Prospective vs Retrospective
The quiet difference between two kinds of validation studies decides whether a healthcare AI product will work in the world. Most published claims live on the wrong side of it.
How to Read a Healthcare AI Press Release
The healthcare AI press release is often the version of a claim most people ever encounter. This field guide shows how to read one in under ten minutes, using eight…
Surrogate Endpoints and the Long Wait for Truth
A measurable proxy for a clinical outcome is a useful tool, until the field forgets that the proxy is not the outcome. Healthcare AI and longevity science have not yet…
The Reproducibility Crisis Healthcare AI Refuses to Talk About
A growing body of evidence suggests that a meaningful share of healthcare AI’s published claims would not survive independent reproduction. The field has not yet decided to confront this.
After the Bitter Lesson
How healthcare AI actually gets built in the foundation model era.
FDA Cleared, FDA Approved, FDA Authorized
A field guide to healthcare AI’s most misused words, and the evidentiary realities they obscure.
What “Clinically Validated” Actually Means
A single phrase covers at least four different evidentiary realities. Learning to tell them apart is the first move in reading healthcare AI.
The Literature Is a Debate, Not a Record
Healthcare AI claims often arrive as facts. The safer way to read them is as arguments shaped by evidence, incentives, peer review, and the missing data still outside the published…
