
Building Noble, the professional home for physician executives (https://teapawt.org/t.co/NBZ6nu8FWd). GP at Patient Cap. Prev @Stanfordmed @Ucsf. Tweets my own.
San Francisco, CA
Joined January 2011
- Tweets689
- Following2.5K
- Followers827
- Likes7.3K
Pinned Tweet
Huge thanks to @olearykm, and @healthtechnerds for launching our vision for #caremodeling as a differentiation in #digital care delivery. Take a read and let us know your thoughts!!! canvasmedical.com/articles/c…
Saharsh Patel, MD retweeted
If Texas and California had a child, it would be Florida.
With California’s weather and beaches, and Texas’s business and tax-friendly climate, it attracts more billionaire residents and tourists than anywhere else.
How is Florida not universally recognized as the best state?
🤖 Made with AI
Saharsh Patel, MD retweeted
What AI has done so far:
MEDICINE
• Helped paralysed people speak again. (Brain implants turn intended speech into words, even recreating their own voice.)
• Helped a paralysed man stand and walk again. (A brain–spine interface let him control his legs by thinking.)
• Helped blind people read and understand the world around them. (Describing surroundings, reading labels and identifying objects through a phone camera.)
• Uncovered cancers doctors would otherwise have missed. (29% higher breast cancer detection in a major study.)
• Identified antibiotic candidates that kill drug-resistant bacteria. (Abaucin targeted a dangerous superbug in lab and animal tests.)
LEARNING
• Made personalised learning available on demand. (An ‘Einstein’ as your personal tutor whenever you want to learn.)
• Helped students learn twice as much in less time. (A custom AI tutor outperformed an active-learning Harvard physics class.)
• Helped people write, code, design and build without years of specialist training.
SCIENTIFIC DISCOVERY
• Predicted the structures of over 200 million proteins. (Opening new paths to understanding disease and developing medicines.)
• Discovered planets hidden in telescope data. (Including Kepler-90i, the eighth planet in a distant solar system.)
• Recovered ancient writing buried by Vesuvius nearly 2,000 years ago. (Reading inside carbonised scrolls too fragile to unroll.)
• Begun unlocking how animals communicate. (Patterns in whale calls. Evidence that elephants use individual, name-like calls.)
• Produced a proposed solution to one of mathematics’ hardest problems. (Navier–Stokes: 10,000 AI agents, 88 hours, according to OpenAI.)
ENVIRONMENT
• Predicted where a hurricane would strike nine days before landfall. (GraphCast forecast Hurricane Lee’s Nova Scotia landfall about three days ahead of conventional forecasts.)
• Engineered enzymes that break down plastic in hours rather than centuries.
• Detected wildfires before the first emergency call. (Spotting smoke and alerting firefighters earlier.)
• Slashed the weedkiller farmers need by targeting weeds individually. (35% less herbicide in sugarcane trials, with nearly the same weed control.)
ENERGY
• Advanced the science of clean fusion energy. (Controlling and shaping superheated plasma inside an experimental fusion machine.)
• Driven a generational wave of investment in carbon-free energy, from nuclear power to solar and wind. (Microsoft’s Brookfield deal alone targets over 10.5 GW of new renewable capacity by 2030.)
TRANSPORT
• Delivered dramatically safer driverless journeys. (Waymo: 81% fewer injury crashes per mile than human drivers in the areas studied.)
• Given people who cannot drive a new way to travel independently. (Including blind passengers and older people who cannot drive.)
JOBS AND GROWTH
• Fuelled an investment boom. (AI-related investment categories accounted for an estimated 37% of U.S. growth in the first nine months of 2025.)
• Driven demand for the skilled trades building AI infrastructure. (Electricians, welders, construction crews and cooling specialists.)
WHAT AI HAS NOT DONE
• Replaced all the radiologists. Guess what? We still need more of them.
• Used a community’s water. Golf courses use more. (U.S. golf irrigation: roughly 550bn gallons in 2020. Data centres’ direct consumption: 17bn in 2023. Microsoft’s next-generation designs consume zero water for cooling.)
• Raised everyone’s household electricity bills. (Oregon’s PGE: residential bills cut 1.3% after shifting costs to data centres. Indiana’s I&M: proposed household savings of roughly $100 a year, supported by large-customer growth.)
• Demonstrated that it wants to kill us all.
