
Associate Professor of Biomedical Informatics, Harvard Medical School @HarvardDBMI | Founding Deputy Editor, @NEJM_AI | Co-host, NEJM AI Grand Rounds
Boston, MA
Joined July 2014
- Tweets1.9K
- Following452
- Followers4K
- Likes3.8K
Pinned Tweet
🧵1/ Our new study on AI and physician reasoning just came out in @ScienceMagazine. As co-senior author, I'm excited about our findings, and I do think AI will reshape medicine. But after seeing some of the discussions, I'm also worried about how our findings may be misinterpreted.
Arjun (Raj) Manrai retweeted
Career update/news including that I'm hiring!
Late in the summer, I made the jump to @AnthropicAI to help co-lead a moonshot effort in genetic medicine.
I'm hoping to have a proper update to share publicly fairly soon, but if you know my collection of interests (AI, clinical genetics, therapeutics, rare disease non-profits), you are unlikely to be surprised. Much of the upfront effort here requires infra for moving atoms as well as bits, and we explicitly want to lean deeply into collaborations with academics, non-profits, and key industry partners in the space. If either of the below roles sound like you, please apply through the link. More to come!
Program Manager:
job-boards.greenhouse.io/ant…
CMC and Manufacturing Lead:
job-boards.greenhouse.io/ant…
On AI Grand Rounds, Dr. Michal Nedoszytko (@mnedoszytko) explains how AI can help physicians gather better information, improve the quality of conversations with patients, and prototype solutions to problems that clinicians experience every day. 🎧 nejm.ai/ep47
Arjun (Raj) Manrai retweeted
1/n Excited to share AI ECHO INSIGHT, the first blinded, randomized trial of AI for the full echo report, presented today by Keane Lee at #ScientificSessions26 Late-Breaking Science.
EchoPrime and EchoNet-Measurements drafted the interpretations and measurements for cardiologist review. #echofirst
It was a ton of fun for us to have Mark Cuban back on our @NEJM_AI podcast for a second time. We reflected on progress in medical AI over the last few years, asked Mark's thoughts about data centers, and picked his brain about his personal uses of AI in his own life. And we of course got to ask about LeBron and Skip Bayless again too. Episode out on @NEJM_AI Grand Rounds soon!
Arjun (Raj) Manrai retweeted
Was great to have @mcuban back on the podcast! Really excited to have this one out, Mark's always such an amazing interview.
Arjun (Raj) Manrai retweeted
1/3 Latest ep of @NEJM_AI Grand Rounds, feat @mnedoszytko @AbridgeHQ just so good. Fav quote: "You need to live the health care system in order to understand it, because nothing in theory translates into that work." podcasts.apple.com/us/podcas… @AndrewLBeam @arjunmanrai @zakkohane
Arjun (Raj) Manrai retweeted
Doctors are sprinting to build solutions to frictions they’ve tolerated for years. But there’s a chasm between a vibe-coded prototype and a solution that can be deployed safely in a healthcare system.
Great piece by @mnedoszytko in @NEJM_AI
ai.nejm.org/doi/full/10.1056…
Arjun (Raj) Manrai retweeted
My new piece in @NEJM_AI, "Vibe Coding versus Clinical Reality": the barrier to building has dropped, but the barrier to building safely hasn't. Physicians can now prototype; getting it safely to patients still takes engineers working alongside us.
ai.nejm.org/doi/full/10.1056…
Arjun (Raj) Manrai retweeted
Fantastic discussion on building for clinical flows with @NEJM_AI.
Thank you @arjunmanrai and @AndrewLBeam for having me!
Start with the friction clinicians actually experience. On @NEJM_AI Grand Rounds, Dr. @mnedoszytko says living inside the problem can reveal what needs fixing — and why physicians may be well positioned to build a useful solution for care. Full episode: nejm.ai/ep47
Arjun (Raj) Manrai retweeted
AI (?SI) in medicine conversations by knowledgeable AIM (?SIM) scientists on the @NEJM_AI Grand rounds. Kudos @arjunmanrai @AndrewLBeam for the top AI in Healthcare ranking podcast.feedspot.com/ai_heal…
I envy us.
Arjun (Raj) Manrai retweeted
I built an interactive echocardiography tutorial with Claude Code.
Chapter 07: a 3D heart, the standard imaging views, the probe position, and simulated ultrasound video.
Arjun (Raj) Manrai retweeted
Excited for the launch of the Smith Institute for Evidence, Innovation, and Policy—tackling health care’s biggest questions and turning evidence into better care and healthier lives
Honored to serve as Director of the Institute & lead this next chapter with @rwyeh @BIDMChealth
Read more: bidmc.org/news-stories/all-n…
After a decade of growth, we’re now the Richard A. and Susan F. Smith Institute for Evidence, Innovation, and Policy.
The Institute's centers will bring together bold ideas, rigorous science, and clinical expertise to improve people’s health and lives.
bidmc.org/news-stories/all-n…
Looking forward to representing @NEJM_AI on this panel with the EICs of Cell, Nature, and Science at the @broadinstitute next week, and discussing AI in submissions & peer review...should be a fun discussion! (free Zoom registration below)
Some of our relevant experience @NEJM_AI: ai.nejm.org/doi/full/10.1056…
Way to go @AdamRodmanMD !! 🚀
Congratulating Dr. Adam Rodman on his Harvard Medical School Promotion!
Adam Rodman MD, MPH, of the Division of General Medicine, has been promoted to an Associate Professor of Medicine at HMS.
13
2,507
Fun for @AndrewLBeam and me to get a chance to chat with @suchisaria today for @NEJM_AI Grand Rounds!
Arjun (Raj) Manrai retweeted
I love this @arjunmanrai: "The real frontier might now be the yardstick itself, a science of [clinical AI] evaluation that is durable and reliable enough to endure the continuing shifts in what is being measured." IOW, let's define the competencies, sub-competencies, and activities against which we evaluate AI (and human) clinicians and that, in their totality, define clinical intelligence. And it ain't solving MCQs.
Are we heading to a reproducibility crisis in medical AI? My latest in @Nature on the (shaky) science of evaluation of medical AI:
Medical AI has a measurement problem
Arjun (Raj) Manrai retweeted
Great article of the challenges of measuring clinical AI, though I would take this a step further -- in measuring clinical AI agents, we have largely (re)discovered the same problems that vex us in measuring the quality of doctors.
Are we heading to a reproducibility crisis in medical AI? My latest in @Nature on the (shaky) science of evaluation of medical AI:
Medical AI has a measurement problem
Arjun (Raj) Manrai retweeted
In @nature "Researchers...in an environment in which medical AI is changing faster than they can study it, and the yardstick used to measure it is often inconsistent." @arjunmanrai summarizes conundrum nature.com/articles/d41586-0… Now benchmarking -> RCTs. But which RCTs are worth the squeeze?
Are we heading to a reproducibility crisis in medical AI? My latest in @Nature on the (shaky) science of evaluation of medical AI:
Medical AI has a measurement problem
























