iiinova — where your digital self keeps evolving

Irene Chen @irenetrampoline.bsky.social · 12/05/2025

What happens in SAIL 2025 stays in SAIL 2025 -- except for these anonymized hot takes! 🔥 Jotted down 17 de-identified quotes on AI and medicine from medical executives, journal editors, and academics in off-the-record discussions in Puerto Rico irenechen.net/sail2025/

0275

Reposted by Irene Chen

Colleen Chien @colleenchien.bsky.social · 04/04/2025

We've launched a biweekly AI & Society salon at Berkeley w/ @rajiinio.bsky.social & @irenetrampoline.bsky.social! This week, sociologist marionf.bsky.social joined EECS’ beenwrekt.bsky.social to discuss The Ordinal Society. Up next, on April 16th: AI & Education. Join us at ai-and-society.github.io

2152

Irene Chen @irenetrampoline.bsky.social · 27/02/2025

AI deployments in health are often understudied because they require time and careful analysis.⌛️🤔 We share thoughts in @ai.nejm.org about a recent AI tool for emergency dept triage that: 1) improves wait times and fairness (!), and 2) helps nurses unevenly based on triage ability

2307

Irene Chen @irenetrampoline.bsky.social · 20/12/2024

Great q! We found that standard ML training (incl rebalancing data, etc) still reflected the differences in EHR data quality. Later we started experimenting with different options such as adding self-report data to the model, but using regular ML training did not seem to help!

110

Irene Chen @irenetrampoline.bsky.social · 20/12/2024

tl;dr Healthcare access disparities cascade through the entire ML pipeline. Check out our working paper here: arxiv.org/pdf/2412.07712

1187

Irene Chen @irenetrampoline.bsky.social · 20/12/2024

Finding 3: Here's what helped: Adding patient self-reported data boosted model sensitivity by 11.2% for underserved patients. (Note adding the low/high access info did NOT help)

120

Irene Chen @irenetrampoline.bsky.social · 20/12/2024

Finding 2: "Just train a better model" isn't enough. EHR reliability has large effects on balanced accuracy (5.8% drop) and sensitivity (9.4% drop).

210

Irene Chen @irenetrampoline.bsky.social · 20/12/2024

Finding 1: For 78% of medical conditions we examined, data quality was worse for patients facing cost/time barriers to health. EHR reliability is defined compared against patient self-report

110

Irene Chen @irenetrampoline.bsky.social · 20/12/2024

How do disparities in healthcare access affect ML models? 💰📉🧐 We found that low access to care -> worse EHR data quality -> worse ML performance in a dataset of 134k patients. Work with Anna Zink (on the faculty job market rn!) + Hongzhou Luan, presented at #ML4H2024

Bar chart of different barriers to healthcare

14014

Irene Chen @irenetrampoline.bsky.social · 18/12/2024

Very cool! Excited to check it out

010

Irene Chen @irenetrampoline.bsky.social · 17/12/2024

It's giving Best Paper at the ML for Health Symposium (co-located w NeurIPS)!! 🥳 Congrats to co-authors Emily, Jin, and many others 👏. Check out our work using LLMs to understand liver transplants, esp understudied social and economic factors 🏥💰🏠! #ml4h2024 arxiv.org/pdf/2412.07924

2683

Irene Chen @irenetrampoline.bsky.social · 12/12/2024

This year our CHEN lab holiday party featured cookie decorating! 🎄 Grateful to have such creative and inspiring students and collaborators. 🥰 Can you spot all of the ML-related cookies? 📈

090

Irene Chen @irenetrampoline.bsky.social · 18/11/2024

Important caveats: 1) Very small sample size (6 medical cases) -> p=0.03 which is kinda sus, 2) human physicians in study had only 3 yrs of training, 3) no nuance of how to use LLMs for diag reasoning: clinical notes != clean cases; paper does not engage with this.

5384

Irene Chen @irenetrampoline.bsky.social · 15/11/2024

What do it mean to be a “low resourced” language? I’ve seen definitions for less training data to low number of speakers. Great to see this important clarifying work at #EMNLP2024 from @hellinanigatu.bsky.social et al aclanthology.org/2024.emnlp-m...

0243

Irene Chen @irenetrampoline.bsky.social · 15/11/2024

Informative recap of EMNLP papers related to multilingual models and low resource languages! Thanks @catherinearnett.bsky.social

071

Irene Chen @irenetrampoline.bsky.social · 14/11/2024

Fairness definitions differ across groups! For white respondents, fairness = "proximity'' to assigned school. For Hispanic or Latino parents, fairness = "same rules'' for everyone. Cool work by @nilou.bsky.social + students

092

Irene Chen @irenetrampoline.bsky.social · 14/11/2024

Summary of #AMIA2024 presentations related to health equity and algorithmic fairness! Thanks for pulling together @alyssapradhan.bsky.social

091

Irene Chen @irenetrampoline.bsky.social · 14/11/2024

Super interested in this use case! Do you remember who the presenter was here?

100

Irene Chen @irenetrampoline.bsky.social · 13/11/2024

If you trained 10 models and they had a huge variance on predictions for you, would you have any faith in the model? Enjoyed this paper defining self-consistency -- and showing enforcing that makes models more fair! Cool AAAI24 paper from A. Feder Cooper et al. katelee168.github.io/pdfs/arbitra...

0113

Irene Chen @irenetrampoline.bsky.social · 12/11/2024

12 hours later, I've realized how much I've been missing a place like OldTwitter where you can share candid thoughts on research without bots clogging up the feed. Thanks Bluesky 💙

0400

Irene Chen @irenetrampoline.bsky.social · 12/11/2024

Giving a talk tomorrow 11:40am PT at the Simons Domain Adaptation Workshop. I'll be speaking about our recent paper on the Data Addition Dilemma! Catch the talk on live-stream or recorded afterwards Paper: arxiv.org/pdf/2408.04154 Workshop: simons.berkeley.edu/workshops/do...

0151

Irene Chen @irenetrampoline.bsky.social · 12/11/2024

Creative AIES 2024 paper by andreawwenyi.bsky.social that uses NLP to help uncover gender bias for men/women defendants. Legal experts used NLP to build consensus and evidence on annotation rules. Could have relevant tie-ins to healthcare and bias in clinical notes

082

Irene Chen @irenetrampoline.bsky.social · 12/11/2024

The CHEN Lab doesn't just work on cool ML+health problems! We also enjoy viewing cacti, making pasta, and climbing on chairs irenechen.net/join-lab/

050

Irene Chen @irenetrampoline.bsky.social · 12/11/2024

First post! I'm recruiting PhD students this PhD admission cycle who want to work on: a) impactful ML methods for healthcare 🤖, b) computational methods to improve health equity ⚖️, or c) AI for women's health or climate health 🤰🌎 Apply via UC Berkeley CPH or EECS (AI-H) 🌉. irenechen.net/join-lab/

24321

Irene Chen @irenetrampoline.bsky.social · 12/11/2024

Can't figure out how to DM on bsky, but are you defining bioML as distinctly from clinical here?

100

Irene Chen @irenetrampoline.bsky.social · 12/11/2024

Love this! Went from 0 to 20+ following in one click.

020

Irene Chen @irenetrampoline.bsky.social · 12/11/2024

Any citations for this? Would love to dig in more 🧐

100