Juan M. Banda, Ph.D

And the proceedings of the #SMM4H workshop are out! If you can't make it this week to #ACL2024 to see our colleague Vishakha Sharma, here are the goodies: aclanthology.org/2024.smm4h-1.4… @aclmeeting @gracielagon @sarkerabeed @davy_weiss @drjmbanda @ivanfloresa @guilopgar @pzfr

@BioNLProc Better yet, offer the additional low-cost remote option... always!

Unpopular opinion, maybe: Please don't organize conferences in exotic remote islands that most people can't get to easily (time, money, u know the usual suspects). If it's small/medium, a Hilton by the airport in a midwest city is what I want 🙂🙏

🚀 Exciting News! 🚀 We're thrilled to announce that our longitudinal electronic health record (EHR) dataset, EHRSHOT, is now available for download! 🌟 📊 6,738 patients 📅 41.7M events 🩺 921,499 visits Details at: ehrshot.stanford.edu

🚀 Checkout our ICLR 2024 Spotlight Poster #165 today (Session 3) 🩺 "MOTOR: A Time-to-Event Foundation Model For Structured Medical Records" ✨ Highlights: - The first TTE foundation model for structured EHRs - Improves SOTA TTE by 4.6% & boosts label efficiency up to 95% - TTE pretraining scales to 16k tasks & reduces GPU memory usage by ~35% - Model weights available for research use! 🔍 Tutorial: github.com/som-shahlab/mo… 🤖 Model: huggingface.co/StanfordShahLa… #ICLR2024 #AI #Healthcare

Thanks to the @nlm R01 funding - The competitions remain active on CodaLab for fair comparison of future systems. Overview of the 8th Social Media Mining for Health Applications (#SMM4H) shared tasks at the AMIA 2023 Annual Symposium academic.oup.com/jamia/article/…

SMM4H-2024: The 9th Social Media Mining for Health Research and Applications Workshop and Shared Tasks — Large Language Models (LLMs) and Generalizability for Social Media NLP healthlanguageprocessing.org/smm4h-2024/

For all NLP enthusiasts interested in social media data: Sign up for the #SMM4H 2024 Workshop and Shared Tasks! This year at @aclmeeting 2024 healthlanguageprocessing.org/smm4h-2024/ @ivanfloresa @gracielagon @sarkerabeed @YutingGuo12 @drjmbanda @davy_weiss @pzfr Lucia Schmidt and more

Second keynote from #BLAH8 has @MKrallinger showing all the awesome work being done @BSC_CNS regarding clinical NLP and for low-resources languages as well.

Excited to be back in Japan for #BLAH8 where the focus this time is LLM usage in the context of biomedical annotation. Kicking things off we have @ProfLHunter making some great points about their evaluation

@bayesianboy Put up everything you own in storage and go travel for a few months/weeks. Best way to wind down from PhD program and will bring clarity to next steps.

@ANordsletta @ehealthNORWAY @AMIAinformatics Not quite true on the parameters. GPT3 has 175 billion parameters. However, chatGPT was based on GPT-3.5 and more recently GPT-4 which the parameter numbers is not clear: pcmag.com/news/the-new-c…

At #AMIA2023 we learned from Jesse Spencer-Smith, Vanderbilt University that the ChatGPT has 175 billion parameters. The ChatGPT we had last week could only do 32 K tokens, 24 k words. Last Tuesday a new model was presented. It is increased to 128 K tokens and 96k Words.

Busy day at #AMIA2023 on the #SMM4H2023 workshop! Looking forward to hear about the winning teams on this year's five shared tasks. @gracielagon @sarkerabeed and many others!

It was such a fun event! Thanks for the invite, and looking forward to the following ones!

Excellent panel on LLMs at the NLP Workgroup meeting. #OHDSI2023

Loving the LLM interest at the OHDSI 2023 symposium! Super cool study on use for chart reviewing patients! #ohdsi2023

It’s next Friday! Last year was super fun and I can’t wait to see what’s in store this year. Registrations are still open and please don’t forget to register for the NLP workgroup meeting on Oct 21st. #JoinTheJourney #OHDSI2023 @HuaXu_SBMI @drjmbanda

The #SMM4H Program is out! On Nov 11, we have shared task winners, two fantastic keynote speakers: the Academic Keynote by @LuisMateusRocha from Binghamton U and the Industry keynote by @RaulREsteban from Roche, and more! healthlanguageprocessing.org/smm4h-2023/

Do you want to deliver reliable evidence from observational healthcare data or develop tomorrow's hottest phylodynamics model? Find computational statistics and data science fascinating? Let me hire you as a Postdoctoral Fellow. Please email me directly ASAP! (flexible start)

There is still time to join the shared tasks at the premier venue for Social Media Mining for Health research #SMM4H, endorsed in 2023 by the AMIA KDD working group at the AMIA Symposium in New Orleans this November. 5 tasks - annotated datasets now out. healthlanguageprocessing.org/smm4h-2023/

There is still time to register and participate in this year's #SMM4H shared tasks led as always by @gracielagon and co-organized by @drjmbanda @RaulREsteban + others. Some really interesting tasks this time! healthlanguageprocessing.org/smm4h-2023/