Poll: Americans say there’s a serious risk of AI destroying humanity dlvr.it/TVVpRD
It’s too bad that common sense isn’t so common.
Imagine a chef employed at a restaurant that charges $100 for a hamburger.
One day he gets sick of his institution ripping off customers, so he goes across the street and opens a shop with $5 hamburgers.
Now the hamburger loving people are better off. Competition drives down prices and increases quality.
The original restaurant, angry over the lost business, gets a law passed that bans chefs from owning restaurants.
Everyone would recognize this as a corrupt, protectionist law.
And yet, in healthcare, with skyrocketing costs, we still outlaw physician owned hospitals.
4
223
Saharsh Patel, MD retweeted
This photo makes me fucking happy. Indian guys in cowboy hats getting rowdy at a college football game.
It’s going viral for the wrong reasons right now. But I’m glad people get to see what America looks like in 2026.
We have arrived baby 🤠
Have never seen a healthcare company ship at this rate @OpenEvidence
Open Evidence is a truly exceptional company
Most doctors in America now use the product
The founders are AI native, having previously founded Kensho
They are hiring an elite+++ young engineer to work with the founders on special projects
DM me or apply online
@OpenEvidence
5
680
Saharsh Patel, MD retweeted
Apparently, yesterday @midjourney pivoted from AI image generation to...whole body ultrasound , presumably AI-augmented. I spent some time trying to find hard data and did not come up with much beyond the video. Some thoughts based on the X reactions today.
1) "Nobody's ever done this before." This seems to be a variant on ultrasound tomography, with Butterfly sensors arranged in rings. Ultrasound tomography is not new, with commercial systems available for breast imaging. The system proposed here seems very similar to Garrett et al 2024 (pmc.ncbi.nlm.nih.gov/article…) which provided fuzzy images of the abdomen and extremity. By collating sound wave return from the ring array the system can attempt to minimize artifact from bone and gas. So, we have known this is possible since 2024.
2) "So easy for the patient." The system requires the patient to submerge themselves in water. For commercial breast UT, this simply requires laying on top of a shaped tank, but not going fully in water. As some people have difficulty lying on a DEXA or CT scanner (the latter of which can image in seconds) I will be interested to see how this is received by patients.
3) "This will revolutionize medical imaging." Ultrasound is limited by bone, air (lung, stomach, bowel) and depth of penetration. In the abdomen, this system can "see" around bowel and spine by adding together the full set of images. There is no workaround for the head or lungs and you'll notice that's why they didn't offer any pictures of those areas. It also means it won't be great at screening inside the stomach, intestine, or colon. I also note the volunteers appear fairly skinny. Ultrasound is always more limited in heavier patients.
4) "But AI can fix it!"...not really. Current DL-based reconstruction techniques require at least some undersampling of a region in order to reconstruct the image. You'll get a lovely picture of the outside of the skull. I can AI-upsample a fuzzy photograph but that doesn't mean what comes out of it actually existed. We have a variant of this issue already with MRI DL reconstruction.
5) "But this is better than MRI in the 1970s!" Yes, true. But the competition is not 1970s MRI, it's modern CT/MRI/US and most especially low-field MRI. For brain, for example, low-field MRI is already diagnostic quality and doesn't need shielding. A low-field scanner costs 50k and can be used in an ICU or put in a van. Why would I send a patient to get an experimental full body US when there's whole body MRI available that's already diagnostic quality? science.org/doi/abs/10.1126/…
6) "The FDA has no idea how to regulate this." This one made me laugh. There's an entire set pathway for this. Commercial ultrasound tomography already exists as an easy reference of a similar technology in the application. If they haven't submitted to the FDA, it's because they plan to try at a later date, or because they're not planning on submitting it at all.
Do I think this is new and exciting? Yes. It looks like it's going to be great for body composition, and I do think there will be improvement in the future.
Is it currently medical-grade diagnostic quality? No, not based on what they showed us. Apparently in-person there was a great hand demo. I don't see why that would be an improvement over routine US or MRI in visualizing hand soft tissues.
To quote @khakrish: "It feels like all the same problems as full body MRI with the added problem of an unproven imaging modality and no FDA clearance."
