I’m really excited to share the first paper of my PhD, “Learning Disease Progression Models That Capture Health Disparities” (accepted at #CHIL2025)! Link and summary in thread✨1/

I can’t believe I’m saying this: our work received a Best Paper Award at #CHIL2025!! So so excited and grateful 🥰 Looking forward to day 2 of the conference with these awesome people :)

RT @NikhGarg: I wrote about science cuts and my family's immigration story as part of the McClintock Letters initiative. Haven't yet placed….

RT @dmshanmugam: New work 🎉: conformal classifiers return sets of classes for each example, with a probabilistic guarantee the true class i….

RT @rishi_d_jha: I’m stoked to share our new paper: “Harnessing the Universal Geometry of Embeddings” with @jxmnop, Collin Zhang, and @shma….

I really enjoyed (and learned a LOT from) working on this project with these wonderful co-authors:.@dmshanmugam .Ashley Beecy.Gabriel Sayer.@deborahestrin .@NikhGarg .@2plus2make5 . Check out the paper here! 7/7.

Our work underscores the importance of accounting for health disparities; we lay a foundation for doing so with a method to (1) estimate disease severity in the presence of health disparities and (2) identify disparity patterns that can inform public health interventions. 6/.

The interpretability and identifiability of our model also allow us to capture fine-grained descriptions of disparities. Fitting our model on heart failure patient data from NewYork-Presbyterian, our model identifies groups that face each type of health disparity. 5/.

We prove that *failing to* account for these disparities biases severity estimates. By jointly accounting for all three, our model more accurately recovers severity. Indeed, accounting for these disparities in real heart failure data does meaningfully shift severity estimates. 4/.

We propose an interpretable disease progression model that captures 3 key disparities: certain patient groups may (1) start receiving care at higher disease severity levels, (2) experience faster disease progression, or (3) receive less frequent care conditional on severity. 3/.

Disease progression models are often used to help healthcare providers diagnose and treat chronic diseases. But these models have historically failed to account for health disparities that bias the data they are trained on. 2/.

RT @2plus2make5: The US government recently flagged my scientific grant in its "woke DEI database". Many people have asked me what I will d….

check out the findings from our #dogathon 😍🐶 !!.

RT @kennylpeng: New paper/code! Sparse Autoencoders for Hypothesis Generation. HypotheSAEs generates interpretable features of text data th….

RT @rajivmovva: 💡New preprint & Python package: We use sparse autoencoders to generate hypotheses from large text datasets. Our method, Hy….

RT @2plus2make5: Please retweet: I am recruiting PhD students at Berkeley!. Please apply to @Berkeley_EECS or @UCJointCPH if you are intere….

RT @NikhGarg: My NSF CAREER proposal was just awarded! Excited to continue our work on data science/AI/operations for the public interest,….

1 down, N-1 to go… Moving from Ithaca to NYC today, which marks the end of my first year as a PhD student! This year in Ithaca has been full of wonderful friends and lots of growth :) Excited for the rest! 🌃

RT @BenDLaufer: It’s an honor to have been named a “rising star” by Stanford in management science and engineering, and to be featured on t….

RT @JuntaoRen: Excited to share a new framework to design provably efficient inverse reinforcement learning algorithms, to appear at #ICML2….