Irene Chen
@irenetrampoline
Followers
9K
Following
18K
Media
121
Statuses
1K
ML for healthcare and equity. Assistant Professor @UCBerkeley and @UCSF. Prev @Harvard, @MIT, @MSFTResearch
Cambridge, MA
Joined April 2013
RT @benlandautaylor: I read a lot of science fiction as a kid, so it's kind of a shock that the most prescient novel from my youth was in H….
0
690
0
Looking for an emergency reviewer for NeurIPS paper for a fairness paper, due in a week. Email or DM me! Ideally you’ve first-authored a paper in a major ML conference . Reward is a thoughtful compliment about you and your work.
1
2
10
RT @lltjuatja: committed to doing my part in decreasing reviewer workload by writing fewer papers.
0
18
0
RT @dhadfieldmenell: As peer review continues to fall into a death spiral, we should be paying attention to basically nothing else except i….
0
5
0
RT @NeurIPSConf: NeurIPS is seeking additional ethics reviewers this year. If you are able and willing to participate in the review process….
0
12
0
RT @DrDominicNg: Microsoft claims their new AI framework diagnoses 4x better than doctors. I'm a medical doctor and I actually read the pa….
0
1K
0
RT @MonicaNAgrawal: General LLMs perform well on clinical NLP tasks, even though they never see EHR data. How?. Our CHIL 2025 paper, led by….
0
8
0
RT @rajiinio: This was actually one of the tech stories that really captured my imagination back in the day. But I think people are now wel….
0
13
0
Jessica is the type of PhD student that makes me immensely honored to be a professor. If you are going to ICML and interested in post-deployment monitoring, techno-optimism, and why AI predictions are dumb, you should meet up with her!.
@rajiinio @paula_gradu @irenetrampoline @beenwrekt I will be at ICML in a few weeks & would love to chat about how to make this real - I am a critic at heart and also hate self-promo so that’s how you know I really believe in this 🥲.
0
0
27
RT @jessicadai_: individual reporting for post-deployment evals — a little manifesto (& new preprints!). tldr: end users have unique insigh….
0
28
0
8 years ago I attended my first ML for healthcare conference and wrote up some thoughts. Rereading it now, what's old is new again: interpretability, RL, and operationalizing promising tech. Any predictions for 8 years from now? (+ bonus nostalgia pic)
1
1
42
There's a temptation to think that dataset size = inclusiveness, but we can often miss important populations, like CHILDREN! . Our study led by @stanleyzhua shows children are 1% of public datasets, leading to, e.g., 50% false diagnosis rate of cardiomegaly.
The release of public datasets is driving innovations in healthcare AI, but are children seeing the benefit?. Our systematic dataset review reveals that children account for less than 1% of patients across 181 public medical imaging datasets. #HealthEquity #SafePediatricAI
3
2
23
Neha's post here: It was a great honor (and great amount of work 🙃) to serve as General Chair for 2025. I'll be coming back as General Chair for 2026 for CHIL in Seattle. If you're interested in sponsoring, reviewing, or organizing, please let me know!.
medium.com
Last week, I attended the 6th Annual Conference on Health, Inference, and Learning in Berkeley, CA. Here are some insights and questions…
0
1
3
Curious about what's going on in ML + healthcare research? If you missed CHIL 2025 last week, my student Neha wrote up 23 things she learned from attending 🧠
1
1
16
It is easier and flashier to evaluate LLMs on clean data like NEJM cases, but we can't start talking about "medical superintelligence" until we engage with the messy reality of actual real-world clinical data.
Wow. Bullish on AI for clinical reasoning. but nejm cases are not real world :). furthest thing from it. highly curated, highly packaged. none of my patients come with pithy blurbs distilling hours of conversations & chart reviews into pertinent positives and negatives.
7
15
111
RT @stanleyzhua: The release of public datasets is driving innovations in healthcare AI, but are children seeing the benefit?. Our systemat….
0
3
0
General audience blog post: ICML 2025 paper focusing on fairness application: ArXiv position paper:
api.omarshehata.me
Jessica Dai on theory for the world as it could be
0
0
2
What more could we understand about the fractal, “jagged” edges of AI system deployments if we had better ways to listen to the people who interact with them? . What a joy to work w @jessicadai_ using individual experiences to inform AI evaluation (blog/ICML/arXiv links 👇)
4
18
66