Not too big. Not too small.
#ML4H2025 is just right for deep conversations and building meaningful connections.
Come get your healthy dose of ML research and vitamin D in sunny San Diego!
Register today: ahli.cc/ml4h-register/
It might be your favorite conference of the year!
New pre-print from @emilyalsentzer.bsky.social et. al., CHIL 2025 convened experts to discuss critical themes in healthcare AI, including user-centric explainability, bias mitigation, domain adaptation, foundation models, and learning from small medical datasets.
#MedSky #MLSky #MedAI
Page 1 of the Perspective "Redefining Bias Audits for Generative AI in Health Care" Read full article at ai.nejm.org.
Perspective by Irene Y. Chen, PhD, and Emily Alsentzer, PhD: Redefining Bias Audits for Generative AI in Health Care nejm.ai/4mhOFte
@irenetrampoline.bsky.social @emilyalsentzer.bsky.social #AI #MedSky #MLSky
🚨 Calling all health AI founders & builders!
Join us at Health AI Builders: A CHIL Unconference — June 25th @ UC Berkeley.
💡 Real talk on AI, regulation, GTM, & fundraising
👥 Small-group convos, big impact
🎯 Apply to attend: lu.ma/2arsxv64
#CHIL2025 #HealthAI #ML4H
It’s finally out! We brought a multidisciplinary team of physicians, computer scientists, and engineers to red team LLMs for healthcare uses. And we have shared the dataset! www.nature.com/articles/s41...
Required reading If you ever use models to brainstorm.
Really nice study design: Domain expert researchers search for plagiarized papers of LLM- systems that generate research plans. Many successfully find papers, verified by authors of those papers.
But very hard to detect, see screenshot.
Clinical #AI has come a long way, but are we losing some of the core principles of NLP? Dr. @emilyalsentzer.bsky.social discusses how early rule-based approaches still offer valuable lessons for today’s AI-powered clinical decision support. Full episode: nejm.ai/4gOGeSo
#MedSky #MLSky
AI Grand Rounds Episode 27 From Clinical Notes to GPT-4: Dr. Emily Alsentzer on Natural Language Processing in Medicine
Dr. @emilyalsentzer.bsky.social, a Stanford faculty member and expert in clinical #AI, discusses the evolution of natural language processing, the challenges of AI in clinical settings, and what the future holds for open-source medical AI. Full episode: nejm.ai/4gOGeSo
#MedSky #MLSky
Editorial To evaluate LLMs for clinical applications, we must move beyond fixed, narrowly scoped datasets and develop a suite of benchmarks that reflect the complexity and diversity of real-world clinical tasks. “It’s Time to Bench the Medical Exam Benchmark” by Inioluwa Deborah Raji, B.A.S., Roxana Daneshjou, M.D., Ph.D., and Emily Alsentzer, Ph.D.
To move forward as a field, clinicians need to design benchmarks that better align with the tasks LLMs are expected to perform upon deployment. Read the editorial by Inioluwa Deborah Raji, BAS, @roxanadaneshjou.bsky.social, and @emilyalsentzer.bsky.social: nejm.ai/3PK8v1D
#MedSky #AI #MLSky
Well said, and very nice!
It’s Time to Bench the Medical Exam Benchmark @roxanadaneshjou.bsky.social @emilyalsentzer.bsky.social
ai.nejm.org/doi/full/10....
Medical licensing exams are convenient, but don’t reflect real-world clinical tasks. With LLMs already in EHRs, we need evals to match real-world needs. Let’s partner w/ hospitals piloting these tools to create diverse task-specific evaluations.
w/@rajiinio.bsky.social @roxanadaneshjou.bsky.social
Amazing - 30th anniversary of @pacsym.bio. Celebrating the amazing co-chairs and staff that have made this conference possible! #psb25
Submit an abstract to join us in Puerto Rico!
✨focus on real-world deployment of AI into the clinic with practical, in-depth discussions
✨intimate setting for detailed conversations & networking to start new collaborations
✨beachfront hotel 🌴
phd students in ML for health: my team based in cambridge UK is hiring interns for 2025!
jobs.careers.microsoft.com/global/en/sh...
Couldn't find a machine learning for health starter pack so I made one.
DM/Reply if you want to be added!
go.bsky.app/PJKJ8vK
