🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I have the same username at the other place that ends in sky.

Major med twitter exodus happening to the place where skies are blue. My handle is the same there.

Same handle as here

It feels like the good days of Twitter again!

It's not an echo chamber. People are just nice and without the algorithm, I'm actually seeing science again.

Fascinating session on generative AI & LLMs with Roxana Daneshjou MD/PhD & Dr. Camila Gonzalez (Camila González). They explored the opportunities, risks, & ethical complexities of these transformative tools. #AIPlusHealth24

I’m not at NeurIPs this year but I have seen the deeply offensive and racist slide shown by a keynote (not reposting here). It’s completely unacceptable, and I stand with my Chinese colleagues.

No, it’s a language model. Its performance on the task has nothing to do with cognitive impairment.

This young MD literally cannot get her cancer treatment thanks to Humana. This is unacceptable.

What is this? Starlink? Over Bay Area.

By simulating realistic patient-doctor conversations, a framework can be applied to LLMs to investigate shortcomings and bias in patient interactions, providing insight prior to actual clinical deployment Pranav Rajpurkar Roxana Daneshjou MD/PhD SJ nature.com/articles/s4159…

Wonderful new study from colleagues SJ Pranav Rajpurkar Roxana Daneshjou MD/PhD et al with a new method for benchmarking the conversational data collection skills of language models (as well as a very cool leaderboard)

Roxana Daneshjou MD/PhD et al. Great new paper w/ "realistic doctor–patient conversations, comprehensive history-taking, open-ended questioning and using a combination of automated and expert evaluations" nature.com/articles/s4159…

What do we want to know about LLMs in research? Out today in Nature Medicine, we take a stab at developing a comprehensive, living taxonomy of LLM use-cases and reporting.

ARPA-H, which funds projects meant to directly improve American health, just had to cancel their proposer’s day because of the Trump administration health agency communication freeze.

In medical settings, researchers & institutional users often cite medical examination benchmark results as a proxy for AI model performance across a range of medical tasks. This is a woefully misguided practice - as with actual doctors, test performance != clinical competence!

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 Deb Raji, BAS, Roxana Daneshjou MD/PhD, MD, PhD, and Emily Alsentzer, PhD: nejm.ai/3PK8v1D

The previous episodes of this podcast series featured doctors, tech developers, a patient, and a VC about the reality of AI in healthcare. But what are, and should be, the guidelines for using AI? Provocative conversations with Laura Adams, Vardit Ravitsky, and Roxana Daneshjou MD/PhD.