Healthcare has spent the last two years talking about artificial intelligence as though the central question were model intelligence. The more consequential question is turning out to be system design. A new study from the Icahn School of Medicine at Mount Sinai published in npj Health Systems found that an orchestrated multi-agent setup sustained markedly stronger performance than a single general-purpose agent under simulated clinical workloads, with accuracy holding up far better as concurrent tasks increased and compute use dropping by as much as 65-fold.

The federal case against Anchorage rheumatologist Claribel Tan should not be read as a routine fraud prosecution with unusually vivid facts. In a March 17 sentencing release from the U.S. Attorney’s Office for the District of Alaska, the Department of Justice said the scheme involved more than $12.5 million in health care fraud, more than $4.2 million in tax loss, and conduct that stretched across 15 years. What makes the case editorially important is not only the money. It is the allegation that the fraud was built into treatment itself.

The latest administrative simplification rule from the Centers for Medicare & Medicaid Services may sound like a narrow technical update, but in its final rule fact sheet the agency says it creates the first HIPAA-adopted standards for health care claims attachments and electronic signatures.  That makes the policy less about retiring fax machines than about fixing one of healthcare’s oldest operational failures: the messy, manual handoff between clinical documentation and payment.

A common frustration in congenital cardiology is that the most consequential decisions still depend on piecing together partial views. Echocardiography excels at real-time valve motion but can be constrained by acoustic windows and angle dependence. CT provides crisp anatomy but cannot directly visualize flow and brings ionizing radiation into a population likely to need repeated imaging across a lifetime. Cardiac MRI can measure flow and tissue without radiation, yet clinical teams have often had to choose between images that show structure well and images that show hemodynamics well.