Rohit Vashisht

Tahoe sky!

Data to Decisions: Engineering the Foundations for Target Trial Emulation and Causal Inference in Medicine Across @uofcahealth.bsky.social

Excited for this talk at UCSF-Epibiostat. I will discuss our ongoing efforts in harnessing large-scale RWD for post-market monitoring of therapeutic.

GitHub - rohit43/UcColoR Contribute to rohit43/UcColoR development by creating an account on GitHub.

Great!
In case there’s a need to use UC brand colors in plots etc. github.com/rohit43/UcCo...

The Catch in Catching Cancer Early New blood tests promise to detect malignancies before they’ve spread. But proving that these tests actually improve outcomes remains a stubborn challenge.

The catch in catching cancer early!

As usual an impeccable article by Siddhartha Mukherjee in @newyorker.com

All the more important when one tends to think deeply about causal inference from healthcare data!

A must read.

www.newyorker.com/magazine/202...

Swimming in DuckLake!
@duckdb.org

I so want to switch back to Nokia ਗਿਆਰਾਂ-ਦੱਸ

L3M: Large language life models
L2M: Large language models

Appreciated the opportunity to partner with Aaron Boussina to share our experience at UC San Diego Health in using LLMs to measure quality, safety, and patient flow through our health system at the National Academy of Medicine Leadership Consortium.

You can’t improve what you can’t measure.

DuckDB is straight-up fire!

The mechanics behind the beauty of roses As rose petals change shape during maturation, they do not follow classical geometrical incompatibility

One of those rare and remarkably beautiful studies, often published once in long time. Read with evening chai to enjoy this beautiful work!

The mechanics behind the beauty of roses | Science www.science.org/doi/10.1126/...

Impressive! The conversation it creates around a simple phrase like ਰਾਵੀ ਤੋਂ ਚਨਾਬ ਪੁੱਛਦਾ, ਕੀ ਹਾਲ ਆ ਸਤਲੁਜ ਦਾ is really something! Like listening to All India Radio, Jalandhar late at night sleeping on roof top!

NotebookLM now supports Punjabi.

support.google.com/notebooklm/a...

Great meeting everyone!

Never really could understand why adjusting only for PS is sufficient. What if PS model specification is wrong, or not optimal among other things.

Excited for this seminar!

New Constraints on DMS and DMDS in the Atmosphere of K2-18 b from JWST MIRI The sub-Neptune frontier has opened a new window into the rich diversity of planetary environments beyond the solar system. The possibility of hycean worlds, with planet-wide oceans and H$_2$-rich atm...

The K2-18b paper is now up as a preprint (to be followed by the final paper soon) arxiv.org/abs/2504.12267

Manual coding is the best coding. AI sucks the soul and joy out of typing, deleting and typing again of the thoughts. I tried it once and hated it, never again.

Are you in SoCal?

Come join me on April 24 for a behind-the-scenes talk on the origin of Tidier.jl for #julialang, and why #rstats users should give it a look.

More details will be posted here: www.meetup.com/socal-rug/

STATUS List | Karandeep Singh Karandeep Singh, a professor at UC San Diego, is a leading researcher on the adoption of AI systems in health care and was named to the 2025 STATUS List.

Congratulations, one and only @kdpsingh.bsky.social

www.statnews.com/status-list/...

AI at Meta We're connecting people to what they care about, powering new, meaningful experiences, and advancing the state-of-the-art through open research and accessible tooling

Llama 4 series is here ai.meta.com

Incredible progress!

YouTube video by Prime Video India Dupahiya Official Trailer | Prime Video India

youtu.be/YZ1S3Jvegz4?...

Congratulations @keisukenakagawa.bsky.social!

Legitmately thrilled to share our latest work, in which @fernpizza.bsky.social solved an experimental challenge in plasmid biology as old as the field: measuring how plasmids compete and evolve within individual cells!

Intrinsically disordered regions as facilitators of the transcription factor target search https://www.nature.com/articles/s41576-025-00816-3 (read free: https://rdcu.be/eaMBK)

Disease diagnostics using machine learning of B cell and T cell receptor sequences Clinical diagnosis typically incorporates physical examination, patient history, various laboratory tests, and imaging studies but makes limited use of the human immune system’s own record of antigen ...

What an incredible work, and joyful read!

Disease diagnostics using machine learning of B cell and T cell receptor sequences | Science www.science.org/doi/10.1126/...

@anshulkundaje.bsky.social and team.

The capabilities of the large language of life models (LLLMs) are rapidly proliferating!
nature.com/articles/d41...
@nature.com
arcinstitute.org/manuscripts/... @arcinstitute.org
science.org/doi/10.1126/... @science.org

I am excited to partner with our AI researchers in cancer care at @ucsdhealth.bsky.social @ucsdhealthsci.bsky.social to ensure that we can bring cancer discoveries to the bedside.

Learn about the great work happening at Moores Cancer Center: view.publitas.com/77e2eb4e-53b...

AI Grand Rounds Episode 27 From Clinical Notes to GPT-4: Dr. Emily Alsentzer on Natural Language Processing in Medicine

Dr. @emilyalsentzer.bsky.social, a Stanford faculty member and expert in clinical #AI, discusses the evolution of natural language processing, the challenges of AI in clinical settings, and what the future holds for open-source medical AI. Full episode: nejm.ai/4gOGeSo

#MedSky #MLSky

DuckDb

“Researched models aren’t implemented. Implemented models aren’t researched.”

Karandeep Singh, Chief Health AI Officer @ucsdhealth.bsky.social & associate prof @jchi-ucsd.bsky.social, closes out the keynote session by discussing the health AI paradox.

@kdpsingh.bsky.social #SPIEMedicalImaging