James Marcus

Between rooms. On rounds. Walking the corridor outside an OR. Charting one-handed during a phone call. This is where clinical questions happen. Today we're launching Voice Mode. OpenEvidence is the first multimodal medical AI: physicians can type, speak, or listen, on the same evidence base. The clinician asks a clinical question out loud. Voice Mode waits when you pause, stops when you interrupt. The answer comes back concise, peer-reviewed, and verifiable against the source. Conversation with a colleague. That was the bar. For years we've focused on the intelligence: curation, retrieval, citations. Voice Mode is the interface catching up to where physicians practice. The evidence quality doesn't change with the modality. Voice answers are shorter and shaped for listening; the references and the full written form stay in the conversation. Voice Mode is now in OpenEvidence web and mobile.

@Astorshuman @IntlMenopause @OpenAI Very cool, love it.

Had a lot of fun using codex to build this menopause tool 🫶🏻 The future of physician-builders is here menotool.com

Until now, physicians using AI in clinic had to assemble the patient’s context themselves. Allergies, comorbidities, medications, prior procedures, copy-pasted in from the chart. Today we’re announcing a partnership with @CedarsSinai. OpenEvidence now works directly inside Epic, drawing on the patient’s full record and interpreting the medical literature through the lens of that specific patient. Cedars-Sinai is the first academic health system to deploy patient-aware clinical intelligence at enterprise scale. The clinician asks a complex question in natural language. The answer reflects both the best available evidence and the patient in front of them. Patient data is never stored after the clinical session or used for any other purpose.

We're releasing Medmarks v0.1, the largest completely open-source automated evaluation suite for assessing the medical capabilities of LLMs! Developed in our @MedARC_AI community, w/ support from @PrimeIntellect So far we’ve explored 46 models to figure out the best!

@doctorbhargav @DrDiGiorgio Epic is staring to integrate tons of AI feature right now

AI can scale quickly. EHR infrastructure can’t. That mismatch is why progress feels slower than the hype.

Scanned documents are now part of the conversation. Ask Art can pull specific clinical details from scanned and imported documents, just by asking.

We now have causally-informative data on the effects of AI scribe adoption on how doctors spend their time. They work well! AI scribes help doctors to spend less time in EHRs and filling out documentation, allowing them to spend more time with patients.

@yacineMTB Nice! Best hot pool in Ottawa is Splash beside the Costco near Blair rd

PLAN FOR THIS WEEKEND saturday: pool swim time sunday: play dough play date FOOD - hamburgers, bourek, tabouleh, onigiri - baked chicken and baked potatoes and steamed brocolli fuuuuuuuuuuuuuuuuuuuuck yeah

First day using AI-powered smart glasses in clinic. Real-time EHR. No turning to the screen. Just eye contact and conversation. All the data I need, when I need it, dynamically served up and projected into the room. Even differential diagnosis! Early… but unbelievably good 👇

@PGC1a_RB NAC

Gimme all them PM/night antioxidants and increasers of circulation

This may be the most controversial thing I’ve posted. But I think it needs to be said. We are having an urgent conversation about slowing AI in medicine. Instituting rigorous safety measures. Thorough vetting before deployment. Many respected voices are calling for caution, and their instincts are grounded in a tradition of patient safety that I deeply respect. But I want to pose a question that I haven’t seen anyone ask. What is the cost of slowing down? Not the cost to technology companies. The cost to patients. We talk about AI safety as if the alternative is a well-functioning system. It isn’t. The current system produces error rates that have barely improved in decades. M&M cases that rarely lead to broad physician education. Community hospital physicians reliant on self-education of highly variable quality. Emergency physicians who never receive feedback on whether their practice patterns are calibrated — whether they order too many CTs or too few, admit too aggressively or too conservatively. Practice patterns that drift with fatigue across a single shift and across an entire career. These aren’t hypothetical harms. They’re the measured, documented, persistent background rate of medical error that we have normalized. Half of chronic disease medications aren’t taken correctly. Twenty percent of prescriptions are never filled. Up to half of adverse drug reactions are preventable. Thirty to eighty percent of hypertension patients discontinue treatment within the first year. This is the baseline. This is what we’re protecting when we slow AI deployment. Calculus measures continuous change. If we modeled the rate of improvement in patient care as a function over time, slowing AI adoption doesn’t just delay improvement by a fixed amount. It changes the integral. The cumulative patient harm prevented shrinks. Every month of delayed deployment represents ongoing harm from errors that a more capable system could have caught. We aren’t comparing AI with safety checks versus AI without safety checks. We’re comparing AI deployed in 2028 after rigorous vetting versus the current system continuing to produce the same error rates it has produced since 2000. The question is whether the cumulative harm from that delay exceeds the harm AI might introduce. I am not arguing against safety measures. I’m arguing that the cost of delay must be measured against a baseline that is far worse than most people acknowledge. We apply compassionate use and emergency authorization frameworks to drugs when the background mortality rate justifies accelerated deployment. We should at least ask whether AI in medicine has reached that threshold. The instinct to slow down feels responsible. But if slowing down means patients continue dying from errors that AI could prevent — errors we’ve failed to fix for decades through every other means — then the calculus of caution isn’t as simple as it appears. Sometimes the most dangerous thing you can do is nothing.

