Roxana Daneshjou MD/PhD
@RoxanaDaneshjou
Assistant professor of Biomedical Data Science @StanfordDBDS and Dermatology @StanfordMed | AI/ML & precision health | @Rice_BioE alum | @pdsoros Fellow 2014
Excited to see our @NatureMedicine paper out today led by @ChanwooKim_ with my co-senior author @suinleelab and an amazing team! We used a dermatology foundation model to enable explainable and transparent AI - from auditing datasets to models. nature.com/articles/s4159…
We submitted to the datasets and benchmarks track and actually got this review which makes me suspect AI: “However, this paper mainly focuses on dataset aspects, and therefore does not fit well with the conference theme: neural information processing systems"
Really great to see MIT tech review talking about our new preprint, where we find that newer LLMs have fewer medical disclaimers. Led by Sonali Sharma! Also with @_ahmedmalaa
AI companies have stopped warning you that their chatbots aren’t doctors trib.al/OL4aqhu
Really excited to be part of this conversation hosted by @pearvc on Deploying Safe and Scalable AI in Healthcare for Providers and Payers. gatsby.events/pear-vc/rsvp/r…

On call this weekend and time for the wise @MishaRosenbach pearl. “Any erosion in the hospital is HSV or VZV until proven otherwise.” So as I tell the residents: always swab!
Heard from #CHIL2025 panel: VC doesn’t want to fund high risk work (one VC even said “write a R01 grant). That’s what NIH grants are supposed to be. Without that, we won’t be able to do the high risk work that leads to innovation and companies.
Remembering @atulbutte at #CHIL2025. The world lost an amazing light and mentor. He helped shape my career and the careers of many others in the medical informatics and medical AI space.

Thank you to Guillermo Sapiro for showing with Apple Watch data that pregnancy ages you 😂

We are kicking off #CHIL2025 with Dr. Maia Hightower. As a program organizer, we are showing our values by centering health equity and responsible AI.

I was very excited to be part of the team that put this together!
Datasets, Benchmarks, and Protocols by A.S. Chiou et al.: Multimodal Image Dataset for AI-Based Skin Cancer (MIDAS) Benchmarking nejm.ai/3SO0PwA #AIinMedicine #DermTwitter
If you were impacted by Atul Butte personally or professionally, we hope you will take a moment to share a memory and photo at kudoboard.com/boards/OMydGod…. These will be shown at the celebration of life this Saturday ⤵️
It’s not too late to register for the major AI and healthcare academic conference: Conference for Health, Inference, and Learning! We have an amazing line up of speakers from industry and academia! chil.ahli.cc
Only a cowardly regime targets the sick and wounded. The Islamic Republic’s attack on the largest hospital in southern Israel is not just a crime it’s pure brutality. My heart is with every innocent civilian caught in the crossfire of this cruelty. This is inhuman,…
There's a lot to be said on this newest preprint showing that reliance on LLMs in writing tasks leads to a 'consistent underperformance' in neural and behavioral levels with potential long-term consequences. Interestingly, I think this ties to similar but (early)…
Interesting snapshot of growth in clinical AI publications in China @NEJM_AI (TLDR rapid growth but lagging in the highest visibility journals) and in which institutions.
How do LLMs do when red teamed by an interdisciplinary group of engineers, informations, and healthcare workers? We also built a dataset that can be used to test future LLM iterations. @npjDigitalMed nature.com/articles/s4174…
Celebration of the life of Atul Butte. Join colleagues from three universities to celebrate him at 10 am PST on Saturday.