Plenty of doctors love the vision here --- we all need to dream a lot bigger in healthcare. Personally, I believe it's incredible seeing the increased investment and energy from the technology ecosystem. We need it. Lots to prove here, but that is the whole point. Congratulations @midjourney
You'll see a lot of doctors come out "against" this kind of broad screening system. They can even get quite agitated about it. This resistance stems from a well-established clinical consensus: traditional population-level imaging fails to improve health outcomes because false positives and invasive follow-ups do more harm than good. But this view suffers from an obvious blind spot. Existing studies rely on static data and completely ignore time-series imaging. And time-series is ignored because we haven't been able to afford to do high frequency imaging at population scale. Clearly, time series is going to be immensely more valuable than a single image. If you drop costs, value can go from 0 -> 1. On a more fundamental level, the argument against screening rests on an obviously false precept "More information is bad" -- just clearly untrue. More information better, you just have to interpret it correctly.
2
7
226
Saharsh Patel, MD retweeted
I’ll die on this hill.
AI models need to be trained at the individual clinician-level, not the population-level, in order to achieve widespread adoption.
Physicians think about problems differently from one another, and do their work differently as well.
A single AI model to be used “for all” will only be used by a minority of physicians and will be abandoned by the rest.
Rather, AI systems need to be thought of as the individual clinician’s agent. And like a dog, I think that each clinician is going to have to spend substantial time working with and training the model to make it work in the way they need it to.
Until I see this - a lot of this AI software is mostly hype to me.
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.
Proud to support this dream team on a solution that the industry and patients are ready for— lets go!!
NEW: Kin Health raised $9M to build an AI notetaker for patients.
The app transcribes visits, summarizes medical advice, surfaces follow-up actions, & lets users share their care journey with family/friends.
AI scribes have helped clinicians and are now supporting patients too
1
10
1,109
Saharsh Patel, MD retweeted
There's a shocking fact about AI that nobody tells you: You can catch up to the public AI research frontier in just 2 weeks. Yes, really.
I've built a $150M annual revenue startup over the last 8 years and If I were to start a company today, I’d drop everything and go all-in on AI.
But like many busy software builders, I felt lost—overwhelmed by the noisy, crowded and fast-moving modern AI landscape. And I wasn’t alone.
So I spent my entire holiday diving deep into AI research—reading 30+ papers, watching hours of lectures, analyzing trends, and catching up to the research frontier.
✨ Here’s what I learned:
- You don’t need months (or years) to catch up.
- You don’t need a PhD or decades of ML experience.
- You need fewer than 20 papers and 2 weeks to understand the major breakthroughs shaping AI today.
It's because the technology is extremely nascent and most techniques that came before are no longer relevant:
- ChatGPT is barely 2 years old and Transformers are only 7 years old.
- Most game-changing discoveries happened within the last 4 years, driven by a few breakthrough ideas, scaling laws, and efficient matrix multiplication.
The biggest secret?
Many groundbreaking AI papers with thousands of citations are surprisingly simple and applied, like adding "let's think step by step" to the prompt, or simply asking the LLM over and over again to improve its answer (Self-Refine).
I realized there are tons of founders and builders in the same boat—wanting to dive deeper into AI but unsure where to start.
I've created an essential AI Guide that helped me catch up, in just 2 weeks, to the frontier of public AI research to figure out where the next opportunities and gaps were:
- Curated list of only the most important papers
- Simple explanations of key concepts
- Clear pathway to understanding the frontier of modern AI
It’s perfect for:
- Founders expanding into AI
- Builders wanting to innovate at the frontier of AI
- Investors looking to separate the signal from the noise
👇 Want the full guide?
- Like and Share this post
- Comment "AI Guide"
- I'll send you the complete guide
(ps, I’m also teaming up with @VishalVasishth, co-founder of @obviousvc with @ev (focused on large-scale societal impact companies like Twitter, Medium, Beyond Meat), to host a small meetup to discuss what's working and needs to be solved in the AI stack in SF. Message me if you're interested)
Saharsh Patel, MD retweeted
OpenEvidence started as the place clinicians go to find clinical evidence. Now they're becoming the place medical societies go to CREATE it - that's a whole new moat for winning the AI CDS market. My 5 thoughts...
First, the gist of what OpenEvidence announced:
→ The American Academy of Otolaryngology-Head and Neck Surgery Foundation (AAO-HNSF) and OpenEvidence have partnered to keep clinical practice guidelines current using AI-augmented literature surveillance
→ OpenEvidence built a custom methodology with AAO-HNSF that systematically compares existing guideline recommendations against current medical literature.
→ The system flags specific recommendations for review when new evidence either supports revising the existing guidelines or reaffirms it.
