Arjun (Raj) Manrai (@arjunmanrai) 's Twitter Profile
Arjun (Raj) Manrai

@arjunmanrai

Assistant Professor of Biomedical Informatics, Harvard Medical School @HarvardDBMI | Founding Deputy Editor, @NEJM_AI | Co-host, NEJM AI Grand Rounds

ID: 2693638267

linkhttps://dbmi.hms.harvard.edu/people/arjun-raj-manrai calendar_today30-07-2014 18:28:42

1,1K Tweet

3,3K Followers

396 Following

NEJM AI (@nejm_ai) 's Twitter Profile Photo

On the latest NEJM AI Grand Rounds, Dr. Faisal Mahmood (Faisal Mahmood) shares how releasing the CLAM model supercharged progress in computational pathology and unlocked ideas he never imagined — from scaling systems to plant pathology applications. nejm.ai/ep29

Marinka Zitnik (@marinkazitnik) 's Twitter Profile Photo

That's a wrap on our graduate course in Biomedical AI! We have made materials publicly available for others to benefit from them and to support learning in this fast-moving field zitniklab.hms.harvard.edu/AIM2/ DBMI at Harvard Med Harvard Medical School Kempner Institute at Harvard University Broad Institute

Pranav Rajpurkar (@pranavrajpurkar) 's Twitter Profile Photo

A big day – we are making the largest dataset of chest X-rays available to the world. This is the first dataset to cross 100k patients. huggingface.co/datasets/rajpu


AATS (@aatshq) 's Twitter Profile Photo

To start his #AATS2025 David J. Sugarbaker Memorial Lecture, Arjun (Raj) Manrai presents a case and diagnosis. He then asks, “How would Dr. GPT do?”

To start his #AATS2025 David J. Sugarbaker Memorial Lecture, <a href="/arjunmanrai/">Arjun (Raj) Manrai</a> presents a case and diagnosis. He then asks, “How would Dr. GPT do?”
Crystal Zhang, MD, MPH (@crystalzhangmd) 's Twitter Profile Photo

Dr. Arjun (Raj) Manrai gave a thought-provoking, cautionary, yet hopeful talk about AI in Medicine and Surgery during #AATS2025, emphasizing the need for physicians to be actively involved in ensuring AI generates accurate medical information AATS DBMI at Harvard Med NEJM AI

Dr. <a href="/arjunmanrai/">Arjun (Raj) Manrai</a> gave a thought-provoking, cautionary, yet hopeful talk about AI in Medicine and Surgery during #AATS2025, emphasizing the need for physicians to be actively involved in ensuring AI generates accurate medical information <a href="/AATSHQ/">AATS</a> <a href="/HarvardDBMI/">DBMI at Harvard Med</a> <a href="/NEJM_AI/">NEJM AI</a>
Arjun (Raj) Manrai (@arjunmanrai) 's Twitter Profile Photo

It was fun to be at #AATS2025 and meet many amazing surgeons, and a real privilege to deliver the Sugarbaker Memorial Lecture in honor of an impressive physician and leader en.wikipedia.org/wiki/David_Sug


Arjun (Raj) Manrai (@arjunmanrai) 's Twitter Profile Photo

#SAIL2025 was a terrific meeting and this sample of anonymized quotes collected by Irene Chen includes a level of candor rarely heard in medical AI meetings (kudos to Emily Alsentzer Isaac Kohane and organizers for both the program and deciding on Chatham House Rule)

Alan Karthikesalingam (@alan_karthi) 's Twitter Profile Photo

Pleased to join Arjun (Raj) Manrai Andrew Beam on NEJM AI Grand Rounds with my teammate Anil Palepu. Thanks for the chance to discuss our work & an amusing side note on how to pronounce our projects... with a name like mine I find it’s best to take a relaxed view

Adam Rodman (@adamrodmanmd) 's Twitter Profile Photo

Huge update to our preprint today on the superhuman performance of reasoning models in medical diagnosis! TL;DR – they don't just surpass humans in meaningful benchmarks, but in actual medical care from unstructured clinical data: A đŸ§”âŹ‡ïž: x.com/AdamRodmanMD/s


Adam Rodman (@adamrodmanmd) 's Twitter Profile Photo

As someone who studies clinical reasoning and human-computer interaction, I have a LOT of feelings about this, hence this NEJM AI editorial with Arjun (Raj) Manrai Laura Zwaan and Andrew Olson, MD (link: ai.nejm.org/doi/full/10.10
)

As someone who studies clinical reasoning and human-computer interaction, I have a LOT of feelings about this, hence this <a href="/NEJM_AI/">NEJM AI</a> editorial with <a href="/arjunmanrai/">Arjun (Raj) Manrai</a> <a href="/LauraZwaan81/">Laura Zwaan</a> and <a href="/andrewolsonmd/">Andrew Olson, MD</a> 

(link: ai.nejm.org/doi/full/10.10
)
Adam Rodman (@adamrodmanmd) 's Twitter Profile Photo

Arjun (Raj) Manrai and I wrote this piece a year ago -- and I'm incredibly excited that we're one step closer to this reality. link: statnews.com/2024/05/03/ai-


Arjun (Raj) Manrai (@arjunmanrai) 's Twitter Profile Photo

We just added a major new experiment to our o1 study, comparing o1 and attending physicians at key diagnostic touchpoints on REAL cases from the BIDMC ER Stellar work led by Thomas Buckley and Peter Brodeur as part of a rapidly growing DBMI at Harvard Med and BIDMC collab 🚀

NEJM AI (@nejm_ai) 's Twitter Profile Photo

Cardiologist & Abridge CEO Dr. Shiv Rao, MD joins NEJM AI Grand Rounds to explore what it takes to build trustworthy AI in health care. From generative AI to clinician trust, taste to empathy — this episode is about more than tech. Listen now: nejm.ai/ep30

Cardiologist &amp; <a href="/AbridgeHQ/">Abridge</a> CEO Dr. <a href="/ShivdevRao/">Shiv Rao, MD</a> joins <a href="/NEJM_AI/">NEJM AI</a> Grand Rounds to explore what it takes to build trustworthy AI in health care. From generative AI to clinician trust, taste to empathy — this episode is about more than tech. Listen now: nejm.ai/ep30
Ethan Mollick (@emollick) 's Twitter Profile Photo

Updated paper by physicians at Harvard, Stanford, and other academic medical centers testing o1-preview for medical reasoning & diagnosis tasks: “In all experiments—both vignettes and emergency room second opinions—the LLM displayed superhuman diagnostic and reasoning abilities.”

Updated paper by physicians at Harvard, Stanford, and other academic medical centers testing o1-preview for medical reasoning &amp; diagnosis tasks: “In all experiments—both vignettes and emergency room second opinions—the LLM displayed superhuman diagnostic and reasoning abilities.”
Morgan Cheatham (@morgancheatham) 's Twitter Profile Photo

in the not-too-distant future, the most complete record of a patient's symptoms may live in the memory of a consumer-facing language model.

Arjun (Raj) Manrai (@arjunmanrai) 's Twitter Profile Photo

Really fun to have my co-host and great friend Andrew Beam be the guest on NEJM AI Grand Rounds. We've spent a lot of time together over the last decade but even I learned a lot about Andy's childhood and career, what he's up to now, and where AI is going. Episode out soon!

Really fun to have my co-host and great friend <a href="/AndrewLBeam/">Andrew Beam</a> be the guest on <a href="/NEJM_AI/">NEJM AI</a> Grand Rounds. We've spent a lot of time together over the last decade but even I learned a lot about Andy's childhood and career, what he's up to now, and where AI is going. Episode out soon!