In case you were wondering why there hasn't been a new @BedsideRounds in a while ... magazine.hms.harvard.edu/art…

I think @ZekeEmanuel and others are wrong about AI replacing physicians, but AI is already playing an important role in my clinical life. I’ve come to rely on @OpenEvidence enormously, and I believe it’s making me a better doctor. At the same time, I worry that frictionless access to clinical decision support is making my learners worse. I wrote about this for @nytopinion: nytimes.com/2026/09/25/opini…

"Access to medical knowledge shouldn't depend on geography," said Daniel Nadler, founder and CEO of OpenEvidence. That's why OpenEvidence and @AnthropicAI are bringing a specialized version of OpenEvidence, free, to clinicians in about 100 low- and middle-income countries, including Uganda, Angola, Sudan, Haiti, and Mongolia. More here: reuters.com/legal/litigation…

The promise of medical AI is not simply better performance — it is better care grounded in evidence that can be trusted. On AI Grand Rounds, @DrXiaoLiu discusses what rigorous evaluation looks like as technologies move from publications into practice. 🎧 nejm.ai/ep46

Trust in medical AI hasn't been earned yet. But it potentially can be with randomized trials conducted in real world medicine @NatureMedicine @HardyShakerman @cameronphchen nature.com/articles/s41591-0…

The Center of Healthcare Delivery Science hosted a special program about the future of AI in healthcare, featuring Dr. @mdhowellmd, Chief Clinical Officer at @Google and former BIDMC faculty & CMR, and Dr. Adam Rodman. An extraordinary showcase & thank you to all who joined!

You ask, @NYTScience will answer: nytimes.com/2026/09/14/scien…

New Good Medicine with @AdamRodmanMD ! What if AI outdiagnoses your doctor—and adding the doctor back makes the answer worse? That’s the uncomfortable question behind @ZekeEmanuel's recent JAMA article that inspired so much debate! Some takeaways from our conversation. 🧵 1/5

As artificial intelligence is becoming increasingly capable of clinical diagnosis, a new commentary argues that clinicians remain essential for managing risk and accountability, drawing on four uniquely human capacities that #AI cannot replicate. bit.ly/4h039MG @andrewparsonsMD @AdamRodmanMD

📣 New episode of Good Medicine! Dr. Adam Rodman (@AdamRodmanMD), a physician, researcher, and medical historian, discusses the uncomfortable realities of AI in healthcare. Key takeaways: -Why "human in the loop" is a hypothesis we need to test, not assume. -Why AI diagnostic accuracy doesn't automatically mean better patient care. -How AI's greatest value might be filling the gaps in care we currently can't provide. Plus: deskilling, self-driving cars, and a philosophical defense of pineapple on pizza. Where do you think physician oversight adds the most value? If you're a physician, join the conversation on Roon: roon.com/doctors/posts/bFUe2… Or catch the episode here: rohanramakrishna.substack.co…

How do physicians perceive the quality of #AI generated e-consult advice? And how does that influence their uptake of management recommendations? Take a look at our new article in @JournalGIM! By Gabi Desjardins, Varun Jain, and @mgsimonson1 🧵Below link.springer.com/article/10…

The clinician's role in the AI medical era "Clinicians cannot, and should not, resist powerful AI technologies if these systems improve the quality of patient care." "We contend that the clinician's enduring role is accountability." [I think the enduring role is well beyond that, but OK] perspective by @andrewparsonsMD and @AdamRodmanMD @AnnalsofIM acpjournals.org/doi/10.7326/…

Star Trek pubmed is pretty slick

This feels like the plot of a Neal Stephenson novel from the 90s...

