After the Bitter Lesson
How healthcare AI actually gets built in the foundation model era.
How healthcare AI actually gets built in the foundation model era.
A field guide to healthcare AI’s most misused words, and the evidentiary realities they obscure.
A single phrase covers at least four different evidentiary realities. Learning to tell them apart is the first move in reading healthcare AI.
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…
Coronary artery calcium (CAC) scoring shows whether atherosclerosis is already in your coronary arteries. Inside the Agatston origin story, the MESA evidence base, the Power of Zero, the AI tools…
Two landmark studies published in Nature used AI-powered deep learning to show that thymic health predicts longevity, cardiovascular risk, and cancer immunotherapy outcomes, rewriting decades of assumptions about adult biology…
A peer-reviewed study published in Science finds OpenAI’s o1 model correctly diagnosed 67% of real emergency room cases, beating two attending physicians and triggering one of the most consequential debates…
Wearable glucose monitoring is moving beyond diabetes management toward a broader era of metabolic intelligence, where CGMs, rings, watches, and AI begin to connect food, sleep, stress, and exercise into…
The FDA’s anesthesiology category shows how medical AI is moving into sleep apnea detection, respiratory sound analysis, PAP therapy comfort, bedside monitoring, and the continuous physiology of everyday life.
FDA AI in urology is still early, with the current FDA list showing a smaller Gastroenterology-Urology category shaped by endoscopy, surgical robotics, and procedural vision.
Sign up for personalized wellness coaching and the Daily Discovery Newsletter.