MonicaNAgrawal

byron wallace photo

@byron_c_wallace

AMIA NLP WG photo

@amiaNLPwg

Shenghuan(Harry)_Sun 孙圣桓 photo

@Harry_S_Sun

Sirota Lab at UCSF photo

@SirotaLab

Stephan Tulkens photo

@tulkenss

AMIA KDDM WG photo

@amiaKDDMwg

Liling Tan photo

@alvations

Rui Zhang, PhD, FAMIA photo

@RuiZhang1229

Tejas Srinivasan photo

@_Tejas_S_

Alice Summer Tang photo

@AliceTang_mstp

Jingcheng Du photo

@JingchengDu

You Chen, PhD, FAMIA photo

@ohpenlab

Really excited to see our paper on curating a detailed oncology information extraction benchmark featured in #AMIA2024 year-in-review! Read the paper here: ai.nejm.org/doi/full/10.10… @atulbutte @UCSF_BCHSI @UCSF_DOCIT

madhumitasushil's tweet image. Really excited to see our paper on curating a detailed oncology information extraction benchmark featured in #AMIA2024 year-in-review! Read the paper here: <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/7tljeH6MQc">ai.nejm.org/doi/full/10.10…</a> @atulbutte @UCSF_BCHSI @UCSF_DOCIT

Madhumita Sushil Reposted

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

NobelPrize's tweet image. BREAKING NEWS
The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

Grateful for the opportunity provided by the NAIRR Pilot program! I hope it becomes a permanent program to democratize access to computing resources. Extending thanks to @bmeow19 for helping all through the ideation and writing, and Oksana for helping shape it even further!

WOW! @MadhumitaSushil wins another National Artificial Intelligence Research Resource (NAIRR) pilot award, now bringing @UCSF total to 5 and the @UofCalifornia total to 16! BRAVO! nairrpilot.org/projects/award…



Such a well-deserved award! We are extremely grateful to be beneficiaries of your vision, care, and mentorship. Your commitment towards your vision and your team members inspires me every single day, @atulbutte

We are thrilled to announce that Atul Butte, MD, PhD (@atulbutte) has received the 2024 Morris F. Collen Award of Excellence. lnkd.in/gy5YACpb

AMIAinformatics's tweet image. We are thrilled to announce that Atul Butte, MD, PhD (@atulbutte) has received the 2024 Morris F. Collen Award of Excellence. <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/opgkGzjhTW">lnkd.in/gy5YACpb</a>


Madhumita Sushil Reposted

Summer reading! Can LLMs reduce need for large scale data labeling ? @madhumitasushil @Atulbutte Travis Zack and co compare LLMs on zero-shot inference and supervised classification of breast cancer pathology reports. In Journal @AMIAinformatics buff.ly/4fmkOgd @BCHSI


Madhumita Sushil Reposted

People ask me all the time for AI use cases in healthcare So last month, we hosted the first OOP hackathon using generative AI tools Here are all the projects that were made in 36 hours. They made me more optimistic about the future

nikillinit's tweet image. People ask me all the time for AI use cases in healthcare

So last month, we hosted the first OOP hackathon using generative AI tools

Here are all the projects that were made in 36 hours. They made me more optimistic about the future

It was an absolute pleasure to discuss my journey into medical NLP and path to UCSF! Thanks @tomiko22 and @msirota84 for the opportunity! @UCSF_BCHSI

Day #8! Huge thank you to @madhumitasushil for sharing your inspiring journey with our high school students as well as insights into your fascinating work involving language models and electronic medical records to advance healthcare! #AI #LLM #NLP

ai4allatUCSF's tweet image. Day #8! Huge thank you to @madhumitasushil for sharing your inspiring journey with our high school students as well as insights into your fascinating work involving language models and electronic medical records to advance healthcare! #AI #LLM  #NLP


Madhumita Sushil Reposted

Day #8! Huge thank you to @madhumitasushil for sharing your inspiring journey with our high school students as well as insights into your fascinating work involving language models and electronic medical records to advance healthcare! #AI #LLM #NLP

ai4allatUCSF's tweet image. Day #8! Huge thank you to @madhumitasushil for sharing your inspiring journey with our high school students as well as insights into your fascinating work involving language models and electronic medical records to advance healthcare! #AI #LLM  #NLP

Madhumita Sushil Reposted

Social drivers of health are crucial in assessing & addressing patient needs. Now out in JAMIAOpen @Harry_S_Sun +team: topic-modeling clustering of 1 million deidentified notes from our social worker colleagues, to better understand all our patient needs! buff.ly/3Li2gjj

atulbutte's tweet image. Social drivers of health are crucial in assessing &amp; addressing patient needs. Now out in JAMIAOpen @Harry_S_Sun +team: topic-modeling clustering of 1 million deidentified notes from our social worker colleagues, to better understand all our patient needs! <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/ZoVCw4fXot">buff.ly/3Li2gjj</a>
atulbutte's tweet image. Social drivers of health are crucial in assessing &amp; addressing patient needs. Now out in JAMIAOpen @Harry_S_Sun +team: topic-modeling clustering of 1 million deidentified notes from our social worker colleagues, to better understand all our patient needs! <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/ZoVCw4fXot">buff.ly/3Li2gjj</a>

Can't emphasize how under-appreciated these struggles are for immigrants in academia. The playing field is so different. Academia is tough for everyone, but not being eligible to even apply for so many grants without a green card makes it infinitely harder.