In 2019, a flood on the Congo River triggered something truly remarkable. Long after the flood reached the Atlantic, a dense underwater avalanche kept going for more than 700 mi (1,130 km) across the seabed, leaving a huge scar. And it accelerated as it went. 1/n

The authors of this perspective cannot be more wrong. 5 reasons why: 1/ It is already well known that when you clearly scope a task to a defined input set, or when the input data is clearly defined with a known prevalence of disease, AI will almost always outperform clinicians. This covers tasks like interpreting free text, differential diagnosis, or prescribing treatment or management. What is much less clear are the grey areas where interpretation is open-ended, especially when there is no clear pathological signal, such as the early onset of a chronic disease. These are usually the areas where AI models underperform and where clinical judgement plays a critical role. For example, how do you integrate a person's history, symptoms and context to decide which additional clinical tests to order and ultimately establish a differential diagnosis? 2/ The perspective heavily cites AI systems such as Google's AMIE as evidence that AI is about to surpass physicians. But note how these systems are evaluated. Much of the evidence comes from simulated clinical encounters or carefully constructed cases, which may contain far less of the noise, ambiguity and incompleteness of real-world clinical care. In such clean and bounded data spaces, it is not particularly surprising that AI performs exceptionally well. The authors themselves acknowledge that most studies comparing AI and physicians are simulations of discrete cognitive medical tasks rather than analyses of real clinical interactions. 3/ More importantly, none of this gives us enough evidence to make such a sweeping conclusion about autonomous AI. Where are the randomized, prospective, real-world trials comparing AI alone vs physicians vs AI + physicians across actual clinical workflows? The perspective cites studies mainly with carefully constructed evaluations and retrospective comparisons, but very little evidence of AI operating across the messiness of real clinical care. And yet from this relatively narrow evidence base, the argument moves quite confidently towards AI-alone care becoming superior to AI-aided physicians. 4/ Somehow I feel the authors have treated medicine like a game where the winner deserves to replace the weaker entity, which in this case happens to be the human. But medicine is not a zero-sum game. Humans have never been particularly good pattern recognizers in very high-dimensional data spaces, and this is not something they should have to do alone in the first place. Their job is to provide care using whatever tools are available at their disposal, from the simplest stethoscope to a frontier LLM. It involves understanding context, uncertainty, preferences, and treating another human being with compassion, empathy and as little bias as possible. 5/ I strongly believe the future is AI + human, not AI vs human, and I think there is even a simple statistical intuition behind this. Independent judgements can cancel out each other's errors. There is a reason aggregated or crowd-sourced judgement can outperform a standalone opinion. So the more interesting question is not whether AI will replace physicians. It is how we can design AI + clinician systems where one compensates for the weaknesses of the other, and together they provide better care than either could alone

Lol at me filming promotional videos 😂 It's a great course run by great educators -- hope to see you there!

This might be the most beautiful thing I've read in my life. What a privilege to be alive in 2026. ordinaryabundance.com

Hi clinician friends - I'm really excited to release Osler Prerounds! Prerounds is a tool I built for hospital medicine, to serve as a "command center" to think, plan, and track everything during busy inpatient service. I've been using it daily on inpatient medicine service, and it has been extremely useful in helping me better reason about, and stay on top of, patient management. Some useful features: - quickly store and track evolving patient data across your entire service - TODO tracking across all patients + timed reminders for tasks - export to PDF/printout to take with you during rounds - all data is stored 100% locally, with nothing leaving your computer! Available now, for free! any feedback welcome :)

How do we train AI to practice medicine like a real clinician? 🩺🤖 Moving away from static medical QA, we introduce ResidencyRL — a learning-in-simulation RL framework to train AI agent through interactive "practice". The agent "practices" with LLM simulated patients —learning when to probe further, utilize tools, and avoid "premature closure". A major milestone toward clinical mastery through RL simulation! 🔗 arxiv.org/abs/2608.07418 This work is a collaboration across teams at @GoogleDeepMind @GoogleResearch, with @OpsBug @quocleix and many more!

Interesting piece on "echoborgs" in residency interviews (where an applicant is effectively a "mouthpiece" of an AI system, like what happened with leetcoding interviews). I've heard RUMORS of this -- anyone experienced this in real life? cureus.com/articles/520726-a…