Today Clinical Implementation of AI-Based Screening for Risk for Opioid Use Disorder in Hospitalized Adults by @Majeans2011 @UW_ICU_DataSci was highlighted as a most impactful paper of 2025 at #AMIA2025 ! https://t.co/p2GkIXTugv

Beyond the perhaps superficial semantic distinction between "reasoning" and "pattern matching", there is a fundamental gap in the practical capabilities and behavior of these systems. You don't create an invention machine by iterating on an automation machine.

What a fun and important collaboration with @HeyEpic to build such an important open-source tool for evaluating ChatGPT outputs in healthcare. Evaluation is a must to understand how we can integrate AI safely and effectively into our practice - check it out! @UW_ICU_DataSci

Big shoutout to Dr. Majid Afshar @Majeans2011 of @uw_medicine, Dr. Brian Patterson of @UWEmerMed, and PhD student Emma Croxford of UW BMI for representing @UWMadison at @HeyEpic’s XGM in front of hundreds at the Physician Advisory Council! 👏🎆 @UWInformatics (1/4)

Epic staff are also contributing to the science behind this work—like in this recent @Nature_NPJ paper on evaluating AI-generated clinical summaries. Lots more to do on this front. https://t.co/L5XY3djGHD

See our @JMIR_AI article by Dr. Rahman & team! Chest X-rays hold hidden clues to patient deterioration. In a 22K-patient study, Densenet121 beat other models in predicting ICU transfer and patient mortality. Medical Imaging + AI = powerful early warning: https://t.co/jW0L5AbLY7

See our @JAMA_current article by the @UW_ICU_DataSci, @PCCRG, @anzics! 2x RCTs + ML modeling = Individualized oxygenation targets -> improve survival of critically ill patients undergoing invasive mechanical ventilation.

Doctors and researchers at the UW-Madison School of Medicine and Public Health have developed an artificial intelligence tool to ensure some of our most vulnerable patients, those battling opioid use disorder, don't fall through the cracks.

🎉 How can we use AI for good in addiction care? Our new study in @NatureMedicine shows an AI tool successfully screens for opioid use disorder—reducing hospital readmissions and costs! 🔗 https://t.co/3M5ttTHjtj 🔗 https://t.co/U9nqumlop1 📺 https://t.co/XMdOCMfAkn @NIDAnews

Thanks for the mention, @HeyEpic! Our Clinical Informatics team is thrilled to be a part of this collaboration. @Majeans2011 @UW_ICU_DataSci @DrJoelGordon @p_kleinschmidt @uw_medicine

This is a great opportunity to work with a brilliant PI…don’t miss your chance

Paper: https://t.co/VV9RCL1l5k Interactive site to complete the checklist:

TRIPOD-LLM is out! Check out our consensus guidelines for reporting #LLM research in biomedicine. TRIPOD-LLM is intended to be a living guideline to keep up with the rapid advances in #LLMs/Gen AI. Kudos to lead author @JackGallifant

@SkatjeZero led our team in exploring how different embedding models and pooling methods affect EHR information retrieval for the clinical domain, to inform strategies for RAG frameworks in healthcare applications! @Serena_pancakes @Majeans2011 @dmitriydligach @NLM_NIH

Our preprint is live! Learn how we prepared for a clinical trial of GenAI in healthcare: A Novel Playbook for Pragmatic Trial Operations to Monitor and Evaluate Ambient Artificial Intelligence in Clinical Practice https://t.co/iP8yjibbkB @UWInformatics @UWHealth @abridged_io

☀️had a great #EMNLP2024 ! thanks for stopping by our poster! I really enjoyed answering the questions and discussion on LLM embeddings for EHR and clinical tasks ⚕️🏥 🧩happy to see that the hype of #LLMs cools down a bit and foundational #NLP problems are back!

🤖Are LLMs good at tabular medical data? 🥼Can they be useful for medical machine learning tasks and beat classical ML setup? #EMNLP2024 Stop by our poster Nov 14 (Thu), session 12, 14:00-15:30 Paper available🎉: https://t.co/aPk2iR3ber @lark_nlp_lab @UW_ICU_DataSci

A day of presenting many of our NLP work at AMIA! P1: our JBI paper on role of UMLS supporting DDx by LLM P3: Multi-modal ML for clinical prediction P4: Human&Auto Eval for LLM Diagnosis prediction #AMIA2024 @UW_ICU_DataSci @Majeans2011

🩺💡The Bitterman lab has spend much of the past year researching #LLMs for healthcare. This post summarizes our inroads into making LLMs safer and reliable for clinicians and patients: https://t.co/tr2AIFNFti. We'll be at #EMNLP2024 - come chat if you have similar interests!

Here are some reflections on many studies we did this year. Tons of progress has been made, but there are still safety concerns..🧐 We are going to be at #EMNLP2024 🏖️ Happy to chat and connect! 📃 https://t.co/cdPTSgQiF9 🔊 https://t.co/66UI7aOPuF @dbittermanmd @JackGallifant