iiinova — where your digital self keeps evolving

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 06/02/2026

It uses physiological data from multiple sensors to assess hormone levels with calibration with urine samples so I see no reason it wouldn’t work for you. Given that this was a company and not a product launch, privacy protections are being developed still.

030

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 02/01/2026

My 10 year old niece was watching TV, and there was a travel ad. Someone asked her if she would like to visit there. She replied, “This is probably all fake. I can’t trust the world.” This is the world generative AI is creating.

2222

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 19/12/2025

Be careful with using AI to craft your personal statements. AI-based statements begin to sound REALLY similar (the tone, wording, etc is really similar). This will cause your readers to zone out. The fresh voice of an AI-less personal statement, on the other hand, will snap them out of it.

0122

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 17/12/2025

Woah…. Curious if there is a way to get rid of the gradient in one organelle and just… see what happens?

110

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 14/12/2025

Seven year old said to her dad, “I don’t want your idea to be part of my project. I want to be independent.” 😂

2130

Reposted by Roxana Daneshjou, MD, PhD

Pauline Funchain @funchainmd.bsky.social · 04/11/2025

AI in Clinical Science - amazing data being presented today by @jason-fries.bsky.social Sylvia Plevritis @roxanadaneshjou.bsky.social @akshay-chaudhari.bsky.social but still feel like we are just barely cracking the egg in this field. So impatient for the omelette…! @stanford-cancer.bsky.social

042

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 24/09/2025

Hahahaha nope, mom must pay tribute to all the children.

000

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 24/09/2025

Game over. The 21 month old knows what tahdig is and demands it by name when he sees me having a piece. Between him and the six year old, my tahdig eating days are over.

460

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 22/09/2025

“I believe attachment is the root of all suffering.” Sir, we are at a SuperCuts.

0251

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 14/09/2025

One of my six year old’s classmates was encouraging her saying, “There’s no such thing as fear. It’s all in your mind.” Kids these days are 6 going on 60.

0120

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 05/09/2025

“Can we pause it?” No girl, we cannot.

010

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 05/09/2025

Finding out that my six year old doesn’t understand TV. She is asking if I can start the movie on Disney channel from the beginning. She asked where the skip button was during the commercials. 😂

3202

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 09/08/2025

As we talk more about the use of LLMs by both the general public and professionals for high risk tasks like healthcare... there's one thing I don't see mentioned as often, which is sycophancy. Sycophancy occurs when LLMs sacrifice truthfulness for user agreement. arxiv.org/pdf/2502.08177

arxiv.org

3316

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 02/08/2025

Today I went on a Stanford sponsored grant writing retreat for junior faculty. Given the constant assault on academia, the mood was muted but at least we got beautiful views.

1220

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 18/07/2025

Not my 19 month old son saying “all done” as I was kissing his chubby cheeks over and over again.

1100

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 14/07/2025

And it was in this case! Consulting team thought pressure ulcer but it was herpes.

010

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 13/07/2025

On call this weekend and time for the wise @misharosenbach.bsky.social pearl. “Any erosion in the hospital is HSV or VZV until proven otherwise.” So as I tell the residents: always swab!

192

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 27/06/2025

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.

1122

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 27/06/2025

Remembering @atulbutte.bsky.social 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.

041

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 26/06/2025

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. @ahli-cc.bsky.social

Dr Hightower giving a talk on responsible AI

060

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 25/06/2025

I was very excited to be part of the team that put this together!

080

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 25/06/2025

My daughter loves old school magic school bus, and I can’t help but wonder what Arnold becomes when he grows up…

270

Reposted by Roxana Daneshjou, MD, PhD

Trish Greenhalgh @trishgreenhalgh.bsky.social · 19/06/2025

Thanks for the reminder @janemunday.bsky.social. Every summer, I repost this article DROWNING DOES NOT LOOK LIKE DROWNING. To date, I know of FOUR kids who were saved after someone who'd clicked on the link learnt how to spot actual drowning. Take time to read and pass on. slate.com/technology/2...

slate.com

Drowning Doesn’t Look Like Drowning

Drowning is not the violent, splashing call for help that most people expect.

10955954783

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 20/06/2025

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

chil.ahli.cc

CHIL

041

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 12/06/2025

I have. The timing of when it arrives is really variable, as is the quality. Some of the stuff was good and some of it was terrible. I used it to get Pokemon themed stuff I couldn’t find elsewhere.

110

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 06/06/2025

I build and test AI for healthcare, and it must absolutely be regulated.

210724

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 03/06/2025

Even if we got it all back tomorrow, there’s already been severe damage done. So yeah, it’s gonna be bleak in 4 years.

0161

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 03/06/2025

When you are twinning with your postdoc by mirroring jacket/nails. #womeninstem

090

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 01/06/2025

Both my kids, I was in labor for 24 hours (and thus awake). And then at the end, I had to push a baby out while in complete exhaustion.

130

Reposted by Roxana Daneshjou, MD, PhD

the JID Journal @thejidjournal.bsky.social · 28/05/2025

See this opportunity with our sister journal @thejidinnovations.bsky.social; seeking candidates for the position of Editor. Interested? JID innovations would love to hear from you ow.ly/a8Ym50VZ64c

ow.ly

JID Innovations Editor Search - SID

EDITOR SEARCH The Society for Investigative Dermatology, in collaboration with the European Society for Dermatological Research, seeks candidates for the...

011

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 27/05/2025

I went on the last kindergarten “field trip”. They walked down to the market to buy groceries for making a salad for the rest of the school. Why am I feeling so emotional? Why do they grow up so quickly?

0101

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 21/05/2025

This is what happens when publishing papers becomes the metric instead of doing good science. People use AI to write papers, too many papers to review, now using AI to review paper. What’s the point?

050

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 20/05/2025

Haha ask me later, it’s a hot mess right now. My daughter was 1.5 when Covid hit and I was doing my postdoc with her at home (daycare closed). I had my son who is now 17 months during my first year as faculty.

100

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 20/05/2025

Eventually, we know the microbiome is important but all the details are still being worked out.

010

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 19/05/2025

I had my first baby in residency so during my postdoc/faculty, I was already juggling it. I do 10 percent clinic and the rest is teaching/research. My children are my world so I prioritize pickup/drop off and activities. I work on research after they sleep to make up for any time missed.

210

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 19/05/2025

Great question! My lab focuses mostly on deep learning and training our own models, particularly on image based data. We also have been working with large language models and prompt engineering.

010

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 19/05/2025

🧪 Hey science feed, I’m an assistant professor of biomedical data science and dermatology (physician scientist). I’m going to do a Ask Me Anything thread here. Happy to talk about my job, what things are like now, having two young kids in academia.

4193

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 18/05/2025

I was a Covid postdoc. Our daycare was closed for several months; everything was a struggle. I thought that was going to be the hardest part.

010

Roxana Daneshjou, MD, PhD @roxanadaneshjou.bsky.social · 18/05/2025

The impact of these federal cuts to science won’t be seen tomorrow. But in 5-10 years, when we have a drop off in new treatments for cancer, heart disease, and everything else… it will because we significantly cut the number of scientists trained and killed the careers of existing scientists.

622368