Michael Moor
Hi there! I’m a MD, PhD who is excited about machine learning in healthcare. Since late 2024, I was appointed as a tenure-track assistant professor for medical AI at ETH Zurich (D-BSSE) located in Basel. Previously, I did a postdoc at Stanford University in the Computer Science department with Prof. Jure Leskovec. My research focuses on developing and evaluating large-scale medical foundation models, with the ultimate vision to unlock generalist models for medical AI.
News
- 2024-09-01: Excited to start my new research group at ETH Zurich! Check out lab-related news on that page.
- 2024-02-02: It was a great honor to be invited to talk at the NASA Ames Research Center!
- 2024-01-25: Excited to see our paper on retrieval-augmented language models for medicine published in NEJM AI!
- 2024-01-20: Looking forward to give a keynote presentation at the Basel Healthtech Conference 2024!
- 2023-10-05: Delighted to announce that our paper Zero-shot causal learning got accepted to NeurIPS 2023 as a Spotlight! We developed a framework for meta-learning treatment effects across thousands of drugs and millions of patients to unlock a new capability: predicting personalized treatment effects zero-shot, i.e. without ever having observed the intervention before (e.g., a novel drug). Check out the thread.
- 2023-07-27: Excited to announce Med-Flamingo, a multimodal medical few-shot learner! Stoked to see our thread to reach >200k impressions! Furthermore, the paper got covered by Huggingface Daily Papers and the medical AI newsletter Dr. Penguin!
- 2023-07-17: Thrilled to give a talk at IBM Research Zurich today! I will talk about our recent Nature paper and some exciting ongoing medical foundation model work.
- 2023-07-11: Honored to join Stanford HAI today to give an executive education course on multimodality in foundation models!
- 2023-06-22: Thrilled to talk today about Generalist medical AI at Stanford’s MedAI Group exchange. I will present our recent Nature paper and some cool ongoing work.
- 2023-05-25: Excited to give a guest lecture at Stanford in Prof. Emma Brunskill’s CS 31 N course ‘Counterfactuals: The Science of What Ifs?’. Hamed and I present and discuss our recent paper Zero-shot causal learning.
- 2023-04-12: A dream come true. Thrilled to announce our paper Foundation models for generalist medical AI was published today in Nature! Check it out here.
- 2023-04-10: Excited to give a talk at Prof. Sean Mackey’s lab at Stanford Medicine titled Medical foundation models: a primer on pre-trained, multimodal medical AI.
- 2023-02-05: New preprint: Zero-shot causal learning. First paper of my postdoc! Check it out here
On X (Twitter)
Finally, it's official: I will join @ETH Zurich as an assistant professor!!
— Michael Moor (@Michael_D_Moor) July 12, 2024
My group will be part of the beautiful @ETH_BSSE department (see new building below right).
Our group will focus on medical foundation models, multimodality, retrieval augmentation, dataset and… pic.twitter.com/u7lXgeCY8E
📢 New piece published today in @Nature!
— Michael Moor (@Michael_D_Moor) April 12, 2023
It was a pleasure to work with such a stellar team including Oishi Banerjee, @ZahraShakerii, @hmkyale, @jure, @EricTopol, and @pranavrajpurkar!
🧵below.https://t.co/xSEkkaXqJ8@Stanford @Harvard @Yale @UofT @scrippsresearch
1/n
Excited to see our paper covered on the @Stanford news front page:
— Michael Moor (@Michael_D_Moor) April 13, 2023
Link to the post: https://t.co/Z2uPX0yw2g
Thank you for great article @coreybinns, and the strong support by Jill Wu and @Taylor_Kubota! https://t.co/ObXhtGAX9r pic.twitter.com/OtQkGGh0Vx
Gave my first live talk @Stanford about "Topol🍩gical representation learning".
— Michael Moor (@Michael_D_Moor) May 25, 2022
Here are the slides 🖥, created with reveal.js 🔥https://t.co/IXlTb9hxtM#MachineLearning #TDA#topology #revealjs (1/2) pic.twitter.com/r1C3uwLlTw
I am truly delighted to announce that I will join @jure's group at @Stanford as a #postdoc this March!
— Michael Moor (@Michael_D_Moor) February 2, 2022
Excited to connect & chat about #ML/#AI for #health and more! @StanfordEng @StanfordMed #MedTwitter (1/4) pic.twitter.com/ZmeTRxKvcv
If you want to predict clinical phenotypes using #MachineLearning, check out our systematic review on ML-based #sepsis prediction. A THREAD with take-aways that could be relevant to #AI in #healthcare in general. (--> = hints for practitioner) 1/nhttps://t.co/t9tzkTQ6Cn pic.twitter.com/j6gnOuKQ2a
— Michael Moor (@Michael_D_Moor) May 29, 2021