@MarcusMilione Yes

I want to build a continuous blood lactate meter (if its even possible) anyone want to build together

@NurseTribeNet @AI_4_Healthcare interested on how you are doing this? what ehr are you using?

day 0! the best way i’ve gotten adoption is to run workshops where we give them case studies and the tools and just let them play. sandbox it - no wrong answers, can’t hurt anything. when you come back it’s amazing to hear the creative ways people use it. we’ve seen 92% confidence gain and majority using it daily months later. even coming back with new ideas

This is ass backwards ... "Getting a vendor in the door, running a proof of concept, generating promising numbers in a controlled environment -- health systems have gotten very good at that. What most haven’t figured out is what comes after: how to move AI from a carefully managed experiment into the fabric of clinical and operational workflows, with the governance structures to keep it safe, compliant and trustworthy over time." What the F ... ajita! This is the fault of health system administrators and CAIOs/CIOs! Governance, data readiness/cleanliness, security, legislative compliance, and projecting workflow and patient flow impacts -- involving HCPs and clinicians -- should be occurring Day 1 if not Day 0 or Day -50 of #HealthcareAI pilot projects. Institutions/systems are and will be using a host of AI applications and tools! 🔗beckershospitalreview.com/healthcare-inf… HT @BeckersHR

@JoshCMandel @grok summarize the article

@peptidemaxxer @hollowearthterf @vrilpeptides What about LPS in research peptides?

@hollowearthterf @vrilpeptides lowest price, highest quality. send before after pics lmao

Can someone make an AI tool that takes all medical records in EMR and outside forms a concise note that meets documentation/billing standards and incorporates OpenEvidence AI to formulate plan and discussion Once this tool is made my job just becomes communicating with patients.

for those who have never worked in healthcare, I made a simulation to get a sense of how difficult it is to do something even very simple like order Tylenol. WARNING: this may be infuriating to some providers

GLP 1 medicines are expanding beyond diabetes into obesity, cardiovascular, liver, and inflammatory disease care. Prevention still matters most, and AI will help identify risk earlier and personalize treatment decisions. nature.com/articles/s4159… #MedTwitter #Cardiology #AIinHealthcare #GLP1

@venturetwins @grok what app is this?

One of the industries really adopting AI video? Real estate. Properties are now advertised like products on social feeds — and AI enhancements help them stand out. AI is being used to bring properties to life, or to imagine what could be done in a space.

Be Dr Elisabeth Potter > Princeton molecular bio > crush Emory med school > match into the most competitive plastics residency at UT Southwestern > fellowship at MD Anderson learning to rebuild breasts with a woman’s own tissue > graduate top of the game, DIEP flap queen, 1,000+ cases deep > join big hospital systems in Austin > watch insurance companies nickel-and-dime cancer patients for years > see OR fees hit $30k+ before the surgeon even picks up a scalpel > get the infamous @UHC call *while patient is under anesthesia* asking if she really needs to stay overnight after mastectomy + reconstruction > step out of the OR, fight on the phone, they deny her anyway > posts the video > it explodes > millions of people finally see what doctors have been screaming about for a decade > United sends the lawyers > “delete the videos or else” > she laughs, posts the letter instead, and goes harder > they cut her brand-new surgery center out of network > Redbud Surgery Center, the one she poured millions into so women wouldn’t get crushed by hospital bills > suddenly staring at bankruptcy while still trying to operate > double down on cash-pay transparency > same elite surgeons, same microsurgery expertise > do the $100k+ hospital case for a fraction of the price > same day, same quality, zero corporate middlemen bleeding the patient dry > keep posting, keep fighting, keep winning small battles (Aetna in-network, Cigna in-network, one patient at a time) > turn the whole thing into a movement > be the surgeon who said “if I want healthcare to be different, I have to practice differently” > actually do it > still in the arena > still taking on the biggest insurers in America > still rebuilding women after cancer I’m inspired! The Elizabeth Potter arc is what I hope for all my physician colleagues @EPotterMD @DutchRojas