Assistant Professor @Stanford in Biomedical Data Science and (by courtesy) CS. Trustworthy, deployable ML for healthcare.
Palo Alto, CA
- Tweets 495
- Following 1,075
- Followers 2,524
- Likes 2,435
What do models trained on clinical notes leak about patients? Our #EMNLP2026 paper proposes a clinically grounded privacy eval w/realistic attackers & clinically meaningful leakage
Led by rising star @SashaRonaghi, who won the Social Impact Award as a master’s student! Details ⬇️
[1/5] Our paper “Clinically Grounded Privacy Evaluation of Medical LMs” received the Social Impact Award at #EMNLP2026! 🎉
We probe LMs trained on patient notes with realistic adversary knowledge & measure leakage that has real-world consequences and is attributable to training.
1
12
824
Clinicians are increasingly using LLMs to retrieve info from longitudinal EHRs, but we have no way to evaluate models at scale and over time
Introducing 🧀 BRIE: a living Benchmark for Retrieving Information from EHRs 🧀
Led by rising star @itscahoon
👇
1/ As LLMs are integrated into our health systems, how can we efficiently evaluate whether evolving systems can reliably retrieve the information clinicians need?
Excited to share our new preprint: A Living Benchmark for Information Retrieval from Electronic Health Records.
4
12
111
7,235
Highlights:
1⃣A benchmark generator, validated by 15 clinicians, that runs on new notes so the benchmark stays current
2⃣Omission is the dominant error mode
3⃣Models do worse on multi-hop vs single-hop que -> we need granular "licensing" for clinical AI
4⃣dataset coming soon!
1
9
455
Special thanks to @itscahoon for embracing my love of cheese w/ her naming of one of the first papers from the Alsentzer Lab 🧀
5
285
Clinical LLMs learn from EHR data not found in pretraining, but training them is expensive & they go stale as general models improve.
We introduce CAPT, which steers a general model w/ a clinical model at inference (even w/ diff tokenizers!)
Led by the stellar @SashaRonaghi
👇
Check out our paper “Training-Free Adaptation of New-Generation LLMs using Legacy Clinical Models” recently presented at @CHILconference
2
30
4,209
Aishwarya is a rockstar. Excited to see all of the incredible things she’ll accomplish next!
A little delayed, but I graduated from my PhD! 🎓
I'm forever grateful to my advisors @BeEngelhardt and @EmmaBrunskill , my committee members @lschmidt3 , @Emily_Alsentzer and John Duchi, and the many collaborators + friends + family who supported me along the way.
I’m not done working on healthcare! Next stop: research scientist @sprinterhealth , where I’ll be working on algorithms to prioritize and personalize preventive care.
Stay tuned for more!
2
1
25
4,873
Couldn't agree more! This is why we've started a data-centric AI for healthcare class at Stanford. It is so easy to introduce errors in healthcare data that corrupt all downstream models and analyses
There is a crisis of rigor in AI for medicine, reading recent high profile Nature paper: "Towards autonomous medical artificial intelligence agents", I noticed temporal leakage for labs (using the wrong timing column). What is the likelihood this is the only error? (1/5)
2
1
25
5,763
Emily Alsentzer retweeted
Early bird registration for #CHIL2026 is open!
Join us June 28–30, 2026 at Seattle Children’s Research Institute for keynotes, research talks, posters, roundtables, the Doctoral Symposium, and more.
Use code EARLYBIRD26 through May 31.
Register: chil.ahli.cc/register
2
3
702
Emily Alsentzer retweeted
The Health AI Builders Unconference is back! 🙌
Join us on June 28th in Seattle, WA for a full day of exploring entrepreneurship in health AI. Join the waitlist: luma.com/kiy45vie
#CHIL2026 #HealthAI #Entrepreneurship #AIinHealthcare
5
5
984
Emily Alsentzer retweeted
June is going to be a busy month for Seattle 👀
CHIL, FIFA, and… 🥁
AHLI’s inaugural Health AI Summer Camp
📍 University of Washington
📅 June 22–28, 2026
Fully funded for accepted participants.
⏳Apply by April 15 (limited spots): ahli.cc/summercamp
12
16
2,186
Emily Alsentzer retweeted
The CHIL 2026 Doctoral Symposium is back! Apply by March 13th 📅
chil.ahli.cc/submit/doctoral…
Last year, we welcomed 28 outstanding PhD researchers for mentorship and lightning talks in health AI.
Watch 3 participant talks from 2025 👇 (see 2:48:43)
piped.video/watch?v=YaDonAIm…
7
14
1,656
Emily Alsentzer retweeted
Help us shape the conversation at CHIL 2026! We invite suggestions for Research Roundtable topics about controversial or open questions in machine learning for healthcare. Drop your suggestions here: forms.gle/XPNddbmqaMZyv6T67
7
6
1,362
Emily Alsentzer retweeted
Only 2 weeks left to submit to #CHIL2026! ⏳
mailchi.mp/ahli.cc/call-for-…
14
11
2,405
Emily Alsentzer retweeted
Happy Holidays from AHLI! But first, a quick reminder:
📣 CHIL 2026 is coming to Seattle, June 28-30th.
📝 Submission site is now open!
⏰ Deadline: Feb 4, 2026
🤝 Sponsorship opportunities available
🌎 Request an invitation letter for visa applications
chil.ahli.cc
2
3
641
Emily Alsentzer retweeted
Where should we host next year's symposium? Please let us know by filling in our feedback form or commenting below:
#ML4H2025
2
9
969
Looking forward to @SymposiumML4H! The Alsentzer Lab just turned 1, & we’re celebrating with 4 papers on longitudinal EHR QA eval, LLMs for rare disease diagnosis, prior-chat bias in LLMs, & inference-time merging of general+clinical models.
We’re recruiting postdocs-Let’s chat!
1
13
814
Emily Alsentzer retweeted
✨I'm on the research scientist and postdoc job market! I'll be graduating from my PhD this academic year with a thesis that focuses on reinforcement learning and healthcare. ✨
12
45
329
52,376
Emily Alsentzer retweeted
I'll also be presenting some new work at ML4H (arxiv.org/abs/2511.17818) which focuses on building synthetic datasets for off-policy evaluation in healthcare.
1
3
13
3,541
Emily Alsentzer retweeted
CALL FOR ABSTRACTS | SAIL 2026 on May 5–8 in Río Grande, Puerto Rico! In-person attendance limited to those with accepted work. Apply by 1/16/26. Oral presentation invitations & @NEJM_AI-sponsored travel awards go to the top abstract submissions. #SAILhealth26 - sail.health/event/sail-2026/…
ALT Blue promotional graphic for the SAIL Symposium on Artificial Intelligence for Learning Health Systems, featuring a sailboat logo with binary code, the tagline ‘Integrating AI into clinical medicine,’ and a banner reading ‘Call for Abstracts – Deadline Jan. 16, 2026,’ with the sail.health URL at the bottom.
2
8
12
2,885