How healthcare systems actually behave

Healthcare interoperability, data platform architecture, and clinical AI, for the people who choose these systems, build them, and live with them — specific enough to be useful, opinionated enough to be wrong about.

Article · Data platforms
What a healthcare data platform is made of
The same two words describe an integration engine and a cloud lakehouse. Naming the parts, six components and two shared services, is what makes two very different platforms comparable.
October 15, 2026 · 14 min read
Article · Data platforms
On-Premises & Hybrid Clinical AI Framework
Running the model on hospital hardware answers latency, bandwidth and residency. It does not stop the data moving. The inference stays; the evidence, the updates and the accountability travel.
October 10, 2026 · 16 min read
Article · Applied AI
An AI agent is a client, not a user
SMART defines three subjects and an agent is none of them. What a record actually sees when a model asks it a question, and why the answer is usually one service account doing everything.
October 3, 2026 · 12 min read
Article · Applied AI
Clinical AI regulation: intended use determines the path
Intended use decides, not the architecture and not the accuracy. FDA rewrote the four criteria in January 2026, and three of them now read differently.
October 2, 2026 · 22 min read
Article · Applied AI
Imaging AI: six handoffs between the scanner and the chart
An imaging AI deployment is not one integration. It is six, each governed by a different standard, and the two nobody scopes are the last two: what the radiologist did with it, and who pays.
September 17, 2026 · 9 min read
Update · IHE
MADO: the imaging manifest becomes its own document
IHE Radiology published MADO in March and revised it in August. It takes the retrieve address out of the signed report, gives the manifest two encodings, and asks less of a server than XDS-I.b did.
September 12, 2026 · 8 min read
Article · Data platforms
The data platform is the evidence package
Of 691 AI devices the FDA cleared through July 2023, 95.5% never said who was in the training data. That is not a paperwork failure. It is a platform that could not produce the answer.
September 9, 2026 · 12 min read
Guide · Interoperability
IHE Radiology: how imaging systems are made to work together
DICOM and HL7 define the words. They do not define the conversation. IHE writes the conversation down, and Scheduled Workflow.b is the one running almost every radiology department.
August 31, 2026 · 11 min read
Guide · Interoperability
DICOM: not just a file format for medical images
Every scanner, archive and viewer on earth speaks DICOM. Almost every team building AI on medical images discovers, painfully, that it is a four-layer stack and not a header.
August 31, 2026 · 8 min read

Working on one of these problems?

Tell us what you’re working on in interoperability, data platforms, or clinical AI, and we’ll tell you what we think.