🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

But we know how to test efficacy in medicine. Clinical trials are messy, more expensive than in silico studies, and require multidisciplinary expertise. But they're still the right thing to do. Only 5% of LLM in medicine studies even use real data (pubmed.ncbi.nlm.nih.gov/39405325/)!!

Interesting to work with Adam and others on this dive into the performance of newer LLM models on clinical tasks. In summary, they’re getting technically better and we need to figure out how they could interface with actual medical care

Yup

The use of oseltamivir in the total absence of evidence of benefit meets the criteria of therapeutic fashion. Evidence-based practice has a long way to go.

Diagnostic stewardship, which extends to clinical medicine, and laboratory stewardship serve complementary roles & collaboration allows both programs to grow and improve patient care. Mini-Review by Kimberly Claeys, KC Coffey & Dan Morgan: buff.ly/3CCoX0y

Articles like this wear me out. It comes so close to discussing real problems - then parrots back the same platitudes. Do we *really* need more doctors? Or do we need a system that incentivizes doctors to practice in the ways/places we need, instead of doing the very opposite?

Great to see talk about Mindlines, evoking the great BMJ paper about actual clinical practice.

There is a lot of buzz about our new paper in Nature Medicine on the effects of LLMs (GPT-4) on physician management reasoning! I had TONS of fun working on this -- but what it MEANS requires some unpacking. A 🧵⬇️ x.com/EricTopol/stat…

Great work Jon Baghdadi

Among the 12 most commonly diagnosed cancers in the US, we found striking variability in the incidence/mortality relationship – with correlation coefficients ranging essentially from 0 (breast and thyroid cancer) to 1 (lung cancer): bmjopen.bmj.com/content/15/2/e…

De-Baathification was.... not a successful policy... like... famously... it was the source of most of America's challenges in Iraq for the years that followed... seems like maybe it really is an apt metaphor for the current strategy...

Great to hear about these SNAP trials, Emily McDonald !

Annual N95 fit-testing is still required based on 1 small study of 229 participants. In a study of 12,065 HCWs followed over 3 yrs, fit‑test failure was <0.5% (Martin et al). Annual fit‑testing still costs US healthcare ~$200–400 M/yr. Time to switch to every 3 years.

Requirement to throw away most medical equipment after single use is largely driven by extra barrier by ⁦FDA⁩ to prove safe to reuse. ⁦Dr. Martin Makary⁩, would you reconsider this? ⁦SHEA⁩ conference

Wild to hear about DeepSeek being used in Chinese hospitals. Seems risky but a snapshot of where things are going..... Worth a read Adam Rodman Preeti Malani jamanetwork.com/journals/jama/…

At the ⁦SHEA⁩ conference, Valeria Fabre talking about diagnostic stewardship! ⁦Valerie Vaughn⁩