Nisarg Patel, MD

@UCSF surgeon. Researching AI for clinical reasoning. Health policy for @FT, WaPo. Cofounder @memorahealth (acq). Alum @ycombinator w18, @harvardmed.

[Nisarg Patel, MD @nxpatel]

@nikillinit Their Doximity integration is fire - made it so easy to onboard.

[Nisarg Patel, MD @nxpatel]

@pnatarajanmd @Amgen They’re so lucky to have you, congrats Pradeep!

[Nisarg Patel, MD @nxpatel]

I think initial peer review of Doximity generated content is solicited from authors of cited papers for a given answer.

That being said I still do occasionally get misrepresented (and sometimes dangerous) management recs from evidence summaries across all these tools, so I’ll click into whichever citation(s) look highest quality to double check myself.

[Nisarg Patel, MD @nxpatel]

@doximity @slotkinjr The more inference the better!

[Nisarg Patel, MD @nxpatel]

Me teaching every surgeon I meet how to use ChatGPT for Clinicians / OpenEvidence.

[Grant Hesser @GrantHesser]

Forward Deployed Clinician (FDC)

[Nisarg Patel, MD @nxpatel]

Immensely proud.

[Malhar Patel @malharhar]

I wanted my first public video to be learnings from the past 7.5 years here at @AppliedInt. Hopefully it’s useful to the next set of builders 🐻

[Nisarg Patel, MD @nxpatel]

@icmlconf Any additional main conference spots available for workshop paper authors? Was able to register for the workshops but main conference is showing as sold out even with some time remaining for the early registration deadline.

[Nisarg Patel, MD @nxpatel]

@dvasishtha Stark (and welcome) reversal from the “single line item” perspective of 2010s health IT procurement.

[Nisarg Patel, MD @nxpatel]

@nikillinit The closest thing I’ve seen to this is the Red Dot museum in Singapore. Some of the healthcare hardware on display (some in the metal, some on posters) felt like sci-fi.

[Dhruv Vasishtha @dvasishtha]

Quick piece of advice for clinicians being offered equity to join a startup’s clinical or scientific advisory board:

Its total BS when a founder says, “We’re offering you 10,000 shares. That’s 0.1% of the company, and since we just raised at a $100M valuation, that’s $100K of value.”

That is not really how it works. Your common shares are not worth the same as the preferred shares investors just bought. There will likely be future dilution. And the paper value is not the same as actual economic value.

Clinicians should evaluate these roles differently than typical startup advisors because you are not just giving advice. You are lending credibility, validation, and halo to the company’s care model.

The real questions are:
- Do you trust the founders and feel comfortable vouching for them?
- Do you believe the problem they are solving matters?
- Do you believe in the care model they are building?
- Do you believe the product can actually improve care?

If the answer is yes, the opportunity may still be worth it for the learning, relationships, and ecosystem connectivity.

But if you want to evaluate the economics, ask the founder directly: how much dilution do you expect the common stock to take, and what would my advisor shares be worth pre-tax in a low, base, and high exit case?

[Jaya Gupta @JayaGup10]

https://t.co/IcLsopvUhQ

[Nisarg Patel, MD @nxpatel]

Healthcare is one of the few sectors where policy has arguably *driven* tech innovation and diffusion rather than vice-versa.

With that in mind, there are plenty of policy levers in both public health and medicine that are positive-sum! Reference pricing to promote service competition and better correlate price to quality, all payer rate setting (e.g., Maryland) to reduce admin complexity, lead removal from paint/water to reduce childhood lead toxicity and resulting healthcare costs, etc. Even tech-specific policies like Cures and TEFCA that improve interop will likely reduce admin overhead as CMS rolls out implementation details over the next few years.

Until we see more policy movement and the implementation science (via academics or industry) to adopt and expand new system-level incentives and interventions, most newcos will, very reasonably, try to maximize adoption by operating within the tradeoffs of cost/quality/access rather than maximizing clinical value per dollar.

[yoni rechtman @yrechtman]

Most healthcare “innovation” is zero-sum at best, negative-sum at worst. I want to see more more positive sum HC ideas that grows the surplus rather than shifting it around

[Nisarg Patel, MD @nxpatel]

@nikillinit “I went to a small accelerator before it moved to SF”

[Nisarg Patel, MD @nxpatel]

I think AI surfacing guidelines/most up-to-date treatment options is okay! I’m optimistic that most physicians will either agree with those recs (and honestly, some may be seeing new guidelines for the first time and be better for it) or apply their own judgment as to why a specific patient case/goals differs from those guidelines in a way that merits patient-specific treatment.

The way I describe it to trainees is that these tools, at the very least, elevate the floor for medical decision making.

There’s still a missing layer in most models (even the medical ones) about guiding clinical decisions with imperfect information, particularly as many of these society guidelines start to unravel as patients become more medically complex, but that’s a model architecture/system prompt conversation.

[Nisarg Patel, MD @nxpatel]

How long until this is a standard ask for health systems fielding agent vendors? cc @arieldora

[Mati Staniszewski @mati]

Voice agents built with ElevenLabs can now be covered with insurance - in the same way that human agents can!

A first of its kind - adding real risk coverage and accountability, even for the toughest edge cases.

https://t.co/5IKndEXHKI

[Nisarg Patel, MD @nxpatel]

@nikillinit It’s starting https://t.co/op5ZNouGU8

[Nisarg Patel, MD @nxpatel]

Specialty-specific instance of course, but a few years ago Epic added the ability to take photos from their mobile app and automatically upload it into a patient chart, which turned out to be invaluable for documenting pre-/postop facial photos and (manually) following oral/facial lesions, scars, bruising, etc. Particularly useful for referencing in cases where multiple residents were following the same patient over time.

[Nisarg Patel, MD @nxpatel]

@dvasishtha Still true
https://t.co/Mmleh32Giu

[Nisarg Patel, MD @nxpatel]

@B_Madden4 Honestly I’ve thought about this @ddiamond article at least once a week for the last 8 years. https://t.co/xTClAKNS0W