Immigrant scientists in academia endure a unique kind of struggle. We are often not eligible for most fellowships and grants. We must be exceptionally productive—our publications and articles contribute towards our green card applications!



Madhumita Sushil Reposted

And it's out! Congratulations @madhumitasushil and team on our new publication in Journal @AMIAinformatics on comparing multiple LLMs on zero-shot inference and task-specific supervised classification of @UCSF breast cancer pathology reports, including UCSF-BERT! "On tasks where…


Madhumita Sushil Reposted

Review Article by Jiageng Wu, MS, et al.: Clinical Text Datasets for Medical Artificial Intelligence and Large Language Models — A Systematic Review nejm.ai/3wNGMXM #AIinMedicine

NEJM_AI's tweet image. Review Article by Jiageng Wu, MS, et al.: Clinical Text Datasets for Medical Artificial Intelligence and Large Language Models — A Systematic Review <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/9WhNwtPDsp">nejm.ai/3wNGMXM</a> 

#AIinMedicine

Madhumita Sushil Reposted

35 teams were awarded @NSF @WhiteHouse Natl AI Research Resource NAIRR pilot projects, for access to @DOEScience & NSF advanced computing systems! AMAZING to see three awarded to @UofCalifornia, and TWO at @UCSF including @MadhumitaSushil! CONGRATS! buff.ly/4be3sPQ


Check out this study led by @cykwilliams assessing the utility of GPT models for triaging patients in the emergency department. TLDR: these models are pretty good at the job!

Thrilled to announce our latest paper "Use of a Large Language Model to Assess Clinical Acuity of Adults in the Emergency Department" published today in @JAMANetworkOpen @TravisZack2 @bmeow19 @madhumitasushil Michelle Wang @AaronKornblith @atulbutte



Madhumita Sushil Reposted

UCSF receives 2 of the 35 inaugural @NSF -led National AI Research Resource Pilot awards partnership with DOE @ENERGY! meritalk.com/articles/nsf-d… Full list nairrpilot.org/awarded-projec… @madhumitasushil & Vadim Shteyler Announced at the @WhiteHouse


Madhumita Sushil Reposted

How should we evaluate #LLMs for downstream clinical use cases? In this @npjDigitalMed article, we propose a transition from static QA-style benchmarks to dynamic agent-based simulators, similar to methods used in biology, epidemiology & social sciences. nature.com/articles/s4174…

_ahmedmalaa's tweet image. How should we evaluate #LLMs for downstream clinical use cases? In this @npjDigitalMed article, we propose a transition from static QA-style benchmarks to dynamic agent-based simulators, similar to methods used in biology, epidemiology &amp; social sciences.

<a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/giyVwMZDpl">nature.com/articles/s4174…</a>

Madhumita Sushil Reposted

AI can help to bring high-quality, equitable care across the globe 🌏

GoogleHealth's tweet image. AI can help to bring high-quality, equitable care across the globe 🌏
GoogleHealth's tweet image. AI can help to bring high-quality, equitable care across the globe 🌏
GoogleHealth's tweet image. AI can help to bring high-quality, equitable care across the globe 🌏
GoogleHealth's tweet image. AI can help to bring high-quality, equitable care across the globe 🌏

Madhumita Sushil Reposted

Happy sharing of CARMEN-I @ PhysioNet (also hosts MIMIC-IV) URL:  physionet.org/content/carmen… CARMEN-I comprises 2,000 clinical records (discharge letters, referrals, radiology reports from H. Clínic). Diverse comorbidities, anonymization, symptoms, diseases, procedures, medications.

MKrallinger's tweet image. Happy sharing of CARMEN-I @ PhysioNet (also hosts MIMIC-IV) URL:  <a style="text-decoration: none;" rel="nofollow" target="_blank" href="https://t.co/TInym4peC5">physionet.org/content/carmen…</a>
CARMEN-I comprises 2,000 clinical records (discharge letters, referrals, radiology reports from H. Clínic). Diverse comorbidities, anonymization, symptoms, diseases, procedures, medications.

Loading...

Something went wrong.


Something went wrong.