→ AAO-HNSF has already applied this to several of its existing clinical practice guidelines. The goal is to make it easier and faster for societies to keep guidelines up-to-date.
My 5 thoughts on this strategy and what it means for the AI CDS industry:
1/ OpenEvidence has strengthened its market position by going beyond simply licensing clinical content from medical societies and journals. By creating a way to add value to medical societies directly, and thus create some dependency for medical societies on OE, it incentivizes those societies to encourage their members to choose OE over other tools.
2/ This is awesome for clinical guideline maintenance. Many clinical practice guidelines become outdated because too many years can go by without a review or updates simply because doing a review is very time and labour intensive. It’s increasingly difficult because the pace of research outpaces our ability to incorporate them into guidelines. By reducing friction to making such updates, we will see guideline updates skyrocket.
3/ In the past, some clinicians may have minimized the value of guidelines because they could be quickly out of date. But if these tools can truly make guidelines more current, the clinician community will be even more willing to use them. This will lead to better patient care.
4/ This puts OE on a potential path to expansion beyond simply evidence search and curation and into opportunities of evidence generation itself. OE is starting by helping to update guidelines, but what if OE creates AI tools to suggest and draft not yet developed, brand new guidelines in the first place? That seems inevitable and the smart thing to do.
5/ This illustrates one of the powerful things about startups. OE has the freedom and courage to try new stuff like this very easily - how do the large incumbents move quickly enough to not just catch up but lead the way on product innovation? Unlike a big entrenched EHR, it’s hard to see how CDS products - even legacy ones - have much of a moat.
More from @EmreTKaratas can only mean good things for our industry
We are open-sourcing our investment hypotheses because the best ideas in healthcare benefit from pressure-testing out in the open. Check out the first 3 here → virtuevc.com/writings
More hypotheses to come and feedback is welcome!
4
309
Saharsh Patel, MD retweeted
Imagine if the federal government paid for all the SaaS in the US. And before you could sell software you had to get a SKU and price assigned by the government. You would not have a software industry.
That's how healthcare works today. And it's why cash payment via HSA (paired with catastrophic insurance for e.g. hospital admissions) is probably the right future vision for US healthcare versus code-based reimbursement.
Any code-based reimbursement system will never be able to anticipate the cambrian explosion of new services AI will offer.
Furthermore, in this analogy Asana and Monday would get the same SKU for something like "TASK MGMT SOFTWARE FOR ENTERPRISES" and therefore be given the same reimbursement.
"But Asana is way better and more featureful than Monday!" you say. "It's crazy that it would be the same price, they should be able to charge more!"
Great point, and another reason to favor cash pay futures. You can't discriminate on quality, convenience, or other preferences consumers might like to express.
We should keep working on codes and models like CMMI's ACCESS, but in parallel the better end state is way more direct HSA/cash payment in American healthcare.
Replying to @DrDiGiorgio @GreenPlusAnE
If you simply let people keep their own money and get a true catastrophic plan, the median American would have around $2M in real dollars by retirement. That covers lifetime healthcare costs for 90% of people with no government involvement.
Saharsh Patel, MD retweeted
I know this might sound crazy, but people who have real direct patient care experience should own and operate our healthcare system.
Saharsh Patel, MD retweeted
Let’s all be honest… who is the most likely to put the patient first?
1) physician
2) insurance company
3) private equity
4) Wall Street
Now ask yourself which of those four are banned from owning hospitals and see if your answer is the same as the first question
Questions?
Saharsh Patel, MD retweeted
We have a food system that pays no attention to health, and the healthcare system that pays no attention to food.
Saharsh Patel, MD retweeted
Due in part to the large number of runaway takes in medical AI, I'm launching a regular thread to spotlight noteworthy and more leveled research papers in the space and/or related fields with promising applications in healthcare.
RTs appreciated. Let's begin!
Saharsh Patel, MD retweeted
You can tell just by looking at this progression that this was a labor of love for a lot of very smart people.
Saharsh Patel, MD retweeted
It’s hard to imagine how bad things would be if the bullet were one inch over.
Hopefully people take this moment to realize we’ve hit total rock bottom in our divisiveness, but miraculously we got the chance to avoid what I think would have been complete civil unrest and chaos.
We badly need patriotism and to me that means actively combating the extreme political polarization we currently have however we can.





































