A trial result and what that result is being used to claim are two different things, and the gap between them is where most health coverage goes wrong. These briefs separate them: what was measured, in whom, over what period, who published it and what stake they hold — plus the structural side, from distribution chains to staffing. Nothing here is medical advice or care guidance, by design.
Drugs and trials · approvals and pricing · disease and condition briefs · health systems · clinical workforce
Tennessee, Mississippi, North Carolina, and other states are loosening or repealing CON rules as private-equity chains and REIT landlords consolidate hospitals those regulations were designed to oversee.
The weight of current evidence favors treating market-based reform and direct subsidy as complements rather than substitutes: the flagship federal response itself, the $50 billion Rural Health Transformation Program, funds…
Hospital closures and openings both follow financial and regulatory logic more than they follow raw community need: closures cluster where a mix of low occupancy, unfavorable private-insurance payment rates, for-profit or…
Rural America lost a net 234 hospitals (114 opened vs. 348 closed) between 2001-2023, even as urban areas posted a net gain of 11 (396 opened vs. 385 closed) — Health Care Affordability Lab at Yale.
The study, published in Nature Medicine as 'Divergent impacts of explainable AI for dermatological diagnosis on…
Key takeaways· 2▼
The accuracy boost non-experts got from AI explanations came from deference rather than better reasoning — when the model was wrong, they followed it, and the fluent written explanations inflated confidence most.
The design choice that changed the finding was feeding deliberately wrong AI answers to both groups; a study that only measures performance when the AI is right will overstate the tool's value.
When AI diagnostic advice was incorrect, physician diagnostic accuracy collapsed to 23.6%–26.1% (vs. 85.3%–92.8% when…
Key takeaways· 3▼
Physicians in a Johns Hopkins-affiliated study diagnosed correctly 92.8% of the time when the AI advice was right and 23.6% of the time when it was wrong — a 69-point swing set by the software, not the doctor.
Medical AI names the disease far better than it picks the treatment: one benchmarked system scored 89.3% on diagnosis and 53.0% on treatment, and that gap runs roughly 13 to 47 points across independent studies.
In one pathology study, doctors abandoned a correct diagnosis after a wrong AI suggestion in 7 of every 100 cases — errors that in pathology can mean cancer staged wrong.
A new $100,000 federal fee on each new work-visa petition led Frederick Health in Maryland to drop a plan to sponsor up to 45 international nurses, per CBS News reporting.
The federal agency that models health workforce needs once projected a surplus of more than 340,000 registered nurses by 2025; its current cycle projects an 8% national nurse shortage in 2028 instead.
Employer-based insurance pays hospitals roughly twice what Medicare does, while Medicare covers only 82-87% of the cost of care — which is why new hospital capacity gets built where commercially…
The main U.S. skilled-worker visa is close to unusable for nurses: because a standard bedside RN job does not require a bachelor's degree, the position fails the specialty-occupation test the H-1B is…
A four-phase nurse retention program works only if the first phase establishes what violence incidents are actually happening—most hospitals' logs capture reporting willingness rather than incidence…
◆
Run one on your own health question.
These were produced in minutes, from a URL or a sentence. So can yours.